WO2020036710A1 - Methods and apparatus for facial recognition - Google Patents
Methods and apparatus for facial recognition Download PDFInfo
- Publication number
- WO2020036710A1 WO2020036710A1 PCT/US2019/043008 US2019043008W WO2020036710A1 WO 2020036710 A1 WO2020036710 A1 WO 2020036710A1 US 2019043008 W US2019043008 W US 2019043008W WO 2020036710 A1 WO2020036710 A1 WO 2020036710A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- requester
- visible light
- faceplate
- biometric
- face
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 106
- 230000001815 facial effect Effects 0.000 title claims description 57
- 238000005070 sampling Methods 0.000 claims abstract description 33
- 230000003287 optical effect Effects 0.000 claims description 37
- 238000005286 illumination Methods 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 description 78
- 238000004422 calculation algorithm Methods 0.000 description 76
- 230000005855 radiation Effects 0.000 description 43
- 238000005259 measurement Methods 0.000 description 39
- 238000012795 verification Methods 0.000 description 36
- 230000008569 process Effects 0.000 description 34
- 238000004891 communication Methods 0.000 description 30
- 238000012545 processing Methods 0.000 description 29
- 239000011159 matrix material Substances 0.000 description 28
- 238000003860 storage Methods 0.000 description 27
- 239000000523 sample Substances 0.000 description 25
- 238000013135 deep learning Methods 0.000 description 23
- 230000006870 function Effects 0.000 description 22
- 238000004458 analytical method Methods 0.000 description 17
- 238000004590 computer program Methods 0.000 description 15
- 239000011521 glass Substances 0.000 description 10
- 210000000887 face Anatomy 0.000 description 9
- 238000012360 testing method Methods 0.000 description 9
- 238000009826 distribution Methods 0.000 description 8
- 230000008901 benefit Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 6
- 230000035515 penetration Effects 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 6
- 210000004207 dermis Anatomy 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 239000002245 particle Substances 0.000 description 5
- 230000002829 reductive effect Effects 0.000 description 5
- 238000012546 transfer Methods 0.000 description 5
- 238000003491 array Methods 0.000 description 4
- 239000000835 fiber Substances 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000000670 limiting effect Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000002787 reinforcement Effects 0.000 description 4
- 230000002207 retinal effect Effects 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 102100029235 Histone-lysine N-methyltransferase NSD3 Human genes 0.000 description 3
- 101100461044 Homo sapiens NSD3 gene Proteins 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000005670 electromagnetic radiation Effects 0.000 description 3
- 230000005021 gait Effects 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 208000002874 Acne Vulgaris Diseases 0.000 description 2
- 241001303601 Rosacea Species 0.000 description 2
- 206010000496 acne Diseases 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000001010 compromised effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 210000005069 ears Anatomy 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 208000000069 hyperpigmentation Diseases 0.000 description 2
- 230000003810 hyperpigmentation Effects 0.000 description 2
- 208000016339 iris pattern Diseases 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 150000004032 porphyrins Chemical class 0.000 description 2
- 230000036544 posture Effects 0.000 description 2
- 201000004700 rosacea Diseases 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 210000003491 skin Anatomy 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000009056 telangiectasis Diseases 0.000 description 2
- KJLPSBMDOIVXSN-UHFFFAOYSA-N 4-[4-[2-[4-(3,4-dicarboxyphenoxy)phenyl]propan-2-yl]phenoxy]phthalic acid Chemical compound C=1C=C(OC=2C=C(C(C(O)=O)=CC=2)C(O)=O)C=CC=1C(C)(C)C(C=C1)=CC=C1OC1=CC=C(C(O)=O)C(C(O)=O)=C1 KJLPSBMDOIVXSN-UHFFFAOYSA-N 0.000 description 1
- 206010004950 Birth mark Diseases 0.000 description 1
- 230000005457 Black-body radiation Effects 0.000 description 1
- 238000001712 DNA sequencing Methods 0.000 description 1
- 206010052128 Glare Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005388 cross polarization Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000004313 glare Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 206010033675 panniculitis Diseases 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 210000004304 subcutaneous tissue Anatomy 0.000 description 1
- 238000001757 thermogravimetry curve Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/08—Key distribution or management, e.g. generation, sharing or updating, of cryptographic keys or passwords
- H04L9/0861—Generation of secret information including derivation or calculation of cryptographic keys or passwords
- H04L9/0866—Generation of secret information including derivation or calculation of cryptographic keys or passwords involving user or device identifiers, e.g. serial number, physical or biometrical information, DNA, hand-signature or measurable physical characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
- H04L9/3231—Biological data, e.g. fingerprint, voice or retina
Definitions
- a requester may be a user/person that requests access to an access controlled assets and/or infrastructure.
- a requester may carry and use a key, which is designed to fit a lock to allow the requester of the key to open the lock and gain entry. A loss or damage to the key, however, can render access impossible.
- a requester may use a key fob to remotely lock or unlock the doors of a vehicle by, e.g., pressing a button on the fob to generate an infrared ("IR") or radio frequency (“RF”) signal, which is detected by a sensor in the vehicle, which controls the doors.
- IR infrared
- RF radio frequency
- Such vehicle keyless access systems may require the requester to operate the ignition system.
- Other similar keyless access implementations may involve inserting and presenting a magnetic card or the like in a slot or a card reader/detector, or enabling an authorized requester to key in a numeric or alphanumeric code on a provided keypad. In each of these conventional techniques, however, it is very difficult to determine if the person holding the key/card is the actual authorized requester. An imposter may steal or duplicate a valid key and gain unauthorized accesses to the premise, vehicle, and/or personal property.
- biometrics access control systems may mitigate some shortcomings of keys/cards-based access control systems, there may be limitations as well.
- Traditional biometric sensors such as iris detection sensors, may be limited to specific light conditions significantly reducing both the effectiveness of the biometric sensor as well as the possible environments to apply same.
- the performance of biometric sensors may be compromised in direct sunlight due to glares, shadows, and other artifacts.
- Even with the emergence of mega pixel camera technology the features of each face may be obscured by ambient lighting, the position of the face, changes to the face, the background behind the face and the quality of the camera. Motion blur, insufficient resolution, environmental impacts, lighting, background, and camera angles collude to obscure subject details, making heterogeneous facial recognition (the matching of video and other probe images to large databases of frontal photographs) difficult.
- biometric sensors also have difficulties obtaining the necessary data in the absence of light. Light source shadowing and other changes in intensity may create contrasts on the face that may be misinterpreted as facial features, and/or slightly distort the measurement of the real facial features. Another major source of inaccuracy is the increased probability of similar measured features between faces in a growing population. Further, the problem of capturing the features of each face may be compounded by the desire for low maintenance and/or low complexity facial recognition systems. Therefore, improvement in access control may be desired.
- Some aspects of the present disclosure include methods for generating a heatmap including a plurality of sampling points having a plurality of characteristic values associated with the detected non-visible light, identifying one or more macroblocks each includes a subset of the plurality of sampling points, selecting a local pattern value, calculating a number of occurrences of the local pattern value within each subset of the plurality of the sampling points for each of the one or more macroblocks, generating a first array including a plurality of weighted values by calculating the plurality of weighted values based on the numbers of occurrences of the local pattern value and corresponding sizes of the one or more macroblocks, assigning a unique index to each of the plurality of weighted values, generating a second array of the unique index by ranking the plurality of weighted values, and generating a third array including a plurality of ranking distances.
- Certain aspects of the present disclosure include a faceplate having an illumination source configured to emit an incident non-visible light, an optical sensor configured to detect a detected non-visible light, wherein the detected non-visible light includes a reflected non- visible light and a radiated non-visible light, one or more processors operatively coupled to the illumination source and the optical sensor, the one or more processors are configured to construct a biometric template of a requester requesting access to an entry point by generating a heatmap including a plurality of sampling points having a plurality of characteristic values associated with the detected non-visible light, identifying one or more macroblocks each includes a subset of the plurality of sampling points, selecting a local pattern value, calculating a number of occurrences of the local pattern value within each subset of the plurality of the sampling points for each of the one or more macroblocks, generating a first array including a plurality of weighted values by calculating the plurality of weighted values based on the numbers of occurrences of the local pattern value and
- aspects of the present disclosure include a computer readable medium having code stored therein that, when executed by one or more processors, cause the one or more processors to execute code for generating a heatmap including a plurality of sampling points having a plurality of characteristic values associated with the detected non-visible light, code for identifying one or more macroblocks each includes a subset of the plurality of sampling points, code for selecting a local pattern value, code for calculating a number of occurrences of the local pattern value within each subset of the plurality of the sampling points for each of the one or more macroblocks, code for generating a first array including a plurality of weighted values by calculating the plurality of weighted values based on the numbers of occurrences of the local pattern value and corresponding sizes of the one or more macroblocks, code for assigning a unique index to each of the plurality of weighted values, generating a second array of the unique index by ranking the plurality of weighted values, and code for generating a third array including
- An aspect of the present disclosure includes a system having means for generating a heatmap including a plurality of sampling points having a plurality of characteristic values associated with the detected non-visible light, means for identifying one or more macroblocks each includes a subset of the plurality of sampling points, means for selecting a local pattern value, means for calculating a number of occurrences of the local pattern value within each subset of the plurality of the sampling points for each of the one or more macroblocks, means for generating a first array including a plurality of weighted values by calculating the plurality of weighted values based on the numbers of occurrences of the local pattern value and corresponding sizes of the one or more macroblocks, means for assigning a unique index to each of the plurality of weighted values, generating a second array of the unique index by ranking the plurality of weighted values, and means for generating a third array including a plurality of ranking distances.
- aspects of the present disclosure include an infrastructure having an access-controlled entry point, a faceplate configured to emit an incident non-visible light onto a face of a requester, detect a detected non-visible light from the face of the requester, wherein the detected non-visible light includes a reflected non-visible light and a radiated non-visible light, generate a biometric template of the requester by generating a heatmap including a plurality of sampling points having a plurality of characteristic values associated with the detected non-visible light, identifying one or more macroblocks each includes a subset of the plurality of sampling points, selecting a local pattern value, calculating a number of occurrences of the local pattern value within each subset of the plurality of the sampling points for each of the one or more macroblocks, generating a first array including a plurality of weighted values by calculating the plurality of weighted values based on the numbers of occurrences of the local pattern value and corresponding sizes of the one or more macroblocks, assigning a unique
- FIG. 1 is an example concurrent real-time identity verification and authentication system, in accordance with some aspects of the present disclosure
- FIG. 2 shows a perspective view of an example of a concurrent real-time identity verification and authentication device, in accordance with some aspects of the present disclosure
- FIG. 3 shows a frontal view of an example of a concurrent real-time identity verification and authentication device, in accordance with some aspects of the present disclosure
- FIG. 4 shows another perspective view of an example of a concurrent real-time identity verification and authentication device, in accordance with some aspects of the present disclosure
- FIG. 5 is a block diagram of an example processing component of a concurrent real time identity verification and authentication device, in accordance with some aspects of the present disclosure
- FIG. 6 shows a flow diagram of a facial recognition method, in accordance with some aspects of the present disclosure
- FIG. 7(a) shows a facial image for a person, in accordance with some aspects of the present disclosure
- FIG. 7(b) shows a different facial image for the same person, in accordance with some aspects of the present disclosure
- FIG. 8 shows an example process for calculating local binary pattern (LBP) feature, in accordance with some aspects of the present disclosure
- FIG. 9 shows an example process for calculating local ternary pattern (LTP) feature, in accordance with some aspects of the present disclosure
- FIG. 10 shows positions of three example key features selected among one or more face images, in accordance with some aspects of the present disclosure
- FIG. 11 shows an example of a receiver operating characteristic (ROC) curve for testing a face database, in accordance with some aspects of the present disclosure
- FIG. 12 illustrates an example of biometric, asymmetric encryption for confidentiality, in accordance with some aspects of the present disclosure
- FIG. 13 illustrates another example of biometric, asymmetric encryption for authentication, in accordance with some aspects of the present disclosure
- FIG. 14 illustrates a schematic view of an example of an environment for implementing one or more gateways for access control
- FIG. 15 illustrates an example of a computer system for implementing a method of managing data in accordance with aspects of the present disclosure
- FIG. 16 illustrates a block diagram of various exemplary system components, in accordance with aspects of the present disclosure
- FIG. 17 illustrates an example of a faceplate for identifying biometric templates, in accordance with aspects of the present disclosure
- FIG. 18 illustrates an example of the components of the faceplate of FIG. 17, in accordance with aspects of the present disclosure
- FIG. 19 illustrates another example of the components of the faceplate of FIG. 17, in accordance with aspects of the present disclosure
- FIG. 20 illustrates an example of a heatmap, in accordance with aspects of the present disclosure
- FIG. 21 illustrates an example of LBP operation on measurement points of the heatmap of FIG. 20, in accordance with aspects of the present disclosure
- FIG. 22 illustrates examples of sub-matrices
- FIG. 23 illustrates an example of a table of results for sequence conversion, in accordance with aspects of the present disclosure
- FIG. 24 illustrates an example of a flow chart for converting a sequence, in accordance with aspects of the present disclosure
- FIG. 25 illustrates an example of a table of verification calculations, in accordance with aspects of the present disclosure
- FIG. 26 illustrates an example of deep learning
- FIG. 27 illustrates the example of deep learning in FIG. 27 .
