CN106650363A - Identity recognition method and system - Google Patents
Identity recognition method and system Download PDFInfo
- Publication number
- CN106650363A CN106650363A CN201610851468.0A CN201610851468A CN106650363A CN 106650363 A CN106650363 A CN 106650363A CN 201610851468 A CN201610851468 A CN 201610851468A CN 106650363 A CN106650363 A CN 106650363A
- Authority
- CN
- China
- Prior art keywords
- card
- local feature
- face local
- face
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- 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
- G06F21/34—User authentication involving the use of external additional devices, e.g. dongles or smart cards
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/0013—Methods or arrangements for sensing record carriers, e.g. for reading patterns by galvanic contacts, e.g. card connectors for ISO-7816 compliant smart cards or memory cards, e.g. SD card readers
-
- 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
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention is applicable to the field of information recognition technology and provides an identity recognition method and system. The method comprises the steps that first facial local features of a first facial image stored in a built-in chip of a card, second facial local features of a second facial image printed on the surface of the card and third facial local features of a third facial image of an onsite cardholder are extracted; the first facial local features and the second facial local features are compared, and authenticity of the card is recognized according to the comparison result; when the card recognition result is true, the first facial local features and the third facial local features are compared, the second facial local features and the third facial local features are compared, and the identity of the cardholder is recognized according to the comparison results. According to the identity recognition method and system, through automatic recognition and comparison of information stored in the built-in chip of the card, information printed on the surface of the card and information of the onsite cardholder, the recognition efficiency of the identity of the cardholder and the accuracy of the results can be improved.
Description
Technical field
The invention belongs to information discriminating technology field, more particularly to a kind of personal identification method and system.
Background technology
Certificate with information storage function, card play important role in our life.Such as we are most normal
Identity card, member card for seeing etc., are exactly to lead to the information Store of user among built-in storage chip the characteristics of they are maximum
Cross identification terminal to be easy to read user related information, including human face image information.
In life, the demand to the certificate with information storage function, holder's identification of card, example are there is
Such as, in market today, exist many hold personation certificate or personation card card owner capture other people block card disrupt the market show
As.
In prior art, the general true and false using identification card card, or the printing image on artificial contrast's card card surface and existing
The method whether holder coincide can so cause the identification efficiency to holder low recognizing holder's identity information
The lower and inadequate problem of result precision.
The content of the invention
The present invention is intended to provide a kind of personal identification method and system, to solve prior art in the identity of holder is known
Other inefficiency and the inadequate problem of result precision.
In order to solve above-mentioned technical problem, in a first aspect, embodiments providing a kind of personal identification method, wrap
Include:
Extract the first facial image of card card built-in chip storage the first face local feature, the of card card surface printing
3rd face local feature of the 3rd facial image of the second face local feature of two facial images and live holder;
The first face local feature and the second described face local feature are contrasted, is demonstrate,proved according to comparing result identification card
The true and false;
When card card recognition result is true time, the first face local feature and the 3rd face local feature are contrasted,
And the second face local feature and the 3rd face local feature are contrasted, holder's identity is recognized according to comparing result.
Further, first facial image of card card built-in chip storage is extracted;By the first described facial image
Information matches the similitude with the template as template in card demonstrate,proves the image of the image of surface printing and live holder
The image-region of maximum is estimated, respectively as second facial image and the 3rd facial image.
Further, described face Local Feature Extraction is:Adopt LBP (Local Binary Patterns
Local binary patterns) feature extraction algorithm carries out face local shape factor.
Further, when card card truth identification result is pseudo-, it is pseudo- information to export holder's identification result.
Further, when the first face local feature and the 3rd face local feature comparing result and described
Two face local features and the 3rd face local feature comparing result are all true time, and output holder's identification result is
Genuine information;When the first face local feature and the 3rd face local feature comparing result and the second face office
Portion's feature and the 3rd face local feature comparing result are not all true time, and it is pseudo- letter to export holder's identification result
Breath.
Second aspect, embodiments provides a kind of identification system, including:
First extraction unit, it is special for extracting the first face local of the first facial image of card card built-in chip storage
Levy, block the second face local feature of the second facial image of card surface printing and the 3rd facial image of live holder
3rd face local feature;
First comparison unit, for contrasting the first face local feature and the second described face local feature, root
The true and false is demonstrate,proved according to comparing result identification card;
Second comparison unit, for being true time when card card recognition result, contrasts the first face local feature and described
3rd face local feature, and the second face local feature and the 3rd face local feature are contrasted, held according to comparing result identification
Card people's identity.