- FIG. 28 illustrates a flow chart of a method for identifying biometric templates.
- a “bus,” as used herein, refers to an interconnected architecture that is communicatively coupled to transfer data between computer components within a singular or multiple systems.
- the bus may be a memory bus, a memory controller, a peripheral bus, an external bus, a crossbar switch, and/or a local bus, among others.
- the bus may also be a vehicle bus that interconnects components inside a vehicle using protocols, such as Controller Area network (CAN), Local Interconnect Network (LIN), among others.
- CAN Controller Area network
- LIN Local Interconnect Network
- a “memory,” as used herein may include volatile memory and/or non-volatile memory.
- Non-volatile memory may include, for example, ROM (read only memory), PROM (programmable read only memory), EPROM (erasable PROM) and EEPROM (electrically erasable PROM).
- Volatile memory may include, for example, RAM (random access memory), synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), and/or direct RAM bus RAM (DRRAM).
- Ranges may be expressed herein as from “about,” “substantially,” or “approximately” one particular value and/or to "about,” “substantially,” or “approximately” another particular value. When such a range is expressed, another implementation includes from the one particular value and/or to the other particular value.
- comprising or “containing” or “including” is meant that at least the named compound, element, particle, or method step is present in the composition or article or method, but does not exclude the presence of other compounds, materials, particles, method steps, even if the other such compounds, material, particles, method steps have the same function as what is named.
- Biometric identification techniques generally refer to pattern recognition techniques that perform a requester identification process by determining the authenticity of a specific physiological or behavioral characteristic possessed by the requester.
- biometric identification may be preferred over traditional methods involving passwords and personal identification numbers (PINs) for various reasons.
- PINs personal identification numbers
- the person (e.g., requester) to be identified is typically required to be physically present at the point-of-identification.
- identification based on biometric techniques obviates the need to remember a password or carry a token (i.e., a security device used to gain access to an access controlled entry point).
- LBP texture based local binary pattern
- LTP local ternary pattern
- biometric signature data for providing keyless access to authorized requesters to a vehicle, building, or the like with varying degrees of security by utilizing various types of biometric data of authorized requesters.
- the biometric signature data may be interchangeable across a wide variety of applications. Accordingly, in some examples of the present disclosure, the same biometric signature data for a person may be used to authenticate that person at one or more locations and for one or more applications. Additionally, an example of a biometric system in the present disclosure allows the biometric signature data to be altered based on a desired security level.
- biometric signature data that may be used for a particular application and/or relating to a particular requester may vary depending on the security level desired for that particular application and/or requester. While some implementations discussed herein are discussed in the context of facial biometric data, those skilled in the art would understand that various implementations of the present disclosure may employ many types of biometric data, including, but not limited to, fingerprint data, iris and retinal scan data, speech data, facial thermograms, hand geometry data, and the like. [52] In some implementations of the present disclosure, the biometric data associated with the intended recipient (e.g., a biometric template) may be obtained via a biometric sensor of a biometric-based access control system.
- the biometric sensor may utilize either near infrared (IR) or ultraviolet (UV) light or a combination of both IR and UV at desired intensities. In an implementation, the method uses near IR light.
- IR near infrared
- UV ultraviolet
- An Infrared light emitting diode (LED) array may be utilized in the facial recognition device or biometric sensor to minimize the impact of the surrounding lighting on capturing the facial uniqueness.
- the camera and the LED array are packaged into a dedicated edge device (e.g., a faceplate) mounted at a location requiring verification and/or identification/analysis, such as a door requiring access control.
- an access control system may utilize IR or new IR illumination and detection to identify facial features.
- IR or new IR lighting may penetrate into the dermis of the face.
- the IR or new IR lighting may penetrate into the dermis by 10 micrometers, 20 micrometers, 50 micrometers, 100 micrometers, 200 micrometers, 500 micrometers, 1 millimeters, 2 millimeters, 5 millimeters, and/or 10 millimeters. Other penetration depths are possible. The penetration depths may depend on the location of the body, wavelength of the infrared lighting, and/or intensity of the infrared lighting.
- the penetration may expose characteristics of the skin that may be difficult to see in visible light including (age spots, spider veins, hyperpigmentation, rosacea, acne, and porphyrins).
- the identification of these subdermal features may be used to adjust/supplement the unique identification of the requester.
- These features on the face of the requester may be unique because they are based on the requesters exposure to nature and the sun over the life of the requester.
- Facial recognition based on subdermal features may identify the uniqueness of the face at the time of capture to provide opportunities for identification analysis. The number of subdermal features may increase over time with exposure to the sun and on a daily basis.
- an access control system may utilize ultraviolet illumination and detection to identify facial features.
- Ultraviolet lighting may penetrate into the dermis of the face.
- the UV lighting may penetrate into the dermis by 10 micrometers, 20 micrometers, 50 micrometers, 100 micrometers, 200 micrometers, 500 micrometers, 1 millimeters, 2 millimeters, 5 millimeters, and/or 10 millimeters.
- Other penetration depths are possible.
- the penetration depths may depend on the location of the body, wavelength of the ultraviolet lighting, and/or intensity of the ultraviolet lighting.
- the penetration may expose characteristics of the skin that may be difficult to see in visible light including (age spots, spider veins, hyperpigmentation, rosacea, acne, and porphyrins).
- the identification of these subdermal features may be used to adjust/supplement the unique identification of the requester.
- These features on the face of the requester may be unique because they are based on the requesters exposure to nature and the sun over the life of the requester.
- Facial recognition based on subdermal features may identify the uniqueness of the face at the time of capture to provide opportunities for identification analysis.
- the number of subdermal features may increase over time with exposure to the sun and on a daily basis.
- the facial recognition system of the present disclosure may estimate the age of a person based on the quantity and nature of the subdermal features.
- the access control system may also track the change in these features over time to confirm the individual’s identity and establish lifestyle and daily routines based on interpretations of the subdermal features.
- Subdermal facial recognition may also increase the difficulty of creating a duplicate (e.g., duplicate of a biometric template) of the face due to its elimination of dependency on facial features capable of being captured by standard visible wavelength photography and camera technology.
- the access control system may also further obfuscate the content of the ultraviolet capture by introducing time-sequenced cross-polarization filters to the capturing process that further eliminates the ability to present an artificial duplicate of the face to the access control system.
- a benefit of the system in the present disclosure includes allowing a single credential system replacing PINs, passwords, and multi-factor authentication that is seamless to the requester. With this architecture in place, the requester(s) of the system may rely on a single credential management solution.
- the system of the present disclosure may support both logical and physical gateways. In some implementations of the present disclosure, the system may provide protection at home and at work.
- aspects of the present disclosure may include a method referred to as“layered reinforcement.”
- the method comprises of taking the image of face from the biometric sensor and overlaying several layers of different size pixel boxes on the image. This layering of pixel boxes of different sizes has an amplifying impact on the analysis of the uniqueness of the face. Areas that are more unique to the face are amplified. Areas that are more common among faces are deemphasized.
- layered reinforcement may improve the algorithm performance while allowing the method to handle a large number of users at multiple sites where the biometric sensor faceplate is deployed.
- The“layer reinforcement” of the method may allow for the processing of the same number of requesters on a local Advanced Reduced Instruction Set Computing Machine (ARM) processor at the biometric sensor faceplate where the image is first captured, thus reducing hardware and processing requirements and contributing to the accuracy and reliability of the method as a network failure cannot prevent the biometric sensor faceplate from processing a face verification.
- ARM Advanced Reduced Instruction Set Computing Machine
- Some aspects of this embodiment of the invention cover the use of a gateway (described below) to manage the data analyzed by the various algorithms to increase performance by decreasing false negative and false positive results through the following processes: pixel box hierarchical analysis to create binary tree of dominant features (i.e., determining what is the most distinctive feature); pixel box time domain analysis with heat maps (i.e., determining over time features that are problematic due to overlap among subjects); and binary tree collision (flagging overlap of biometric signature data for two subjects that may cause a false positive and addressing in a proactive fashion).
- pixel box hierarchical analysis to create binary tree of dominant features (i.e., determining what is the most distinctive feature)
- pixel box time domain analysis with heat maps i.e., determining over time features that are problematic due to overlap among subjects
- binary tree collision flagging overlap of biometric signature data for two subjects that may cause a false positive and addressing in a proactive fashion.
- Benefits to the system of the present disclosure include improved performance when accuracy requires reduction in false negative and false positive results.
- the improvement also allows for the benefits of 1:1 comparison in a l:N environment as a potential replacement to video surveillance and comparison thereby opening up the massive surveillance market to significantly increased accuracy.
- FIG. 1 an example of an identification system 100 for concurrent real time identity verification and authentication for use in, e.g., allowing access by an authorized requester to a vehicle, building, or the like is illustrated in accordance with aspects of the present disclosure.
- FIG. 1 is intended to describe aspects of the disclosure to enable those skilled in the art. Other implementations may be utilized and changes may be made without departing from the scope of the present disclosure.
- the identification system 100 comprises a concurrent real-time identity verification and authentication device 102 including at least one biometric sensor 104, a processor 106, memory 108, a display 110, and input/output mechanism 112.
- the identification system 100 may be used to secure or control access to a secured area, device, or information, such as an airport boarding area, building, stadium, database, locked door, vehicle, or other access controlled assets/infrastructure.
- the biometric sensor(s) 104 may include a camera, a fingerprint reader, retinal scanner, facial recognition scanner, weight sensor, height sensor, body temperature sensor, gait sensor, heartbeat sensor, or any other sensor or device capable of sensing a biometric characteristic of a person. As shown in FIGS. 2-4, in an exemplary implementation of the present disclosure, the biometric sensor(s) 104 may be an optical sensor, such as a camera.
- the biometric sensor(s) 104 may include an optical sensor that captures visual data.
- the biometric sensor(s) 104 may be a camera that senses visual information of a requester, such as the facial features of the person.
- the facial features of the person may include the textures, complexions, bone structures, moles, birthmarks, contours, coloring, of the face of the person.
- the biometric sensor(s) 104 may capture the facial features of the person and convert the visual information into digital sensed information as discussed below).
- the processor 106 may be configured for comparing the sensed information via biometric sensor(s) 104 with known characteristics of a person in an attempt to identify the person via biometric signature data.
- the processor 106 may include any number of processors, controllers, integrated circuits, programmable logic devices, or other computing devices.
- the processor 106 may be communicatively coupled with the biometric sensor(s) 104 and other components of the system 100 through wired or wireless connections to enable information to be exchanged between the device 102 and external devices 114 or systems (e.g., network 116) to allow for comparison of the stored biometric signature data with the sensed information obtained from the biometric sensor(s) 104.
- the processor 106 may implement a computer program and/or code segments stored on memory 108 to perform some of the functions described herein.
- the computer program may include an ordered listing of executable instructions for implementing logical functions in the device 102.
- the computer program can be embodied in any computer-readable medium (e.g., memory 108) for use by or in connection with an instruction execution system, apparatus, or device, and execute the instructions.
- the memory 108 may contain, store, communicate, propagate or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
- Examples of memory 108 may include an electrical connection having one or more wires, a random access memory (RAM), a read only memory (ROM), an erasable, programmable, read-only memory (EPROM or Flash memory), a portable computer diskette, or a portable compact disk read-only memory (CDROM).
- RAM random access memory
- ROM read only memory
- EPROM or Flash memory erasable, programmable, read-only memory
- CDROM compact disk read-only memory
- the memory 108 may be integral with the device 102, a stand-alone memory, or a combination of both.
- the memory 108 may include, for example, removable and non- removable memory elements such as RAM, ROM, Flash, magnetic, optical, USB memory devices, and/or other conventional memory elements.