Further, the system also includes the second extraction unit, for extracting described the of card card built-in chip storage
One facial image;
Matching unit, for using the first described human face image information as template, card demonstrate,prove the image of surface printing and
The image-region maximum with the similarity measure of the template is matched in the image of live holder, respectively as described second
Facial image and the 3rd facial image.
Further, described face Local Feature Extraction is:Face local is carried out using LBP feature extraction algorithms
Feature extraction.
Further, when card card truth identification result is pseudo-, it is pseudo- information to export holder's identification result.
Further, when the first face local feature and the 3rd face local feature comparing result and described
Two face local features and the 3rd face local feature comparing result are all true time, and output holder's identification result is
Genuine information;
When the first face local feature and the 3rd face local feature comparing result and the second face office
Portion's feature and the 3rd face local feature comparing result are not all true time, and it is pseudo- letter to export holder's identification result
Breath.
In an embodiment of the present invention, automatically extract face local feature as a result of face recognition algorithms to go forward side by side pedestrian
Face is contrasted, and the face local feature to three images is contrasted two-by-two so that the recognition efficiency to holder's identity
It is improved, while also improving the degree of accuracy of identification.
Description of the drawings
Fig. 1 is a kind of flowchart of personal identification method provided in an embodiment of the present invention;
Fig. 2 is the structural representation that card card reads scan module in the present invention;
In figure:1- control modules, the contact-type image sensors of 2- first, 3- cards card outlet, the contact type images of 4- second are passed
Sensor, 5- recycling modules, 6- transmission modules, 7- interface modules, 8- information reading modules, 9- cards card entrance, 10- enters card detection mould
Block, 11- crosses card channel, 12- housings, 13- reminding modules.
Fig. 3 is LBP feature extraction schematic diagrames;
Fig. 4 is to apply the invention to recognize the preferred embodiment schematic diagram in identity card holder's identity;
Fig. 5 is the structured flowchart of system provided in an embodiment of the present invention.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, it is right below in conjunction with drawings and Examples
The present invention is described in further detail.It should be appreciated that specific embodiment described herein is only to explain the present invention, and
It is not used in the restriction present invention.
The embodiment of the present invention extracts the first face local feature, the card card of the first facial image of card card built-in chip storage
3rd people of the 3rd facial image of the second face local feature of the second facial image of surface printing and live holder
Face local feature;The first face local feature and the second described face local feature are contrasted, is recognized according to comparing result
The card card true and false;When card card recognition result is true time, the first face local feature and the 3rd face local feature are contrasted,
And the second face local feature and the 3rd face local feature are contrasted, holder's identity is recognized according to comparing result.
Fig. 1 shows a kind of flowchart of personal identification method provided in an embodiment of the present invention, and details are as follows:
In S101, the first face local feature, the card card table of the first facial image of card card built-in chip storage is extracted
3rd face of the 3rd facial image of the second face local feature of the second facial image of face printing and live holder
Local feature.
Before the extraction face local feature, also include:
Capture card card built-in chip storage image, card card surface printing image and live holder's image;
Extract face figure in card card built-in chip storage image, card card surface printing image and live holder's image
Picture.
The capture card card built-in chip storage image and card card surface printing image, can read scanning mould using card card
Block is acquired.
Described because card card built-in chip storage image is that standard shoots, face is in normal place, therefore, it can consolidating
Determine effectively to extract facial image in region.Extract facial image in card card surface printing image and live holder's image
When, using the facial image in card card built-in chip storage image as template, using template matching algorithm similitude survey is carried out
Degree calculates and selects facial image.
It is described to extract face in card card built-in chip storage image, card card surface printing image and live holder's image
Face local feature in image, using LBP feature extraction algorithms face local shape factor is carried out.
In S102, the first face local feature and the second described face local feature are contrasted, according to contrast knot
Fruit identification card demonstrate,proves the true and false.
The contrast face local feature refers to that the LBP features to getting in S101 carry out contrast judgement, decision method
The similarity variance for calculating two LBP features can be adopted, same people is determined whether according to variance yields.Such as:Assume for people
Face image 1 and facial image 2, its LBP feature is respectively H1And H2, then the similarity variance of the two be defined as follows:
Wherein, b represents the length of characteristic vector, and d represents similarity variance, and d values are less, represents that two face samples are got over
It is similar.Therefore the similarity variance between 2 width facial images is calculated by above formula, it is possible to determine that whether be same human head picture.