- the memory 108 may store the known characteristics of a number of people and various other data associated with operation of the system 100, such as the computer program and code segments mentioned above, or other data for instructing the device 102 and other device elements to perform the aspects described herein.
- the various data stored within the memory 108 may be associated within one or more databases (not shown) to facilitate retrieval of the information, e.g., via the external devices 114 or the network 116.
- the memory 108 as shown in FIG. 1 is integrated into the device 102, it should be appreciated that memory 108 may be stand-alone memory positioned in the same enclosure as the device 102, or may be external memory accessible by the device 102.
- the display 110 may be configured to display various information relating to the system 100 and its underlying operations.
- a notification device may be included (not shown) for indicating the sensed biometric characteristic or the sensed signal fail to match the known characteristics of the person and may include an audible alarm, a visual alarm, and/or any other notification device.
- the device 102 may also include input/output mechanism 112 to facilitate exchanging data and other information among different components within the device 102, or with various the external devices 114 or systems via the network 116.
- various I/O ports may be contemplated including a Secure Disk Digital (SD) card slot, Mini SD Card slot, Micro SD Card slot or the like for receiving removable SD cards, Mini SD Cards, Micro SD Cards, or the like, and a USB port for coupling with a USB cable communicatively coupled with another computing device such as a personal computer.
- the input/output mechanism 112 may include an input device (not shown) for receiving identification information about a person-to-be-identified.
- the input device may include a ticket reader, a credit card reader, an identification reader, a keypad, a touch screen display, or any other device.
- the input/output mechanism 112 may be configured to enable the device 102 to communicate with other electronic devices through the network 116, such as the Internet, a local area network, a wide area network, an ad hoc or peer to peer network, or a direct connection such as a USB, Firewire, or BluetoothTM connection, etc.
- known characteristics about persons may be stored and retrievable in remote databases or memory via the network 116.
- the input/output mechanism 112 may thus communicate with the network 116 utilizing wired data transfer methods or wireless data transfer methods such as WiFi (802.11), Wi- Max, BluetoothTM, ANT ® , ultra-wideband, infrared, cellular telephony, radio frequency, etc.
- the input/output mechanism 112 may include a cellular transceiver for transmitting and receiving communications over a communications network operable with GSM (Global System for Mobile communications), CDMA (Code Division Multiple Access), or any other known standards.
- the device 102 may also include a power source (not shown) for providing electrical power to the various components contained therein.
- the power source may include batteries, battery packs, power conduits, connectors, and receptacles operable to receive batteries, battery connectors, or power cables.
- the device 102 may be installed and positioned on an access control entry point (not shown) such as a gate, locked door, etc. for preventing persons from accessing certain areas until the device 102 determines that the sensed biometric characteristic and/or signal match the known characteristics.
- the device 102 may be a stand-alone, compact, handheld, and portable device. In one example, one may use such a stand-alone, compact, handheld, and portable device to protect sensitive documents or information that are electronically stored and accessed on the Internet and/or an intranet.
- a concurrent realtime identity verification facility access unit may use biometric signature data to create interchangeable authentication for a variety of uses (e.g., office, home, smart phone, computer, facilities).
- the processor 106 in FIG. 1 may be configured to include, among other features, a detection module 502 and a recognition module 508 for providing concurrent real-time or near real-time identity verification and authentication with keyless access to authorized requesters to secured facilities or information.
- the detection module 502 may include a face detection module 504 for detecting facial features of a requester.
- the detection module 502 may include an eye detection module 506 for identifying the locations of the eyes of a requester.
- the detection module 520 may include one or both the face detection module 504 and/or the eye detection module 506.
- the processor 106 may receive inputs (digital or analog) from the sensor(s) 104.
- FIG. 6 describes an example procedure of selecting key features from a database with a large number of facial information and building one classifier which can distinguish different faces accordingly.
- LBP and LTP may be used to provide a full description of face information, and then with the use of an adaptive boosting ("adaboost") learning algorithm, one may select key features and build a classifier to distinguish different faces by creating biometric signature data.
- This biometric signature data may be used to create universal verification and authentication that can be used for a variety of applications (e.g., computer, building access, smartphone, automobile, data encryption) with varying degrees of access and security (e.g., access to network, but heightened security for requester computer).
- applications e.g., computer, building access, smartphone, automobile, data encryption
- degrees of access and security e.g., access to network, but heightened security for requester computer.
- the processor 106 and the recognition module 508 may create a face sample database using unrecognized face samples.
- the processor 106 and the recognition module 508 may store, into the memory 108, 1000, different persons with each person showing 10 different postures and/or expressions.
- the detection module 502 and/or the face detection module 504 may extract LBP and LTP features from different blocks in different positions of each face sample.
- At block 606, calculate positive sample and negative sample.
- at least one of the face detection module 502, the face detection module 504, and the eye detection module 506 may calculate the feature absolute value distance for the same position of any two different images from one person and set this distance as positive sample feature database. Further, the face detection module 502 and the face detection module 504 may jointly or separately calculate the feature absolute value distance for the same position of any two different images from different person and set this distance as negative sample feature database.
- the face detection module 502 and the face detection module 504 may select the most distinguishable key feature from the candidate feature database with adaboost and create a face classifier.
- the recognition module 508 may generate recognition result.
- a value is assigned to that unit of the dataset based upon the number of pixels within the block that satisfy that specific LBP. For example, assuming a 10 x 10 macro block in unit number 1 of 255 and LBP of 20, the method 600 determines the number of pixels in the histogram that fall within that LBP of 20 on scalar value. The method 600 calculates scalar value and then normalize value in a second array to address the problem of determining value within various sized macro-blocks.
- the scalar value based upon the known method was based on size of macro-block where the maximum value could be from 100 to 1600 depending upon the size of the macro-block.
- the scalar value in this second array may now a percentage of the total pixels available in that macro block to normalize the data for the subsequent assessment. Normalization causes the data to not be skewed based on the size of the macro block. After normalization under the improved method, each unit of the data set in this second array has the same weight. This normalized data may be then sorted to establish and assign a value from 1 - 2165 where the scale reflects the highest normalized value going to the top of the sort.
- the second normalized array may then be converted to a third simulated dna sequencing array where the position is established within this third array based upon its value in previous sort.
- the third array assesses the position and calculates the differences between where the data set appears in the sequence (e.g., ranking distance).
- This improved method analyzes traits as opposed to scalar value based upon the uniqueness of traits within the face and not merely on scalar values.
- test face sample For example, the detection module 502 may optionally test face samples.
- the detection module 502 and/or the face detection module 504 may extract LBP and LTP features from different blocks in different positions of each face sample.
- online recognition may include the following steps:
- [82] (2) Calculate the key feature selected from step (1) with that of each face sample in database and determine whether they belong to the same person or not. If calculated distance is less than the set threshold, it may be determined that they are the same person, otherwise it may be determined that they are not.
- an example process starts with creating a face database with different postures and different expressions.
- one may include the images of, e.g., 1000, different persons and each person shows, e.g., 10, images differently.
- FIG. 7(a) shows the different face image of one same person
- FIG. 7(b) refers to the different face image of different person.
- LBP and LTP may be used to describe face.
- FIG. 8 shows a calculating process of LBP features
- FIG. 9 shows a calculating process of LTP features.
- different block size may be divided on different positions of face sample.
- face size can be 100 x 100
- block size may be w x h
- w and h values can range from 2 to 100
- 7837 blocks may be selected as a result.
- the identification system 100 may select the bin features of LBP and LTP on different block size and make it as the final candidate feature database.
- the next step is to calculate positive samples and negative samples.
- the bin feature absolute value distance of the same position for different images from a same person may be calculated and set as the positive sample. Additionally, the bin feature absolute value distance of same position for different persons may be calculated and set as the negative sample. For example, the result may involve calculating 32356 positive samples and 58747698 negative samples.
- the key bin feature that can distinguish all positive and negative samples among the large number of feature database may be selected with a learning algorithm. For example, one may choose the learning algorithm of discrete adaboost to select feature and build a classifier.
- An example algorithm of using adaboost to classify may include the following computational steps:
- FIG. 10 shows the position of the first three key features selected among face image by taking online testing for face database of 100 persons based on offline selected features and classifier.
- FIG. 11 shows recognition results for 100 persons, wherein X axis represents false accept rate, which means the wrongly identified rate of face samples. Y axis represents verification rate, which means the rate of face samples correctly recognized. As shown in FIG. 11, when the false accept rate is below 10 4 , it may achieve 95% recognition rate.
- the face recognition in this example not only improves the robustness of face sample, but also reduces its computational complexity thus improves the face recognition significantly.
- the detection module 502 may be configured to use, among other features, a face detection module 504 and an eyes detection module 506 for processing the acquired image of the person-to-be-identified as follows.
- Inputs Acquired frontal face image (grey image), face frame positions, classifier for both left and right eyes, left eye classifier, right eye classifier, left eye coarse detection classifier, right eye coarse detection classifier
- [121] c If user-defined left/right eye course detection classifier for the left/right eye is available, detect the left/right eye on the corresponding half of the obtained face image. Further, based on the coarse detection result, determine whether the detected human subject is wearing glasses or not. If glasses are present, detect the obtained face image and return with results. If no glasses are present, continue to detect the obtained face image based on the coarse detection result and return the detection result without considering the presence of glasses. (If user-defined classifier for glasses-wearing subject is not available, detect the obtained face image without considering the presence of glasses.)
- the processor 106 may further use, e.g., a recognition module 508, to extract pertinent facial features obtained from the detection module 502 for comparing against known characteristics and/or information of a number of authorized people as follows.
- a recognition module 508 to extract pertinent facial features obtained from the detection module 502 for comparing against known characteristics and/or information of a number of authorized people as follows.
- Inputs to-be-normalized image (grey image), the coordinates of the centers of both the left and right eyes on the image axis (the origin is located at the left top comer of the image).
- Outputs If output buffer is NULL, return feature dimensional degrees. Otherwise, assume the size of the output buffer equals the feature dimensional degrees, write the features of the image into the buffer, and return feature dimensional degrees. Certain features are associated with certain image size. For example, #6 feature may require the image size of 100 by 100. Therefore, when the input image fails corresponding defined image size requirement, a result of zero can be returned.
- Outputs parameters information of the algorithm including feature type, feature dimensional degrees, normalized image size, the minimum distance, suggested range, and distance type.
- BSD Biometric Signature Data
- Various implementations of the present disclosure may employ the BSD files to create an encryption/decryption key, thus increasing the security of such keys.
- Examples of the present disclosure can generate asymmetric keys based on one or more BSD files in such a way that by utilizing a biometric sensor, a person's biometric measurement can act as the person's private key.
- Implementations of the present disclosure may also incorporate BSD files into digital rights management (DRM) security in such a way that files cannot be decrypted or accessed by anyone other than the requester or group of requesters intended, or encrypted in a way that the original owners, such as a business, can no longer access the files. Accordingly, by using implementations of the present disclosure employing BSD files, when a file is accessed, there can be assurance of the identity of the requester who accessed the file.
- DRM digital rights management
- BSD files can be generated by the algorithmic analysis of data from an A/D IR and/or UV sensor. Accordingly, many of these elements can be considered when constructing the private key of the asymmetrical pair (i.e., analog and/or digital values). Thus, in some implementations of the present disclosure, multiple elements of a sensor can contribute real time data or real-time analog data related to a recognition event in order to de-encrypt, thus ensuring a real-time event (i.e., the actual measurement of the intended person) has triggered the authentication.
- a real-time event i.e., the actual measurement of the intended person
- messages can be sent as follows.
- a requester can register, e.g., on a computer, and create a public key for the requester.
- the requester than then publish the public key so that the key is publicly known.
- Other people, systems, or entities can use the requester's public key to encrypt messages for the requester and send those messages to the requester.
- the requester can decrypt the message using her private key created by one or more live BSD files associated with the requester. Accordingly, the sender of the message is ensured that the requester is actually the person decrypting the message because the private key used to decrypt the message can be generated by the requester's live biometric data.
- DRM rules can allow for additional content to be added to a file and additional rules to be required.
- DRM rules can be expressed in many rights management languages known in the art, including but not limited to, XrML (extensible rights markup language), XMCL (extensible media commerce language), ODRL (open digital rights language), and the like.
- Rules can specify the actions that are permitted (e.g., decrypting, encrypting, transferring, copying, editing, etc.).
- the rules can also specify the people authorized to perform actions and the conditions under which these actions are permitted.