Can also be using being classified from suitable grader, more than grader in the form of assembled classifier, each
Local feature one grader of correspondence, determines whether the methods such as same people using modes such as ballot or linear weighted functions afterwards, due to
These contrast decision methods are all ways generally in the art, and the present invention does not do statement in detail.
Described to demonstrate,prove the true and false according to comparing result identification card, if comparing result is true, card card recognition result is true, if right
It is puppet than result, then card card recognition result is puppet.
In S103, when card card recognition result is true time, the first face local feature and the 3rd face are contrasted
Local feature, and the second face local feature and the 3rd face local feature are contrasted, holder's identity is recognized according to comparing result.
The contrast face local feature method is with identical in S102.
It is described to recognize that holder's identity is referred to according to comparing result, simultaneously using the first face local feature and institute
The 3rd face local feature comparing result is stated with the second face local feature and the 3rd face local feature comparing result two
Individual comparing result is recognizing other holder's identity.
Further, in the S101:
The card card reads scan module, is as shown in Figure 2 the structural representation that card card reads scan module, wherein wrapping
Include:
Control module 1, the first contact-type image sensor 2, card card outlet 3, the second contact-type image sensor 4 is reclaimed
Module 5, transmission module 6, interface module 7, information reading module 8, card card entrance 9 enters card detection module 10, crosses card channel 11,
Housing 12, reminding module 13.
It is described enter card detection module, arrange and cross card channel side near described on the housing, and with the control mould
Block is connected.
The control module, is respectively connected with the transmission module, described information read module and the scan module.
The transmission module, is connected with the card channel of crossing.
Described information read module, is arranged on the card channel side excessively.
The contact-type image sensor 4 of first contact-type image sensor 2 and second is separately positioned on the cartoon excessively
Road both sides.
It is as follows that the card card reads scan module workflow:
Card card goes out to insert from card card entrance 9, when card detection module 10 detects card card insertion, sends trigger message to control
Molding block 1;Control module 1 is received after trigger, generates transmission control signals and commencing signal, and by transmission control signals
Transmission module 6 described in being sent to the contact-type image sensor 4 of first contact-type image sensor 2 and second, will start letter
Number send to first contact-type image sensor 2, the second contact-type image sensor 4 and described information read module 8;
First contact-type image sensor 2, the second contact-type image sensor 4 and described information read module 8 are being received
After commencing signal, into stand-by operation state;The transmission module 6 drove card channel after transmission control signals are received
Card card is driven to successively information reading module 8, the first contact-type image sensor 2 and the second contact-type image sensor 4 by 11
Corresponded at the position of card channel 11;Information reading module 8, the first contact-type image sensor 2 and the second contact type image sensing
Device 4 is reading scanning to after data, sends data to control module 1;Control module 1 after receiving the data, by interface
Module 7 sends data to exterior terminal, demonstrate,proves out while controlling transmission module 6 and driving card channel 11 that hair fastener card is driven to into card
At mouth 3, and cue is sent to reminding module 13;Reminding module 13 is received after cue, sends prompt tone, points out to use
Take card card away in family;If nobody takes card card away, control module 1 sends recovery signal to recycling module 5;Recycling module 5 is being received
After reclaiming signal, card card is recycled.If wherein described information reading module 8 cannot collect normal card card data
When, control module 1 directly sends transmission control signals, makes transmission module 6 drive card channel 11 that hair fastener card is driven to into card card
To export carried out at 3 and move back card process.
It is described to extract face in card card built-in chip storage image, card card surface printing image and live holder's image
Image includes:
Extract first facial image of card card built-in chip storage;
Using the first described human face image information as template, in card the figure of the image of surface printing and live holder is demonstrate,proved
The image-region maximum with the similarity measure of the template is matched as in, respectively as second facial image and described
3rd facial image.
When facial image is extracted in described pair of card card surface printing image and live holder's image, using carrying
First facial image of the card card built-in chip storage got carries out facial image as template using template matching algorithm
Extract, concrete grammar is:
The 1st, card is demonstrate,proved first facial image of built-in chip storage, (i.e. card demonstrate,proves surface printing in altimetric image to be checked
Image and the image of live holder) in traveled through, do similarity measure calculating.
2nd, according to similarity measure result of calculation, the position of altimetric image to be checked, makees when finding the value of similarity measure maximum
For the facial image in altimetric image to be checked.
Measure for Image Similarity calculate correlation function computing formula be:
Wherein, S (m, n) be image pixel to be detected, T (m, n) be template image pixel, R (i, j) be similarity measure, m
The line number of image pixel, n is the columns of image pixel.
Further, in the S102:
Described face Local Feature Extraction is:Face local shape factor is carried out using LBP feature extraction algorithms.
Described LBP feature extraction algorithms are described as follows:
The calculation of LBP operators is introduced first.As shown in figure 3, in certain regional area in piece image
Arbitrarily pixel f (xc,yc), with its central point gc, to 8 point g in 3 × 3 windows0~g7, texture T is defined as follows:
T~(g0-gc,…,g7-gc) (1)
Other pixels in window are done with binary conversion treatment by threshold value of window center point gray value, such as shown in formula (2):
T≈t(s(g0-gc),…,s(g7-gc)),
The binary number of one 8 is obtained, summation is weighted to pixel diverse location by formula (3), you can be somebody's turn to do
The LBP values of window:
The step of described employing LBP feature extraction algorithms carry out face local shape factor is as follows:
1st, human face region image is divided, is divided into the zonule of n*n.
2nd, above-mentioned LBP operators are carried out to each region to calculate, and draw the LBP values of each zonule.
3rd, the frequency that LBP values occur in the histogram of each zonule, i.e. each zonule is calculated;Then to this described
Histogram is normalized.
4th, being attached the histogram of each zonule for obtaining becomes a characteristic vector, the i.e. LBP of whole image
The face local feature of texture feature vector that is, described image.
Further, also include in the S102:
When card card truth identification result is pseudo-, it is pseudo- information to export holder's identification result.
When the card card truth identification is pseudo-, directly output holder's identification result is pseudo- information, now need not
The first face local feature and the 3rd face local feature are contrasted again, without special to the second face local
The 3rd face local feature of seeking peace is contrasted, and directly obtains identification result.Due to eliminating two contrast steps, greatly
Save time of identification, improve identification efficiency.
Further, in S103:
When the first face local feature and the 3rd face local feature comparing result and the second face office
Portion's feature and the 3rd face local feature comparing result are all true time, and output holder's identification result is really to believe
Breath;
When the first face local feature and the 3rd face local feature comparing result and the second face office
Portion's feature and the 3rd face local feature comparing result are not all true time, and it is pseudo- letter to export holder's identification result
Breath.
It is to apply the invention to recognize the preferred embodiment in identity card holder's identity that Fig. 4 is corresponding, it should be appreciated that
Range of application of the present invention includes but is not limited to system described in the preferred embodiment of the present invention.
Based on the corresponding embodiments of Fig. 4, details are as follows:
Embodiment is made up of three parts, wherein:
Card card scanning read module:It is responsible for the suction to identity card card, built-in chip storage information to read (comprising built-in
The image of chip-stored), image scanning, and built-in chip storage information and the identity card surface printing image that obtains of scanning are passed
Transport to industrial computer;
IMAQ module:The image of responsible collection site holder is simultaneously transmitted to industrial computer;
Industrial computer:It is responsible for receiving from card the information and image for demonstrate,proving scanning read module and the transmission of IMAQ module, and it is right
The image of built-in chip storage is processed with the image that directly transmission comes, and is performed face recognition algorithms and is carried out holder's identity
Identification decision.
Implementation steps in detail are as follows:
1st, scanning read module is demonstrate,proved by card and IMAQ module collects information, the identity of the storage of identity card built-in chip
Card surface printing image and the image of live holder, and transmit to industrial computer.
2nd, industrial computer holds receiving the information of identity card built-in chip storage, identity card surface printing image and scene
After the image of people, the recognition of face first step is performed, facial image is extracted:
Face extraction is carried out to the image of the built-in chip storage in identity card built-in chip storage information, and as first
Facial image;
Using the first facial image as template, identity card surface printing image and scene are held using template matching algorithm
The image of people carries out facial image extraction, match in card demonstrate,proves the image of the image of surface printing and live holder with it is described
The maximum image-region of the similarity measure of template, respectively as second facial image and the 3rd facial image.