- BSD files can be used to authenticate a requester to determine whether the requester is one of the people specified in the rules.
- biometric encryption and authentication can also find application in corporate settings where, e.g., employees use corporate devices for personal use as well as business, or when, e.g., an employee uses a personal device and the corporate digital assets are transferred to and from the personal device.
- employees use corporate devices for personal use as well as business
- the corporate digital assets are transferred to and from the personal device.
- rules to documents that have certain digital signatures there may be controllable segmentation between private and business concerns. Both parties may have access to the parts they are entitled to access but can be prevented from accessing parts that are not entitled to access.
- possible applications include, but are not limited to, providing remote access, making purchases, and conditional security.
- various implementations of the present disclosure can generate BSD files used to authenticate a requester, thus providing secure access for any remote network connection, i.e., VPN server, secure access to network email, and/or company proprietary information, from a remote device.
- biometric authentication techniques of the present invention can be used to make authenticated online purchases/transactions. For example, spending limits can be based on requester or group profile for an account.
- a system can use the biometric authentication techniques of the present disclosure to authenticate the true identity of that requester to verify the requester is entitled to make the desired purchase.
- Biometric authentication techniques can also be used to provide conditional security to various digital files. For example, files that contain sensitive information can only be accessed by authorized requesters, which can be authenticated using the requester's live BSD files.
- SMPTE DC28 the body responsible for digital cinema standards, has identified five separate areas of digital cinema: (1) capture; (2) production; (3) Master (cinema, home, video, trailers, test screenings); (4) distribution (satellite, fiber, packaged); and (5) exhibition (digital projector security).
- a movie is vulnerable to theft.
- movies can be encrypted prior to distribution. Movies are then typically stored in their encrypted state in the theater until showtime. At showtime, the movie is decrypted and decompressed. This decryption/decompression may take place in a server or in a projector.
- DC28.4 can represent the conditional access portions of the cinema delivery system.
- Modem DRM encryption methods have proven sufficient to withstand unwarranted deciphering attempts, but securing the keys has become a problem. From capture to exhibition to distribution, a movie is encrypted and decrypted multiple times. Accordingly, various biometric encryption and authentication techniques discussed herein can be applied to one of more of the encryption, decryption, and authentication steps, in accordance with various implementations of the present disclosure.
- an example of an environment 1400 for managing data may rely on a first gateway l402a, a second gateway l402b, and a third gateway l402c to route data via wired and/or wireless communication links.
- the first gateway l402a may be implemented as a software-based gateway virtualized in a computer system.
- the second gateway l402b may be a standalone device that routes data as described below.
- the third gateway l402c may be a cloud-based gateway. Other architectures are possible.
- the gateways 1402 may perform several functions including managing the movement of data to and from the biometric sensor as described below, providing a networked solution that efficiently moves binary facial data between devices, and when clustered together (physical and virtual), providing a high availability solution for security designs.
- the gateway 1402 may receive credentialing data through an XML file structure. By monitoring and actively consuming the XML files, the gateway 1402 may be able to utilize a standardized universal interface agnostic to the programming language, operating system and type of connectivity of the data source, support physical and logical access control requirements within the same method, offer an interface that supports simultaneous connectivity from different system types, and/or support either live or batch processing of credentials, including the immediate recovery of a credential system through file replacement.
- the environment 1400 may include one or more faceplates 1404, e.g., faceplate-a l404a, faceplate-b l404b, faceplate-c l404c, faceplate-d l404d, faceplate-e l404e, and faceplate-f 1404T
- the faceplates 1404 may transmit data to the gateways 1402 to be routed to another device within the environment 1400.
- the faceplate-a l404a may send a biometric template and/or identity information of a person to the third gateway l402c.
- the third gateway l402c may send one or more biometric templates to the faceplate-a l404a for performing matching operations.
- the environment 1400 may include an access control server l406a, an enterprise server l406b, and a third party server l406c.
- the access control server l406a may be communicatively coupled to one or more access controlled entry points 1408 via a wired or wireless communication link.
- the enterprise server l406b may be communicatively coupled to a storage device 1410.
- the storage device 1410 may be a network drive, local hard drive, flash drive, tape drive, or other suitable storage media.
- the faceplate-b l404b may receive a biometric template of a first requester l450a.
- the first requester l450a may attempt to access one or more access controlled entry points 1408 controlled by the access control server l406a.
- the one or more access controlled entry points 1408 may include a vault, lock, secure door, secure gate, equipment or machinery, computing device, digital storage device, database, or file, for example.
- the one or more access controlled entry points 1408 may be an access controlled door or gate of an infrastructure, such as a warehouse, office building, restricted area, etc.
- the biometric template of the first requester l450a may include one or more of the fingerprints, voice patterns, iris patterns, facial features, signature patterns, shapes of the ears, retinal patterns, gait, hand geometry of the first requester l450a.
- the faceplate-b l404b may extract the facial features of the first requester l450a, and compare the facial features with the facial features of authorized personnel. If the facial feature of the first requester l450a matches one of the facial features of the authorized personnel, the faceplate-b l404b may send a first positive match signal to the third gateway l402c. The third gateway l402c may route the first positive match signal to the access control server l406a. Upon receiving the first positive match signal, the access control server l406a may unlock one of the one or more access controlled entry points 1408 associated with the faceplate -b l404b to allow the requester 1450 access. If the facial feature of the first requester l450a does not match one of the facial features of the authorized personnel, the first requester l450a may not gain access to the entry point 1408 associated with the faceplate -b l404b.
- the faceplate-d l404d may transmit a second positive match signal of a second requester 1450b at a first time and a third positive match signal at a second time of the second requester 1450b to the second gateway l402b.
- the second gateway l402b may route the second positive match signal and the third positive match signal to the first gateway 1402a, which may route the second and third positive match signals to the enterprise server l406b.
- the enterprise server l406b may use the second positive match signal and the third positive match signal to log access information associated with the second requester l450b.
- the enterprise server l406b may record, into the storage device 1410, the first time as the arrival time of the second requester l450b and the second time as the departure time on a work day.
- the enterprise server l406b may record the first and second time as the number of accesses to the one or more access controlled entry points 1408 by the second requester l450b.
- the enterprise server l406b may also log, based on the information in the second and third positive match signals, the premises, equipment, files, locations, and information accessed by the second requester 1450b.
- the faceplate-f l404f may transmit a fourth positive match signal of the third requester l450c to the first gateway l402a.
- the first gateway l402a may route the fourth positive match signal to the third party server l406c through a firewall 1412.
- the firewall 1412 may filter information transmitted through the firewall 1412 and prevent malicious requesters from gaining unauthorized access.
- the fourth positive match signal may indicate to the third party server l406c that the third requester l450c gained access to the one or more access controlled entry points 1408.
- the fourth positive match signal may indicate to the third part server l406c that the third requester l450c accessed a software that requires payment to the owner of the third party server l406c.
- a network administrator 1452 may install, manage, update, maintain, and/or control the software in the faceplates 1404, the gateways 1402, the access control server l406a, the one or more access controlled entry points 1408, the enterprise server l406b, the storage device 1410, and/or the firewall 1412 via a workstation 1414.
- the workstation 1414 may be a desktop computer, laptop computer, tablet computer, handheld computer, smartphone, or other suitable computer devices communicatively coupled via a wired or wireless connection to the third gateway l402c.
- the network administrator 1452 may transmit software commands from the workstation 1414 to the third gateway l402c to be routed to a destination.
- the network administrator 1452 may upgrade the firmware in the faceplates 1404. In other examples, the network administrator 1452 may install new software onto the access control server l406a. In another example, the network administrator 1452 may perform maintenance operations, such as disk error check and defragmentation, on the storage device 1410. In yet another example, the network administrator 1452 may lock down or open the one or more access controlled entry points 1408 in an emergency.
- an employee 1454 may utilize a requester terminal 1416 to access information through the second gateway l402b.
- the requester terminal 1416 may be a desktop computer, laptop computer, tablet computer, handheld computer, smartphone, or other suitable computer devices communicatively coupled via a wired or wireless connection to the second gateway l402b.
- the employee 1454 may download information, such as work hours, arrival time, access history, utilization frequencies, using the requester terminal 1416.
- data exchanges within the environment 1400 may be encrypted.
- Data transmissions between the gateways 1402 and the faceplates 1404 may use advanced TLS vl.2 communications with a proprietary key management framework.
- Data transmitted via TLS vl.2 communications may be fully encrypted to remove the threat of exposure of the data to unwanted parties.
- the encryption of the data may be further protected by protecting the generation of the encrypted keys through the use of the biometric data as the seed for the generation of the keys. As such, data exchanged within the environment may be difficult to access by unauthorized requesters.
- the gateways 1402 may be used to manage the data and the creation of a blockchain for the requesters.
- the first gateway l402a, the second gateway l402b, and the third gateway l402c may each include a blockchain wallet.
- the wallets will contain the requester personal credentials required to authenticate to any device or application.
- the wallets may be tied to the gateways 1402 to provide cybersecurity monitoring and to provide the interaction between the wallet and the facial recognition devices.
- the faceplates 1404 linked to the personal blockchain may be able to enable a transaction in the blockchain. Communications between blockchain wallets, a ledger for the blockchain transactions, and the gateways 1402 may use the blockchain protocol.
- the personal blockchain will also extend to devices that verify more than one requester, like a bank ATM (not shown).
- the gateways 1402 will utilize location tracking to move the link binary facial data and the link to the blockchain ledger between shared devices to improve the security of the transactions and to manage the number of requesters held within each faceplate 1404.
- aspects of the present disclosure may be implemented using hardware, software, a cloud network, or a combination thereof and may be implemented in one or more computer systems or other processing systems.
- features are directed toward one or more computer systems capable of carrying out the functionality described herein.
- An example of such the computer system 1500 is shown in FIG. 15.
- One or more of the gateways 1402, the servers 1406, the firewall 1412, the workstation 1414, and/or the requester terminal 1416 may be implemented based on the computer system 1500.
- the computer system 1500 includes one or more processors, such as the processor 1504.
- the processor 1504 is communicatively coupled to a communication infrastructure 1506 (e.g., a communications bus, cross-over bar, or network).
- a communication infrastructure 1506 e.g., a communications bus, cross-over bar, or network.
- the computer system 1500 may include a display interface 1502 that forwards graphics, text, and other data from the communication infrastructure 1506 (or from a frame buffer not shown) for display on a display unit 1530.
- Computer system 1500 also includes a main memory 208, preferably random access memory (RAM), and may also include a secondary memory 1510.
- the secondary memory 1510 may include, for example, a hard disk drive 1512, and/or a removable storage drive 1514, representing a floppy disk drive, magnetic tape drive, optical disk drive, universal serial bus (USB) flash drive, etc.
- the removable storage drive 1514 reads from and/or writes to a removable storage unit 1518 in a well-known manner.
- Removable storage unit 1518 represents a floppy disk, magnetic tape, optical disk, USB flash drive etc., which is read by and written to removable storage drive 1514.
- the removable storage unit 1518 includes a computer usable storage medium having stored therein computer software and/or data.
- Secondary memory 1510 may include other similar devices for allowing computer programs or other instructions to be loaded into computer system 1500.
- Such devices may include, for example, a removable storage unit 1522 and an interface 1520. Examples of such may include a program cartridge and cartridge interface (such as that found in video game devices), a removable memory chip (such as an erasable programmable read only memory (EPROM), or programmable read only memory (PROM)) and associated socket, and other removable storage units 1522 and interfaces 1520, which allow software and data to be transferred from the removable storage unit 1522 to computer system 1500.
- a program cartridge and cartridge interface such as that found in video game devices
- EPROM erasable programmable read only memory
- PROM programmable read only memory
- Computer system 1500 may also include a communications interface 1524.
- Communications interface 1524 allows software and data to be transferred between computer system 1500 and external devices. Examples of communications interface 1524 may include a modem, a network interface (such as an Ethernet card), a communications port, a Personal Computer Memory Card International Association (PCMCIA) slot and card, etc.
- Software and data transferred via communications interface 1524 are in the form of signals 1528, which may be electronic, electromagnetic, optical or other signals capable of being received by communications interface 1524. These signals 1528 are provided to communications interface 1524 via a communications path (e.g., channel) 1526.
- a communications path e.g., channel
- This path 1526 carries signals 1528 and may be implemented using one or more of a wire or cable, fiber optics, telephone line, cellular link, RF link and/or other communications channels.