3rd, industrial computer performs recognition of face second step, using LBP feature extractions after three facial images are extracted
Algorithm extracts the first face local feature, the identity card surface printing of the first facial image of identity card built-in chip storage
The second facial image the second face local feature and live holder the 3rd facial image the 3rd face local it is special
Levy.
4th, industrial computer performs the step of recognition of face the 3rd after three face local features are extracted, and face local is special
Levy contrast to judge:
The first face local feature and the second described face local feature are carried out into contrast judgement.If contrast judges
As a result it is puppet, then judges identity card as forged identity card, termination face local feature contrasts determination step, and export identity card and holds
The artificial pseudo- information of card.If contrast result of determination is true, judge that identity card is real identity card, and sentence into next step contrast
It is fixed;
By the first face local feature and the 3rd face local feature, the second face local feature and the 3rd people
Face local feature carries out contrast judgement.When the first face local feature and the 3rd face local feature comparing result with
The second face local feature and the 3rd face local feature comparing result are all true time, and output identity card holds the person
Part recognition result is genuine information.When the first face local feature and the 3rd face local feature comparing result and institute
State the second face local feature and the 3rd face local feature comparing result is not all true time, export holder's identification
As a result it is pseudo- information.
In a preferred embodiment of the invention, using the first facial image as template as template extraction the second face figure
Picture and the 3rd facial image, effectively reduce and extract the second facial image and the operand needed for the 3rd facial image, improve
The efficiency of recognition of face also improves the efficiency of identification simultaneously.When card release card is judged as puppet, directly terminate follow-up
Judge, export final identification result, the time being effectively shortened needed for identification, improve the effect of identification
Rate.By being identified to holder's identity automatically using face recognition technology, it is to avoid the inefficiency that artificial contrast brings
The low problem of the degree of accuracy, and simultaneously by the first face local feature, the second face local feature in using face recognition technology
Contrasted two-by-two with the 3rd face local feature, it is to avoid in convention control only the printing image on contrast card card surface and
The inadequate problem of the next degree of accuracy of live holder's picture strip so that holder's identification is full-automatic so that hold the person
More efficiently, result precision is also higher for part identification.
Personal identification method described in correspondence foregoing embodiments, Fig. 5 shows identification provided in an embodiment of the present invention
The structured flowchart of system.
With reference to Fig. 5, the system includes:
First extraction unit 51, it is special for extracting the first face local of the first facial image of card card built-in chip storage
Levy, block the second face local feature of the second facial image of card surface printing and the 3rd facial image of live holder
3rd face local feature;
First comparison unit 52, for contrasting the first face local feature and the second described face local feature,
The true and false is demonstrate,proved according to comparing result identification card;
Second comparison unit 53, for being true time when card card recognition result, contrasts the first face local feature and institute
The 3rd face local feature is stated, and contrasts the second face local feature and the 3rd face local feature, recognized according to comparing result
Holder's identity.
Further, also include before first extraction unit 51:
Second extraction unit, for extracting first facial image of card card built-in chip storage;
Matching unit, for using the first described human face image information as template, card demonstrate,prove the image of surface printing and
The image-region maximum with the similarity measure of the template is matched in the image of live holder, respectively as described second
Facial image and the 3rd facial image.
Further, first extraction unit 51 includes:
Described face Local Feature Extraction is:Face local shape factor is carried out using LBP feature extraction algorithms.
Further, first recognition unit 52:
When card card truth identification result is pseudo-, it is pseudo- information to export holder's identification result.
Further, second recognition unit 53 includes:
When the first face local feature and the 3rd face local feature comparing result and the second face office
Portion's feature and the 3rd face local feature comparing result are all true time, and output holder's identification result is really to believe
Breath;
When the first face local feature and the 3rd face local feature comparing result and the second face office
Portion's feature and the 3rd face local feature comparing result are not all true time, and it is pseudo- letter to export holder's identification result
Breath.
Embodiment described above is only used for illustrate technical scheme, rather than a limitation;Although with reference to front
State embodiment to be described in detail the present invention, it will be understood by those within the art that:It still can be to front
State the technical scheme described in each embodiment to modify, or equivalent is carried out to which part technical characteristic;And these are repaiied
Change or replace, do not make the spirit and scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution, all should
It is included within protection scope of the present invention.
Claims (10)
1. a kind of personal identification method, it is characterised in that include:
The first face local feature, the second people of card card surface printing for extracting the first facial image of card card built-in chip storage
3rd face local feature of the 3rd facial image of the second face local feature of face image and live holder;
The first face local feature and the second described face local feature are contrasted, it is true according to comparing result identification card card
It is pseudo-;
When card card recognition result is true time, the first face local feature and the 3rd face local feature are contrasted, and it is right
Than the second face local feature and the 3rd face local feature, holder's identity is recognized according to comparing result.
2. the method for claim 1, it is characterised in that in the first face figure for extracting card card built-in chip storage
First face local feature of picture, card demonstrate,prove the second face local feature of the second facial image of surface printing and scene holds
Before 3rd face local feature of the 3rd facial image of people, methods described also includes:
Extract first facial image of card card built-in chip storage;
Using the first described human face image information as template, in the image that card demonstrate,proves the image of surface printing and live holder
The image-region maximum with the similarity measure of the template is matched, respectively as second facial image and the described 3rd
Facial image.
3. the method for claim 1, it is characterised in that extract the first face head portrait, the second face head portrait and the 3rd people
The face local feature of human face image information includes in face head portrait:
Described face Local Feature Extraction is:Face local shape factor is carried out using LBP feature extraction algorithms.
4. the method for claim 1, it is characterised in that methods described also includes:
When card card truth identification result is pseudo-, it is pseudo- information to export holder's identification result.
5. the method for claim 1, its feature is described to recognize that holder's identity includes according to comparing result:
As the first face local feature and the 3rd face local feature comparing result and second face local spy
The 3rd face local feature comparing result of seeking peace is all true time, and output holder's identification result is genuine information;
As the first face local feature and the 3rd face local feature comparing result and second face local spy
The 3rd face local feature comparing result of seeking peace is not all true time, and it is pseudo- information to export holder's identification result.
6. a kind of identification system, it is characterised in that include:
First extraction unit, for extracting the first face local feature, the card of the first facial image of card card built-in chip storage
The 3rd of 3rd facial image of the second face local feature of the second facial image of card surface printing and live holder
Face local feature;
First comparison unit, for contrasting the first face local feature and the second described face local feature, according to right
The true and false is demonstrate,proved than result identification card;
Second comparison unit, for being true time when card card recognition result, contrasts the first face local feature and the described 3rd
Face local feature, and the second face local feature and the 3rd face local feature are contrasted, holder is recognized according to comparing result
Identity.
7. system as claimed in claim 6, it is characterised in that also include before first extraction unit:
Second extraction unit, for extracting first facial image of card card built-in chip storage;
Matching unit, as template, in card the image of surface printing and scene is demonstrate,proved for using the first described human face image information
The image-region maximum with the similarity measure of the template is matched in the image of holder, respectively as second face
Image and the 3rd facial image.
8. system as claimed in claim 6, it is characterised in that first extraction unit includes:
Described face Local Feature Extraction is:Face local shape factor is carried out using LBP feature extraction algorithms.
9. system as claimed in claim 6, it is characterised in that first recognition unit also includes:
When card card truth identification result is pseudo-, it is pseudo- information to export holder's identification result.
10. system as claimed in claim 6, it is characterised in that second recognition unit also includes:
As the first face local feature and the 3rd face local feature comparing result and second face local spy
The 3rd face local feature comparing result of seeking peace is all true time, and output holder's identification result is genuine information;
As the first face local feature and the 3rd face local feature comparing result and second face local spy
The 3rd face local feature comparing result of seeking peace is not all true time, and it is pseudo- information to export holder's identification result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610851468.0A CN106650363A (en) | 2016-09-26 | 2016-09-26 | Identity recognition method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610851468.0A CN106650363A (en) | 2016-09-26 | 2016-09-26 | Identity recognition method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106650363A true CN106650363A (en) | 2017-05-10 |