- computer program medium and “computer usable medium” are used to refer generally to media such as a removable storage drive 1518, a hard disk installed in hard disk drive 1512, and signals 1528.
- These computer program products provide software to the computer system 1500. Aspects of the present disclosure are directed to such computer program products.
- Computer programs are stored in main memory 1508 and/or secondary memory 1510. Computer programs may also be received via communications interface 1524. Such computer programs, when executed, enable the computer system 1500 to perform the features in accordance with aspects of the present disclosure, as discussed herein. In particular, the computer programs, when executed, enable the processor 1504 to perform the features in accordance with aspects of the present disclosure. Accordingly, such computer programs represent controllers of the computer system 1500.
- the software may be stored in a computer program product and loaded into computer system 1500 using removable storage drive 1514, hard drive 1512, or communications interface 1520.
- the control logic when executed by the processor 1504, causes the processor 1504 to perform the functions described herein.
- the system is implemented primarily in hardware using, for example, hardware components, such as application specific integrated circuits (ASICs). Implementation of the hardware state machine so as to perform the functions described herein will be apparent to persons skilled in the relevant art(s).
- FIG. 16 illustrates a block diagram of various example system components, in accordance with an aspect of the present disclosure.
- Fig. 16 shows a communication system 1600 usable in accordance with aspects of the present disclosure.
- the communication system 1600 includes one or more accessors 1660, 1662 and one or more terminals 1642, 1666.
- data for use in accordance with aspects of the present disclosure is, for example, input and/or accessed by accessors 1660, 1662 via terminals 1642, 1666, such as personal computers (PCs), minicomputers, mainframe computers, microcomputers, telephonic devices, or wireless devices, such as personal digital assistants (“PDAs”) or a hand-held wireless devices coupled to a server 1643, such as a PC, minicomputer, mainframe computer, microcomputer, or other device having a processor and a repository for data and/or connection to a repository for data, via, for example, a network 1644, such as the Internet or an intranet, and couplings 1645, 1646, 1664.
- PCs personal computers
- PDAs personal digital assistants
- server 1643 such as a PC, minicomputer, mainframe computer, microcomputer, or other device having a processor and a repository for data and/or connection to a repository for data, via, for example, a network 1644, such as the Internet or an intranet, and coupling
- the couplings 1645, 1646, 1664 include, for example, wired, wireless, and/or fiberoptic links.
- the method and system in accordance with aspects of the present disclosure operate in a stand-alone environment, such as on a single terminal.
- FIG. 17 an example of a faceplate 1404 that is configured to perform access control may analyze a biometric template of a requester 1450 to determine whether the requester 1450 is authorized to gain access to an entry point (not shown) associated with the faceplate 1404.
- the faceplate 1404 may include an optical sensor 1702, an illumination source 1704, a display 1706, a keypad 1708, and a scanner 1710.
- the optical sensor 1702 may be configured to capture still or moving images.
- the optical sensor 1702 may capture the fingerprints, the iris patterns, the facial features, the signature patterns, the shapes of the ears, the retinal patterns, the gait, and/or the hand geometry of the requester 1450.
- the optical sensor 1702 may be a broadband camera configured to detect electromagnetic radiation having wavelengths ranging from 200 nanometers (e.g., soft UV) to 2000 nanometers (e.g., near infra-red (NIR)).
- NIR near infra-red
- the optical sensor 1702 is configured to detect radiation between 700 to 900 nanometers.
- the optical sensor 1702 may include a motion sensor configured to detect people approaching the faceplate 1404.
- the optical sensor 1702 may include a wide angle lens (e.g., such as a fisheye lens) used to provide both vertical area coverage to capture faces across the full range of human heights (as well as addressing American’s With Disabilities Act requirements) and to provide horizontal coverage of the complete area of an access point to address more than one person accessing the secure area on one authentication.
- the optical sensor 1702 may employ a high resolution (e.g., megapixel per square inch) charge coupled device (CCD) array.
- the high resolution array may provide the ability to identify faces at a greater distance from the sensor.
- the faceplate 1404 may take advantage of the increased distance of identification to pre-identify requesters in queuing situations.
- Potential requesters may be identified as they enter a queuing area and a placed in a priority list to accelerate the confirmation at the access controlled entry point and discharge of the queue.
- the pre-identification and prioritizing of individuals in the identification process at the access point enables high volume throughput at the entry point by reducing the identification time during the identification and authentication process.
- the illumination source 1704 may emit electromagnetic radiation having wavelengths ranging from 200 nanometers to 2000 nanometers. In certain examples, the illumination source 1704 may emit non- visible radiation between 700 to 900 nanometers and/or 200-300 nanometers. The illumination source 1704 may emit radiation to illuminate bodily features and patterns of the requester 1450 used for biometric analysis (analyzing biometric template to determine access rights). The emitted radiation may impinge on a portion of a body of the requester 1450, and reflect off of the portion of the body. The reflected radiation may be captured by the optical sensor 1702 for biometric analysis.
- the display 1706 may present useful information to the requester 1450.
- the display 1706 may show one or more images of a face 1730 of the requester 1450, captured by the optical sensor 1702, to assist the requester 1450 in aligning the face 1730 during biometric analysis.
- the display 1706 may notify the requester 1450 a status of the entry point associated with the faceplate 1404 (e.g., locked down, temporarily unavailable, normal operations, under maintenance).
- the display 1706 may display information such as time, date, weather, current location, etc.
- the keypad 1708 may allow the requester 1450 to enter numbers, symbols, and alphabets into the faceplate 1404.
- the requester 1450 may enter a password in addition to the biometric analysis to gain access to the entry point.
- the scanner 1710 may be a radio frequency identification (RFID) scanner, a proximity card scanner (e.g., HIDTM card scanner), a contact card scanner, or a magnetic card scanner.
- the scanner 1710 may send an interrogatory signal to a proximity card (not shown) having a coil and an integrated circuit with a programmable or non-programmable identification sequence. The interrogatory signal may be“absorbed” by the coil and may energize the integrated circuit.
- the energized integrated circuit sends a response signal including the identification sequence back to the scanner 1710 via the coil.
- the scanner 1710 analyzes the identification sequence to determine whether or not to grant access.
- the identification sequence may be one or more numbers, alphabets, symbols, and/or a combination thereof.
- the requester 1450 may approach the faceplate 1404 during operations.
- the optical sensor 1702 may detect the requester 1450.
- the illumination source 1704 may emit incident NIR radiation 1760 toward the requester 1450.
- the incident NIR radiation 1760 may impinge on the face 1730 of the requester 1450, and reflect off of the face 1730 of the requester 1450.
- the optical sensor 1702 may detect detected NIR radiation 1762 originating from the surface of the face 1730.
- the detected NIR radiation 1762 may include reflected incident NIR radiation 1760 and/or NIR radiation emitted from the requestor 1450 due to thermal heating (i.e., black body radiation).
- the intensity and distribution of the detected NIR radiation 1762 may depend on the intensity and angle of the incident NIR radiation 1760, the contour of the face 1730, angle of detection by the optical sensor 1702, and other factors.
- the faceplate 1404 may use the detected NIR radiation 1762 to construct a facial template (the“NIR heatmap”) of the requester 1450.
- the faceplate 1404 may compare the constructed NIR heatmap with existing templates stored therein (details described below). If the faceplate 1404 detects a match, the faceplate 1404 may allow the requester 1450 access to the entry point (as described above).
- a NIR heatmap generated via NIR radiation detection may be resistant to changes in ambient lighting. As ambient lighting fluctuates (e.g., changes in luminance, color, color temperature, lighting angle), a NIR heatmap constructed using NIR radiation detection may remain sufficiently constant to prevent a false acceptance or a false rejection.
- the NIR heatmap of the requester 1450 constructed via NIR radiation detection under a“bright” condition e.g., 1000 lux
- a“dark” condition e.g., 100 lux
- a NIR heatmap generated via NIR radiation detection may improve the privacy of the owner.
- the storage device 1410 may store NIR heatmaps of employees and associated confidential information (e.g., birthdates, email account passwords). If an unauthorized person gains access to the NIR heatmaps and the associated confidential information, the unauthorized person may not be able to exploit the stolen confidential information because it may be difficult to identify the employees based on the NIR heatmaps.
- the NIR heatmaps are constructed using, for example, detected NIR radiation, they may be unrecognizable because the NIR heatmap of a person may be drastically different from the visual image of the face of the same person.
- the requester 1450 may approach the faceplate 1404 during operations.
- the optical sensor 1702 may detect the requester 1450.
- the illumination source 1704 may emit incident UV radiation 1760 (e.g., electromagnetic radiations having wavelengths between 315-390 nanometers) toward the requester 1450.
- the incident UV radiation 1760 may impinge on the face 1730 of the requester 1450, and reflect off of the face 1730 of the requester 1450.
- the incident UV radiation 1760 may penetrate the surface of the face 1730 and reflect off of subdermal features of the face 1730 (e.g., dermis, subcutaneous tissue, muscles, imperfections).
- the optical sensor 1702 may detect detected UV radiation 1762 originating from the surface and/or subdermal features of the face 1730.
- the detected UV radiation 1762 may include reflected incident UV radiation 1760.
- the intensity and distribution of the detected UV radiation 1762 may depend on the intensity and angle of the incident UV radiation 1760, the contour of the face 1730, angle of detection by the optical sensor 1702, and other factors.
- the faceplate 1404 may use the detected UV radiation 1762 to construct a facial template (the“UV heatmap”) of the requester 1450.
- the faceplate 1404 may compare the constructed UV heatmap with existing templates stored therein (details described below). If the faceplate 1404 detects a match, the faceplate 1404 may allow the requester 1450 access to the entry point (as described above).
- a UV heatmap generated via UV radiation detection may be resistant to changes in ambient lighting. As ambient lighting fluctuates (e.g., changes in luminance, color, color temperature, lighting angle), a UV heatmap constructed using UV radiation detection may remain sufficiently constant to prevent a false acceptance or a false rejection.
- the UV heatmap of the requester 1450 constructed via UV radiation detection under a“bright” condition e.g., 1000 lux
- a“dark” condition e.g., 100 lux
- a UV heatmap generated via UV radiation detection may improve the privacy of the owner.
- the storage device 1410 may store UV heatmaps of employees and associated confidential information (e.g., birthdates, email account passwords). If an unauthorized person gains access to the UV heatmaps and the associated confidential information, the unauthorized person may not be able to exploit the stolen confidential information because it may be difficult to identify the employees based on the UV heatmaps.
- the UV heatmaps are constructed using, for example, detected UV radiation, they may be unrecognizable because the UV heatmap of a person may be drastically different from the visual image of the face of the same person.
- a heatmap may be a rendering of the dataset that visualizes the consistency of position within the three arrays. If the heatmap is compromised, it may be more difficult to obtain biometric information used to identify the individual.
- the faceplate 1404 may generate a visible-light heatmap based on detected visible-light reflected from the face 1730 of the requester 1450.
- the requestor 1450 may be asked to provide a password, a personal identification number (PIN), and/or a valid HIDTM card to be used in conjunction with the constructed heatmap to gain access to the entry point associated with the faceplate 1404.
- PIN personal identification number
- HIDTM valid HIDTM card
- the faceplate 1404 may include a microphone (not shown in FIG. 17) to perform voice recognition.
- the display 1706 may show the face 1730 of the requester 1450 as imaged by the optical sensor 1702.
- the display 1706 may include alignment marks (not shown) to assist the requester 1450 in aligning the face 1730 with respect to the optical sensor 1702. This alignment process may minimize false acceptances and false rejections due to misalignment.
- the faceplate 1404 may be a pocket-sized mobile device powered by rechargeable batteries.
- the faceplate 1404 may include a processor 1802 having a communication module 1852 configured to communicate with the gateways 1402 and other faceplates 1404 as described in this disclosure.
- the communication module 1852 may be implemented as hardware in the processor 1802 for example, as software code executed by the processor 1802, or a combination thereof.
- the processor 1802 may also include a security module 1854 configured to encrypt and/or decrypt data.
- the security module 1854 may be implemented as hardware in the processor 1802 for example, as software code executed by the processor 1802, or a combination thereof.
- the processor 1802 further includes an algorithm module 1856 for constructing and comparing biometric templates as described throughout this disclosure. Alternatively, the communications with the Gateway may be facilitated by a processor in the control panel.
- the algorithm module 1856 may be implemented as hardware in the processor 1802 for example, as software code executed by the processor 1802, or a combination thereof.
- the processor 1802 may further include a parallel computation module 1858 for performing distributed processing.
- the parallel computation module 1858 may be implemented as hardware in the processor 1802 for example, as software code executed by the processor 1802, or a combination thereof.
- the processor 1802 may include one or more processors or cores, and may be implemented as a semiconductor processor, graphical processing unit, a field programmable gate array, a programmable logic device, a processing cluster, an application specific integrated circuit, or other suitable architectures.
- the faceplate 1404 includes a memory 1804.
- the memory may be static or dynamic memory such as flash memory, random access memory, magnetic memory, or semiconductor memory.
- the memory 1804 may include external memory such as a cloud storage.
- the memory 1804 may include or store applications and/or computer executable code.
- the faceplate 1404 further includes a modem 1808 for communicating with the gateways 1402 and other faceplates 1404, and may operate in cooperation with the communication module 1852.
- the faceplate 1404 also includes a RAM 1806, such as static or dynamic random access memory (RAM).
- the faceplate 1404 may also include an Input/Output (TO) device 1810 communicatively coupled to the display 1706, the optical sensor 1702, the keypad 1708, and the scanner 1710.
- the components within the faceplate 1404 may be interconnected by an internal bus l8l2a.
- the processor 1802, the memory 1804, the RAM 1806, and the internal bus l8l2a may be disposed on a processing board 1820.
- FIG. 19 another example of the faceplate 1404 may include a number of processing boards 1820 interconnected by an external bus 1812b .
- Each processing board 1820 may include the processor 1802, the memory 1804, the RAM 1806, and the internal bus l8l2a. Data distributed among the processing boards 1820 may be distributed by a controller 1814 via the external bus 1812b .
- the faceplate 1404 may download (from the gateways 1402) 240,000 biometric templates of potential requestors.
- the controller 1814 may distribute the 240,000 biometric templates evenly or unevenly among the processing boards 1820 such that each processing board 1820 may store, in the respective memory 1804, 30,000 biometric templates.
- each processing board 1820 may store the same or different number of biometric templates.
- the faceplate 1404 may construct a heatmap (e.g., UV or NIR) of the requestor 1450 based on the detected NIR radiation 1762.
- the controller 1814 may distribute copies of the constructed heatmap to each of the processing boards 1820.
- the processing boards 1820 may simultaneously compare the duplicated heatmaps with the locally stored biometric templates (e.g., 30,000 stored in each processing board 1820). While the current example of the faceplate 1404 shown in FIG 19 includes eight processing boards 1820, other numbers of processing boards 1820 may also be used.
- the faceplate 1404 may include 2, 4, 6, 8, 12, 16, 32 or 64 processing boards 1820.
- the faceplate 1404 may rely on remote processing boards (not shown) to perform the distributed computing described above.
- the faceplate 1404 may send the duplicated heatmaps to the remote processing boards to jointly and simultaneously implement the algorithm (described below) for matching the duplicated heatmaps (or the numerical representation of the duplicated heatmaps) to known biometric templates.
- the processing boards may be within other faceplates within the network.
- the faceplate 1404 may send the duplicated heatmaps to a Beowulf cluster.
- the clustering design may employ inter-process and inter-processor protocols to share processing tasks of the same application between both processors and the processing cores within those processors.
- the first gateway l402a may download 600,000 biometric templates of potential requesters (e.g., employees and contractors) from the enterprise server l406b.
- the first gateway l402a may distribute 100,000 biometric templates to each of the faceplate-e l404e and the faceplate-f l404f, and 200,000 biometric templates to each of the second gateway l402b and the third gateway l402c.
- the second gateway l402b may distribute 100,000 biometric templates to each of the faceplate-c l404c and the faceplate-d l404d
- the third gateway l402c may distribute 100,000 biometric templates to each of the faceplate-a l404a and the faceplate-b l404b. Consequently, the 600,000 biometric templates downloaded from the enterprise server l406b may be evenly distributed among the faceplates 1404 (i.e., 100,000 non-overlapping templates each).
- the faceplate-b l404b may duplicate the constructed heatmap and distribute the duplicated heatmaps to the faceplate-a l404a, faceplate-c l404c, faceplate-d l404d, faceplate-e l404e, and faceplate-f l404f (via one or more gateways 1402).
- the faceplates 1404 may compare the duplicated heatmap of the first requester l450a with the 100,000 templates stored locally to determine a match.
- the faceplate-a l404a, faceplate-c l404c, faceplate-d l404d, faceplate-e l404e, and faceplate-f l404f may send (via one or more gateways 1402) the result of the comparison back to the faceplate-b l404b.
- the faceplate-b l404b may gather the results and determine whether to grant access to the first requester l450a.
- the biometric templates may be unevenly distributed among the faceplates 1404.
- the faceplate 1404 may generate a heatmap 2000 based on measuring the intensity of the detected radiation 1762 from the face 1730 of the requester 1450.
- the heatmap 2000 may include a base matrix 2010 of one or more measurement points 2002.
- the measurement points 2002 may include a value indicative of the intensity of the detected radiation 1762 at a location of the particular measurement point.
- the measurement point-a 2002a may indicate an intensity scale value of 2 corresponding to a region 2004a (e.g., black hair) around the face 1730 of the requester 1450.
- the measurement point-b 2002b may indicate an intensity scale value of 50 that corresponds to a background color.
- the measurement point-c 2002c may indicate an intensity scale value of 21 that corresponds to a region 2004c (e.g., cheeks) on the face 1730 of the requester 1450.
- the intensity scale may range from 0 (no reflection) to 100 (maximum reflection able to be detected by the optical sensor 1702 of the faceplate 1404.
- the intensity scale may measure an absolute intensity (e.g., brightness) of the measurement points 2002.
- the heatmap 2000 may include measurement points 2002 for detected radiation 1762 of different wavelengths (e.g., UY, NIR, red, green, blue).
- the heatmap 2000 in FIG. 20 shows the base matrix 2010 of 10 x 12 measurement points 2002 across the face 1730 of the requester 1450
- other measurement points density may be possible for the base matrix 2010.
- the faceplate 1404 may generate another heatmap using 100 x 100 measurement points across the face 1730 of the requester 1450.
- the faceplate 1404 may generate a heatmap using 500 x 500 measurement points.
- Other measurement points density are also possible, and may depend on desired accuracy, computational constraints, amount of data storage, etc.
- the faceplate 1404 may remove measurement points 2002 indicating the background.
- the faceplate 1404 may apply the LBP operation to one or more of the measurement points 2002 within the base matrix 2010.
- the faceplate 1404 may perform LBP on the measurement point-d 2002d, which includes an intensity value of 41.
- the LBP string for the measurement point-d 2002d is 01110100, based on the span of 1 (i.e., performing LBP using the immediate neighbors, having distance of 1 cell, of the measurement point-d 2002).
- the faceplate 1404 may track the numbers of LBP strings for the remaining measurement points 2002r as shown in a table 2100.
- the faceplate 1404 may compute 24 of the measurement points 2002 as having the LBP string of 00000000, 3 having the LBP string of 00000001, 11 having the LBP string of 00000010, and 0 having the LBP string of 00000011, etc., as indicated in a table 2100.
- the table 2100 may include 256 entries for the possible strings (i.e., 8 bits).
- the table 2100 may include 255 entries by eliminating the entry for the “all white” string (11111111) or the “all black” string (00000000).
- the data in the table 2100 may be plotted as a histogram indicating the number of occurrences (e.g., measurement points 2002) for the possible LBP strings.
- the faceplate 1404 may determine one or more unique features.
- the one or more unique features may be non-zero LBP strings occurring fewer than a threshold frequency (e.g., 5), such as LBP strings 00000001, 01110100, and 11111100.
- the one or more unique features may be the non-zero LBP strings occurring the least, such as LBP strings 01110100.
- the faceplate 1404 may track the location the measurement points 2002 having the one or more unique features. For example, the faceplate 1404 may track the coordinate of the LBP strings.
- the one or more unique features may be the non-zero LBP strings occurring the most.
- the faceplate 1404 may divide the base matrix 2010 into one or more sub-matrices. Each sub-matrix may include a macroblock of measurement points.
- the faceplate 1404 may divide the base matrix 2010 into a 5 x 5 sub-matrix 2202, a 3 x 3 sub-matrix 2204, and a 6 x 6 sub-matrix 2206.
- the faceplate 1402 may calculate the LBP strings of the measurement points 2002 within the 5 x 5 sub-matrix 2202 using a span of 3 (i.e., calculating LBP strings using neighbors 3 cells away).
- the faceplate 1402 may calculate the LBP strings of the measurement points 2002 within the 3 x 3 sub-matrix 2204 using a span of 2.
- the faceplate 1402 may calculate the LBP strings of the measurement points 2002 within the 6 x 6 sub-matrix 2206 using a span of 4.
- Other sizes for the base matrix, the sub-matrices, and spans are possible, as determined by the faceplate 1402.
- a 100 x 100 base matrix may be divided into sub-matrices of six different sizes: 10 x 10, 15 x 15, 20 x 20, 30 x 30, 35 x 35 and 40 x 40.
- the LBP string may be calculated with a different span around the measurement point being calculated to characterize the texture/slope of the area surrounding the cell at different coverage areas.
- the span in pixels from the measurement point 2002 to be calculated to each of the neighboring cells for each of the sub-matrix sizes may be 3, 9, 15, 21, 27 and 33.
- a 200 x 200 base matrix may include 6 different sub- matrices having sizes of 10 x 10, 20 x 20, 35 x 35, 50 x 50, 65 x 65, 80 x 80, and 100 x 100.
- the span in pixels from the measurement point 2002 to be calculated to each of the neighboring cells for each of the sub-matrix sizes may be 3, 5, 7, 10, 25 and 40.
- the sub- matrices may overlap in some instances.
- the faceplate 1404 may apply LTP computations onto the measurement points 2002.
- the faceplate 1404 may convert the list of binary features derived from the heatmap into a data sequence that is extensible and capable of being tailored to the unique traits of each requester 1450 while still providing a methodology of object comparison and matching/verification.
- a binary feature may contain three characteristics: the size of the sub-matrix/macroblock, the location of the sub- matrix/macroblock on the heatmap, and the Uniform Local Binary Pattern (ULBP) assigned to binary feature.
- a macroblock may be a“sub-image” of the image of the face 1730 of the requester 1450.
- a macroblock of size 10 is a 10 x 10 (i.e., 100 measurement points 2002) sub-image of the image of the face 1730.
- the location of the macroblock on the image may be defined by the position of the first pixel in the macroblock located in the top, left corner of the macroblock. The position of this pixel is defined by two values, its distance from the left boundary of the face image (x-dimension) and the distance from the top boundary of the face image (y-dimension).
- the final characteristic is the ULBP, which is a mathematical methodology for establishing a scalar value for the edge and texture characteristics of a pixel starting with the top left of the face 1730. For each pixel within the macroblock, a ULBP calculation is performed.
- the maximum value of a binary feature is the size of the defined macroblock (10x10 is 100) and the minimum value is zero.
- a macroblock may be used in more than one binary feature with a different ULBP definitions.
- the location of a macroblock may also be used in more than one binary feature with a different macroblock size and ULBP definition.
- a table 2300 may illustrate an example of the results of the sequence conversion process for macroblocks having sizes of 10 x 10, 35 x 35, 20 x 20, 30 x 30, 15 x 15, 40 x 40, and 15 x 15.
- Three arrays may be used to generate a biometric template.
- First array may be a scalar value in array normalized.
- Second array may be sorted so that binary feature 2000, which in this example has the highest value, goes to the top of the second array in position 1.
- Third array compares the difference in the position of binary feature 2000 in the sort instead of scalar value. If the position within the array for binary feature 2000 remains the same, the results will reflect a value of 0 representing the least possible change in position and therefore the highest value for significance in the authentication method.
- a method 2400 of converting a sequence may identify the most unique features used for identification.
- the processor 1802 and/or the communication module 1825 may obtain the heatmap of the face 1730.
- each macroblock/ULBP combination assigns a unique index to each macroblock/ULBP combination.
- the algorithm module 1856 may assign a unique index (e.g., 4) to each macroblock/ULBP combination (e.g., macroblock 30 x 30) and analyzing based upon uniqueness of traits within the face and not on scalar values.
- the algorithm module 1856 may construct a first array of scalar values for each macroblock/ULBP combination in the master schema referenced by the schema.
- First array includes number of pixels that fall within that ULBP within that macro-block.
- the faceplate 1404 may perform normal LBP calculation and get a histogram that is the value from 0-255, and if the result is the highest value (standard LBP formula that takes pixel and takes 8 pixels around it and then each pixel has a different binary value) then the result receives a value of 1. If some other LBP is higher than that pixel has a 0 value.
- each scalar value by the size of the macroblock.
- the algorithm module 1856 may weigh each scalar value (e.g., 380) by the size of the macroblock (e.g., 30 x 30).
- sort the first array of scalar values in descending order For example, the algorithm module 1856 may sort the elements of the first array of scalar values in descending order from, for example, 1 to 2156.
- convert the associated indices into a sequence For example, the algorithm module 1856 may convert the associated indices into a sequence or the sort order of the data set instead of the scalar value.
- the algorithm module 1856 may convert the sequence into a second array with a scalar value for each unique index that is the position of the primary index from the beginning of the sequence array with 2165 elements currently but may be extensible depending upon data for each individual.
- a deep learning may be performed on the full data set to establish the minimum data set required to accurately perform facial recognition.
- the result of the deep learning may be a reduced data set of binary features that is a fraction of the total data set (e.g., 1%, 2%, 5%, 10%, 20%, 50%,).
- Each element of data in this data set may be defined by a sub-matrix of a specific size and location and a single value within the full LBP base matrix.
- Each data element may be assigned a unique numeric identifier.
- this static data set is used for each requester. As each requester continues to verify their faces, the verification data may be collected and through deep learning a new set of binary features may be created for each requester.
- the introduction of the sequence to the verification algorithm may allow the introduction of this individualized set of binary features and still allow for comparison between different sets.
- the matching of two sequences may be achieved by calculating the difference (e.g., the difference in position of a data set) of the two arrays. The greater the sum the lower the quality of the match.
- a perfect object match may have a sum of substantially zero.
- a table 2500 illustrates an example of the verification calculations.
- the first step in creating the sequence may be the sorting of the scalar array by the magnitude of the scalar value.
- the sort may be performed in descending order.
- the binary feature unique identification with the largest value is at the top of the sort.
- the binary features providing with the most uniqueness are at the top of the array.
- the new sort position is transferred to that third array and the location on the new array is based upon the binary feature unique identification.
- Binary feature unique identifier is 2000 when it gets sorted it goes to position 1. In third array the 2000 position will receive a value of 1.
- This array may be a unique sequence for the object and is the new basis for object verification and/or matching.
- the sequence matching algorithm determines the quality of the match by the distance of each binary feature unique identification from the beginning of the sequence.
- the distance is the index value of the binary feature unique identification within the sequence array where the index values are sequentially assigned.
- another array is created that contains the distance of each binary feature from the beginning of the sequence.
- the binary feature with the unique identification of one is in position ten of the sorted sequence.
- position one will have a value of ten.
- the absolute value of the difference of the values with the matching index is aggregated to create a single value for the array match. A lower value equates to a closer match. A perfect match may be substantially a zero value.
- sequence array is second array and scalar array is the first array (normalized for block size). Extensible may indicate that the fixed list of binary features may now be expanded and contracted as required to optimize the process of matching objects while also improving the matching process integrity.
- the sequence array may be dynamically adjustable based on two separate deep learning functions based upon the environment of the edge device and the specific individual face being authorized.
- the first function may seek to continuously optimize the default list of binary features applied to some or all object matching attempts prior to the development of an individual list of binary features.
- the second function may aggregate image data on individual objects and over time develop an optimized list of binary features for the face. Once the individualized list of binary features exceeds the matching performance of the default list of binary features through parallel object matching trials on incoming object image data, the default list of binary features may be replaced with the individualized list of binary features for that object in the live object matching functions.
- the deep learning engine for both processes may receive sample data in parallel with the live object/face matching functions.
- two lists of binary features may be applied to it.
- the first list may either be the default or individualized list of reduced binary features (e.g., three most important blocks out of 100 in 10 x 10 macroblock).
- the output of the application of this list may be used in the live matching process.
- the second list may be the full list of binary features, which comprises all possible macroblock size (e.g., all 100 within the 10 x 10 macroblock), applied to possible image positions for each ULBP.
- the complete list of binary features may be, for example, twenty times the size of the default or individualized list of binary features.
- the deep learning engine may receive a sequence derived from the complete list of binary features for each object image received into the system.
- the images may be categorized into the training and validating sets.
- An independent default test set may be created including objects different than the object being learned.
- each object identified by the default or existing individualized list of binary features will be placed in the training, validation and test sets. All other object’s list may be placed in the verification and test sets.
- a deep learning training session for both the default object list of binary features and for each individual list of binary features may be executed for each new live entry from the object detection system.
- the face matrix of data is transferred to the facial recognition algorithm. If the deep learning algorithm has developed specific list of binary features, then an aggregate list of these binary features for all users in the system may be created and used to generate the sequence. Otherwise, the sequence may be generated using the default set of binary features. The sequence may be transferred to the verification algorithm where the matching process may determine the identity of the sequence. With the identity established, a full list of binary features (all sub-matrices with full LBP histograms) may be generated and transferred to that identities data set in the deep learning algorithm. The deep learning algorithm may process the available data set for that identity (the set may continue to grow with each verification) and generate a revised optimum data set for that identity.
- the optimized data set may be converted to a sequence and used in the next verification process for that user.
- the aggregate set of binary features may be updated if necessary for converting the next face matrix.
- the verification process will be within the locale cluster of devices, the deep learning algorithm may occur within both the locale and global clusters as a background task.
- the respective list may be updated in the live verification/matching process.
- the result may be a matching system capable of automatically adjusting to both the overall object population and the specific, unique traits of each object.
- the evolution of the object data will allow for large scale object matching solutions in excess of 100,000 objects capable of the same precision as a small solution ( ⁇ 1,000).
- an example of the deep learning process 2600 may rely on feedback loops and machine learning to refine the identification process.
- the processor 1802 and/or the communication module 1825 may obtain the heatmap of the face 1730.
- the algorithm module 1856 may determine if the face specific macroblock/ULBP is available.
- the algorithm module 1856 may convert image to face generic/default detection list of binary features if the custom list is not available.
- the algorithm module 1856 may obtain face detection default sequence if the macroblock is not available.
- the algorithm module 1856 may convert image to face detection specific list of binary features if the custom list of binary features (could be in original 2156 or could be all new ones that based upon that individual (e.g., 10 additional 10 x lOs that are more distinctive for that particular individual) is available.
- perform face detection For example, the algorithm module 1856 may perform face detection.
- the algorithm module 1856 may perform eye detection and location.
- convert image to full list of binary features For example, the algorithm module 1856 may convert image to full list of binary features (not just 57, but all 100 of 10 x 10 of macroblocks and include all values).
- Tensor flow is the deep learning engine framework provided by GoogleTM. Equation and algorithm for tensor flow is well known in the art.
- develop face detection list of binary features using tensor flow deep learning For example, the algorithm module 1856 may develop face detection list of binary features using tensor flow deep learning.
- the algorithm module 1856 may feedback face detection refined sequence.
- the faceplate 1404 may take entire feature set and collect all data for face and derive a new refined set that replaces the default set. Distance calculation between the position of the binary feature within two sets may be used as metrics. Every feature would be in the same position every time. As face data get better face to face comparison will get smaller and the difference between this face and all others will get larger.
- the example of the deep learning process 2600 shown in FIG. 26 may rely on feedback loops and machine learning to refine the identification process.
- the present disclosure may use tensor flow in a distributed architecture to evaluate at each reader that is privacy protected on all individual devices rather than stored in one central server.
- the algorithm module 1856 may perform eye detection and location.
- obtain face detection specific list of binary features For example, the algorithm module 1856 may obtain face detection specific list of binary features if the macroblock is available.
- obtain facial recognition default list of binary features For example, the algorithm module 1856 may convert image to face generic detection list of binary features if the specific list of binary features for that individual is not available.
- the algorithm module 1856 may determine if the face specific list of binary features is available.
- Custom list of binary features may include the original 2156 or could be all new ones that are based upon that individual (e.g., 10 additional 10 x lOs that are more distinctive for that particular individual)
- the algorithm module 1856 may convert image to face generic list of binary features if the face specific list of binary features is not available.
- the algorithm module 1856 may convert image to face specific list of binary features if the face specific list of binary features is available.
- convert list of binary features to sequences For example, the algorithm module 1856 may convert list of binary features to sequences.
- convert image to full list of binary features For example, the algorithm module 1856 may convert image to full list of binary features.
- the algorithm module 1856 may develop face specific list of binary features using tensor flow deep learning (not just 57 as is typical with LBP, but all 100 of 10 x 10 of macroblocks and include all values).
- Tensor flow is the deep learning engine framework provided by GoogleTM. Equation and algorithm for tensor flow is well known in the art.
- the gateway 1402 and/or the faceplate 1404 may include proactive algorithms to identify and reduce“consistency-collisions” during the verification process.
- a “consistency-collisions” may occur when one or more requesters have unique facial data that causes a mistake (i.e., false acceptance or false reject) in the verification.
- the gateway 1402 and/or the faceplate 1404 may seek out potential‘consistency-collisions’ proactively using two methods of the present disclosure described below.
- The‘Layered Reinforcement’ algorithm may allow the requester to create a binary tree structure for the facial data.
- the binary data may create a hierarchy of data points (e.g., LBP string) based on the uniqueness of the data points.
- Every verification transaction may result in the transfer of the binary facial data from the faceplate 1404 to the gateway 1402.
- the gateway 1402 may begin checking the uniqueness of the new data’s binary tree structure against the data of the other requesters 1450 stored.
- the gateway 1402 may notify the faceplate 1404 to escalate verification transactions between the two identified requesters 1450 to the gateway 1404.
- the gateway 1404 may perform two advanced algorithms (i.e., the Proactive Collision Identification Algorithm and the Time-Domain Trending Algorithm) on the data.
- Binary tree may take most distinctive features and establish hierarchy based upon most and least distinctive.
- Prioritized tree may reduced analysis based on 20 rather than 2165 saving time and computing/processing. Based upon the branches of the tree off the most distinctive features may allow the faceplate 1404 to determine if this is or is not the person rather than going thru all 2165 features. Threshholds may be empirical and derived from testing.
- the first advanced algorithm may take the binary tree data and analyze the facial data based on its location in the binary tree.
- the binary tree data may be weighted. If the weighting of the binary data does not yield a sufficient differentiation of the data, the gateway 1402 may extend the verification process to find adequate differentiation data.
- the facial characteristics of requesters may continuously change. If the biometric data of a face, such as the face 1730 of the requester 1450, remains static, the identification of the face may ultimately result in false rejections, requiring the re- enrollment of the face 1730. Dynamic adjustments to the biometric data may be continuously applied and algorithms may determine whether the proposed change is not the introduction of a different face into the biometric data resulting in a false acceptance on the face 17303. With every iteration of the biometric data, the algorithm must determine the amount of biometric data to retain to insure the next successful identification of the requester 1450 and the amount to change to insure the long-term identification of the requester 1450.
- the determination may be made by a combination of a time-domain analysis where the changes are regressed to insure linearity and facial regional analysis to determine if the area of change is rational.
- the use of this dynamic data capability leads to the second algorithm, the Time- Domain Trending Algorithm.
- the gateway 1402 may maintain the history of the binary data of the requester 1450 and perform a time-domain based analysis of the data to assess what features are changing when the history of the binary data of requester 1450 is compared with face 1730 and the speed with which these features are changing.
- the gateway 1402 may track the evolution of the face and uses this data to extrapolate and reinforce the unique differences identified in the face 1730 of the requester 1450 to establish and later emphasize core features or baseline features and assess the rate of change in these core features for the face 1730. The gateway 1402 then determines using time-domain based analysis whether these changes are taking place over a time period to suggest natural changes in the face 1730, artificial changes in face 1730 warranting further analysis, or a mismatch of the history of binary data of the requester 1450 with the face 1730. The gateway 1402 may identify the unique differences and verify that the differences identified in the verification request are consistent with the trending over time.
- the gateway 1402 may factor in lifestyle and daily routines of the requester 1450 in the Time-Domain Trending Algorithm. For example, if the requester 1450 enjoys outdoor activities, the Algorithm may factor in increased tanning during the summer season.
- the Proactive Collision Identification Algorithm combined with the Time-Domain Trending Algorithm allows the method of this embodiment of the invention to maintain its high performance in a large population‘l:N’ solution.
- a method 2800 of constructing a biometric template may be performed by the faceplate 1404.
- the illumination source 1704 may emit an incident non-visible light.
- the non-visible light may include near IR or UV.
- the illumination source 1704 may emit a visible light.
- the optical sensor 1702 may detect a detected non-visible light, wherein the detected non-visible light includes a reflected non-visible light and a radiated non-visible light.
- the optical sensor 1702 may detect IR light reflected off of the face 1730 of the requester 1450 and/or IR light radiated due to the heat of the requester 1450.
- generating a heatmap including a plurality of sampling points having a plurality of characteristic values associated with the detected non-visible light For example, the algorithm module 1856 may generate a heatmap, such as the heatmap 2000, including a plurality of sampling points having a plurality of characteristic values associated with the detected non-visible light.
- identifying one or more macroblocks each includes a subset of the plurality of sampling points.
- the algorithm module 1856 may identify one or more macroblocks each includes a subset of the plurality of sampling points.
- the one or more macroblocks may be a 10 x 10 macroblock, a 15 x 15 macroblock, a 20 x 20 macroblock, a 30 x 30 macroblock, a 35 x 35 macroblock, and a 40 x 40 macroblock. Other sizes are possible.
- the faceplate 1404 may identify, 2165 macroblocks having 2165 associated d
- selecting a local pattern value For example, the algorithm module 1856 may select a local binary pattern value of 20. In other examples, the algorithm module 1856 may select a local ternary pattern value.
- calculating a number of occurrences of the local pattern value within each subset of the plurality of the sampling points for each of the one or more macroblocks For example, the algorithm module 1856 may calculate a number of occurrences of the local pattern value within each subset of the plurality of the sampling points for each of the one or more macroblocks.
- generating a first array including a plurality of weighted values by calculating the plurality of weighted values based on the numbers of occurrences of the local pattern value and corresponding sizes of the one or more macroblocks.
- the algorithm module 1856 may generate a first array including the weighted values shown in the table 2300 (i.e., [0.30 0.54 0.15 0.42 0.62 0.46 0.53]).
- the algorithm module 1856 may assign unique indices (i.e., 1, 2, 3, 4, 5, 6, and 7) to each of the plurality of weighted values shown in the table 2300.
- the unique index 1 is assigned to the weighted value of 0.30, 2 to 0.54, 3 to 0.15 , etc.
- the algorithm module 1856 may generate a second array of the unique index by ranking the plurality of weighted values, such as the sequence 5, 2, 7, 6, 4, 1, 3 in the table 2300.
- the second array/sequence may indicate a ranking of the weighted values from the highest to the lowest.
- the first number in the sequence is 5 because the weighted value (i.e., 0.62) associated with the unique index of 5 is the highest among the elements of the first array.
- the algorithm module 1856 may generate a third array including a plurality of ranking distances, such as the stored array [5 1 6 4 0 3 2] in the table 2300.
- a ranking distance may indicate a numerical difference between the ranks of the highest weighted value (e.g., 0.62 - rank 1) and the current weighted value (e.g., 0.30 - rank 6). Therefore, the ranking distance between 0.62 and 0.30 may be 5 (i.e., 6-1).
- Information and signals may be represented using any of a variety of different technologies and techniques.
- data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, computer-executable code or instructions stored on a computer- readable medium, or any combination thereof.
- a specially-programmed device such as but not limited to a processor, a digital signal processor (DSP), an ASIC, a FPGA or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination thereof designed to perform the functions described herein.
- DSP digital signal processor
- a specially-programmed processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine.
- a specially-programmed processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.
- the functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a non-transitory computer-readable medium. Other examples and implementations are within the scope and spirit of the disclosure and appended claims. For example, due to the nature of software, functions described above can be implemented using software executed by a specially programmed processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions may also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.
- Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another.
- a storage medium may be any available medium that can be accessed by a general purpose or special purpose computer.
- computer- readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor.
- any connection is properly termed a computer-readable medium.
- Disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above are also included within the scope of computer-readable media.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Collating Specific Patterns (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
BR112021002904-4A BR112021002904A2 (en) | 2018-08-17 | 2019-07-23 | methods and apparatus for facial recognition |
EP19849526.9A EP3837634A4 (en) | 2018-08-17 | 2019-07-23 | Methods and apparatus for facial recognition |
AU2019322625A AU2019322625A1 (en) | 2018-08-17 | 2019-07-23 | Methods and apparatus for facial recognition |
KR1020217007954A KR20210070278A (en) | 2018-08-17 | 2019-07-23 | Method and device for facial recognition |
CA3109748A CA3109748A1 (en) | 2018-08-17 | 2019-07-23 | Methods and apparatus for facial recognition |
MX2021001871A MX2021001871A (en) | 2018-08-17 | 2019-07-23 | Methods and apparatus for facial recognition. |
US16/813,422 US11594072B1 (en) | 2012-09-07 | 2020-03-09 | Methods and apparatus for access control using biometric verification |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201816104826A | 2018-08-17 | 2018-08-17 | |
US16/104,826 | 2018-08-17 |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US201816104826A Continuation | 2012-09-07 | 2018-08-17 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/813,422 Continuation US11594072B1 (en) | 2012-09-07 | 2020-03-09 | Methods and apparatus for access control using biometric verification |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020036710A1 true WO2020036710A1 (en) | 2020-02-20 |
Family
ID=69525795
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2019/043008 WO2020036710A1 (en) | 2012-09-07 | 2019-07-23 | Methods and apparatus for facial recognition |
Country Status (7)
Country | Link |
---|---|
EP (1) | EP3837634A4 (en) |
KR (1) | KR20210070278A (en) |
AU (1) | AU2019322625A1 (en) |
BR (1) | BR112021002904A2 (en) |
CA (1) | CA3109748A1 (en) |
MX (1) | MX2021001871A (en) |
WO (1) | WO2020036710A1 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020227300A1 (en) * | 2012-09-07 | 2020-11-12 | Stone Lock Global, Inc. | Methods and apparatus for facial recognition |
US11017212B2 (en) | 2012-09-07 | 2021-05-25 | Stone Lock Global, Inc. | Methods and apparatus for biometric verification |
US11017213B1 (en) | 2012-09-07 | 2021-05-25 | Stone Lock Global, Inc. | Methods and apparatus for biometric verification |
US11017214B1 (en) | 2012-09-07 | 2021-05-25 | Stone Lock Global, Inc. | Methods and apparatus for biometric verification |
USD976904S1 (en) | 2020-12-18 | 2023-01-31 | Stone Lock Global, Inc. | Biometric scanner |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11741252B1 (en) * | 2022-07-07 | 2023-08-29 | Sas Institute, Inc. | Parallel and incremental processing techniques for data protection |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6309069B1 (en) * | 1996-06-06 | 2001-10-30 | British Telecommunications Public Limited Company | Personal identification |
US20040036574A1 (en) * | 2000-05-19 | 2004-02-26 | Nextgen Id | Distributed biometric access control method and apparatus |
US20070198850A1 (en) * | 2004-10-21 | 2007-08-23 | Honeywell International, Inc. | Biometric verification and duress detection system and method |
US20140072185A1 (en) | 2012-09-07 | 2014-03-13 | David D. Dunlap | Biometric Identification Systems and Methods |
US20170132466A1 (en) | 2014-09-30 | 2017-05-11 | Qualcomm Incorporated | Low-power iris scan initialization |
US20180191952A1 (en) * | 2016-12-30 | 2018-07-05 | Axis Ab | Gaze heat map |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102467655A (en) * | 2010-11-05 | 2012-05-23 | 株式会社理光 | Multi-angle face detection method and system |
-
2019
- 2019-07-23 KR KR1020217007954A patent/KR20210070278A/en unknown
- 2019-07-23 BR BR112021002904-4A patent/BR112021002904A2/en unknown
- 2019-07-23 AU AU2019322625A patent/AU2019322625A1/en active Pending
- 2019-07-23 CA CA3109748A patent/CA3109748A1/en active Pending
- 2019-07-23 WO PCT/US2019/043008 patent/WO2020036710A1/en unknown
- 2019-07-23 MX MX2021001871A patent/MX2021001871A/en unknown
- 2019-07-23 EP EP19849526.9A patent/EP3837634A4/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6309069B1 (en) * | 1996-06-06 | 2001-10-30 | British Telecommunications Public Limited Company | Personal identification |
US20040036574A1 (en) * | 2000-05-19 | 2004-02-26 | Nextgen Id | Distributed biometric access control method and apparatus |
US20070198850A1 (en) * | 2004-10-21 | 2007-08-23 | Honeywell International, Inc. | Biometric verification and duress detection system and method |
US20140072185A1 (en) | 2012-09-07 | 2014-03-13 | David D. Dunlap | Biometric Identification Systems and Methods |
US20170132466A1 (en) | 2014-09-30 | 2017-05-11 | Qualcomm Incorporated | Low-power iris scan initialization |
US20180191952A1 (en) * | 2016-12-30 | 2018-07-05 | Axis Ab | Gaze heat map |
Non-Patent Citations (1)
Title |
---|
See also references of EP3837634A4 |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020227300A1 (en) * | 2012-09-07 | 2020-11-12 | Stone Lock Global, Inc. | Methods and apparatus for facial recognition |
US10853630B2 (en) | 2012-09-07 | 2020-12-01 | Stone Lock Global, Inc. | Methods and apparatus for biometric verification |
US11017212B2 (en) | 2012-09-07 | 2021-05-25 | Stone Lock Global, Inc. | Methods and apparatus for biometric verification |
US11017213B1 (en) | 2012-09-07 | 2021-05-25 | Stone Lock Global, Inc. | Methods and apparatus for biometric verification |
US11017214B1 (en) | 2012-09-07 | 2021-05-25 | Stone Lock Global, Inc. | Methods and apparatus for biometric verification |
US11017211B1 (en) | 2012-09-07 | 2021-05-25 | Stone Lock Global, Inc. | Methods and apparatus for biometric verification |
USD976904S1 (en) | 2020-12-18 | 2023-01-31 | Stone Lock Global, Inc. | Biometric scanner |
Also Published As
Publication number | Publication date |
---|---|
MX2021001871A (en) | 2021-07-15 |
EP3837634A4 (en) | 2022-05-18 |
KR20210070278A (en) | 2021-06-14 |
CA3109748A1 (en) | 2020-02-20 |
AU2019322625A1 (en) | 2021-03-18 |
EP3837634A1 (en) | 2021-06-23 |
BR112021002904A2 (en) | 2021-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11651623B2 (en) | Methods and apparatus for outdoor access control using biometric verification | |
US11163984B2 (en) | Methods and apparatus for constructing biometrical templates using facial profiles of users | |
Del Rio et al. | Automated border control e-gates and facial recognition systems | |
US10438053B2 (en) | Biometric identification systems and methods | |
WO2020036710A1 (en) | Methods and apparatus for facial recognition | |
US11163983B2 (en) | Methods and apparatus for aligning sampling points of facial profiles of users | |
US20190147676A1 (en) | System and method for optimizing a facial recognition-based system for controlling access to a building | |
WO2021138342A1 (en) | Methods and apparatus for facial recognition | |
US20150015365A1 (en) | Point of entry authorization utilizing rfid enabled profile and biometric data | |
US11017212B2 (en) | Methods and apparatus for biometric verification | |
US11301670B2 (en) | Methods and apparatus for collision detection in biometric verification | |
US11275929B2 (en) | Methods and apparatus for privacy protection during biometric verification | |
Shahriar et al. | An iris-based authentication framework to prevent presentation attacks | |
US20230360457A1 (en) | Multi-factor authentication door access control system | |
US11594072B1 (en) | Methods and apparatus for access control using biometric verification | |
US11017213B1 (en) | Methods and apparatus for biometric verification | |
US11017214B1 (en) | Methods and apparatus for biometric verification | |
WO2020185525A1 (en) | Methods and apparatus for facial recognition | |
CN117501265A (en) | Method for authenticating a user of a mobile device | |
Ammaarah et al. | Photographic Methods in Enhancing Biometric Security Systems | |
Kumari | ENHANCING PAYMENT SECURITY THROUGH THE IMPLEMENTATION OF DEEP LEARNING-BASED FACIAL RECOGNITION SYSTEMS IN MOBILE BANKING APPLICATIONS |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19849526 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 3109748 Country of ref document: CA |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112021002904 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 2019322625 Country of ref document: AU Date of ref document: 20190723 Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2019849526 Country of ref document: EP Effective date: 20210317 |
|
ENP | Entry into the national phase |
Ref document number: 112021002904 Country of ref document: BR Kind code of ref document: A2 Effective date: 20210217 |