Family
ID=58853409
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610851468.0A Pending CN106650363A (en) | 2016-09-26 | 2016-09-26 | Identity recognition method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106650363A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109344703A (en) * | 2018-08-24 | 2019-02-15 | 深圳市商汤科技有限公司 | Method for checking object and device, electronic equipment and storage medium |
CN109684987A (en) * | 2018-12-19 | 2019-04-26 | 南京华科和鼎信息科技有限公司 | A kind of authentication system and method based on certificate |
CN112381023A (en) * | 2020-11-20 | 2021-02-19 | 中武(福建)跨境电子商务有限责任公司 | Cross-border e-commerce rapid identity recognition method and cross-border e-commerce rapid identity recognition system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001020564A1 (en) * | 1998-03-10 | 2001-03-22 | Ordicam Recherche Et Developpement Sa | Method for secure identification of a person and portable device implementing said method |
CN103426016A (en) * | 2013-08-14 | 2013-12-04 | 湖北微模式科技发展有限公司 | Method and device for authenticating second-generation identity card |
CN105243357A (en) * | 2015-09-15 | 2016-01-13 | 深圳市环阳通信息技术有限公司 | Identity document-based face recognition method and face recognition device |
CN105488475A (en) * | 2015-11-30 | 2016-04-13 | 西安闻泰电子科技有限公司 | Method for detecting human face in mobile phone |
CN105956578A (en) * | 2016-05-23 | 2016-09-21 | 深圳华中科技大学研究院 | Face verification method based on identity document information |
-
2016
- 2016-09-26 CN CN201610851468.0A patent/CN106650363A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001020564A1 (en) * | 1998-03-10 | 2001-03-22 | Ordicam Recherche Et Developpement Sa | Method for secure identification of a person and portable device implementing said method |
CN103426016A (en) * | 2013-08-14 | 2013-12-04 | 湖北微模式科技发展有限公司 | Method and device for authenticating second-generation identity card |
CN105243357A (en) * | 2015-09-15 | 2016-01-13 | 深圳市环阳通信息技术有限公司 | Identity document-based face recognition method and face recognition device |
CN105488475A (en) * | 2015-11-30 | 2016-04-13 | 西安闻泰电子科技有限公司 | Method for detecting human face in mobile phone |
CN105956578A (en) * | 2016-05-23 | 2016-09-21 | 深圳华中科技大学研究院 | Face verification method based on identity document information |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109344703A (en) * | 2018-08-24 | 2019-02-15 | 深圳市商汤科技有限公司 | Method for checking object and device, electronic equipment and storage medium |
CN109344703B (en) * | 2018-08-24 | 2021-06-25 | 深圳市商汤科技有限公司 | Object detection method and device, electronic equipment and storage medium |
CN109684987A (en) * | 2018-12-19 | 2019-04-26 | 南京华科和鼎信息科技有限公司 | A kind of authentication system and method based on certificate |
CN112381023A (en) * | 2020-11-20 | 2021-02-19 | 中武(福建)跨境电子商务有限责任公司 | Cross-border e-commerce rapid identity recognition method and cross-border e-commerce rapid identity recognition system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
CN105930709B (en) | Face recognition technology is applied to the method and device of testimony of a witness consistency check | |
CN103426016B (en) | Method and device for authenticating second-generation identity card | |
Wang et al. | A thermal hand vein pattern verification system | |
CN105956578B (en) | A kind of face verification method of identity-based certificate information | |
Chintalapati et al. | Automated attendance management system based on face recognition algorithms | |
CN102902959B (en) | Face recognition method and system for storing identification photo based on second-generation identity card | |
US6661907B2 (en) | Face detection in digital images | |
CN101584575B (en) | Age assessment method based on face recognition technology | |
CN102945366B (en) | A kind of method and device of recognition of face | |
CN109800643B (en) | Identity recognition method for living human face in multiple angles | |
CN109101871A (en) | A kind of living body detection device based on depth and Near Infrared Information, detection method and its application | |
CN111339806B (en) | Training method of lip language recognition model, living body recognition method and device | |
CN103778409A (en) | Human face identification method based on human face characteristic data mining and device | |
CN106650669A (en) | Face recognition method for identifying counterfeit photo deception | |
CN107958217A (en) | A kind of fingerprint classification identifying system and method based on deep learning | |
CN109145742A (en) | A kind of pedestrian recognition method and system | |
CN105243376A (en) | Living body detection method and device | |
CN111666835A (en) | Face living body detection method and device | |
CN110796101A (en) | Face recognition method and system of embedded platform | |
CN106650363A (en) | Identity recognition method and system | |
CN110807356A (en) | Living body detection method based on image lip language identification verification code | |
CN113011544B (en) | Face biological information identification method, system, terminal and medium based on two-dimensional code | |
CN108875553A (en) | Method, apparatus, system and the computer storage medium that the testimony of a witness is veritified | |
CN107705370A (en) | A kind of BRT bus rapid transits automatic ticket checker intelligence ticket card ticket checking system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |