WO2020051971A1 - 身份识别方法、装置、电子设备及计算机可读存储介质 - Google Patents
身份识别方法、装置、电子设备及计算机可读存储介质 Download PDFInfo
- Publication number
- WO2020051971A1 WO2020051971A1 PCT/CN2018/110654 CN2018110654W WO2020051971A1 WO 2020051971 A1 WO2020051971 A1 WO 2020051971A1 CN 2018110654 W CN2018110654 W CN 2018110654W WO 2020051971 A1 WO2020051971 A1 WO 2020051971A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- biometric information
- identified
- identification
- identity
- identity recognition
- Prior art date
Links
Images
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
- 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
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- 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
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
Definitions
- Embodiments of the present application relate to the field of data processing technologies, and in particular, to an identification method, device, electronic device, and computer-readable storage medium.
- the identity recognition in security systems usually uses 2D recognition technologies such as face recognition, fingerprint recognition, or pupil recognition, but due to the high misrecognition rate of the 2D recognition technology, it is far from meeting the increasing requirements of the public for security systems .
- Embodiments of the present application provide an identity recognition method, device, electronic device, and computer-readable storage medium.
- an embodiment of the present application provides an identity recognition method.
- the identification method includes:
- the first biometric information is a three-dimensional face image, a three-dimensional pupil image, or a three-dimensional fingerprint image; and / or, the second The biometric information is voiceprint data.
- Biometric information in response to the successful identification of the first identity, obtaining a second of the object to be identified Biometric information, including:
- the method further includes:
- the first biometric information of the object to be identified is repeatedly acquired, and the first identity of the object to be identified is performed according to the first biometric information.
- the present disclosure In response to the failure of the first identity recognition, repeatedly acquiring the first biometric information of the object to be identified, and performing the first identity recognition of the object to be identified according to the first biometric information, further includes:
- the present disclosure is In a fifth implementation manner of the aspect, after performing the second identity recognition on the object to be identified according to the second biometric information, the method further includes:
- a preset authorization operation is performed.
- first aspect Combining the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, and the first aspect of the first aspect Five implementation manners.
- a sixth implementation manner of the first aspect of the present disclosure in response to the second identity recognition failure, repeatedly acquiring first biometric information of the object to be identified, and according to the first biometric
- the feature information performs first identity recognition on the object to be identified, or repeatedly obtains second biometric information of the object to be identified, and performs second identity recognition on the object to be identified based on the second biometric information After that, it also includes:
- an embodiment of the present application provides an identity recognition device.
- the identity recognition device includes:
- a first identification module configured to obtain first biometric information of an object to be identified, and perform first identity identification on the object to be identified according to the first biometric information
- An acquisition module configured to acquire second biometric information of the object to be identified in response to the success of the first identification
- a second identification module is configured to perform a second identity identification on the object to be identified according to the second biometric information.
- the first biometric information is a three-dimensional face image, a three-dimensional pupil image, or a three-dimensional fingerprint image; and / or, the second The biometric information is voiceprint data.
- the obtaining module includes:
- An output sub-module configured to output second biometric prompt information in response to the success of the first identification
- the obtaining submodule is configured to obtain second biometric information of the object to be identified, wherein the second biometric information corresponds to the second biometric prompt information.
- the present disclosure further includes:
- a third identification module configured to repeatedly obtain first biometric information of the object to be identified in response to the failure of the first identification, and perform first identity identification on the object to be identified according to the first biometric information .
- the present disclosure further include:
- the first triggering module is configured to trigger a first preset alarm operation when the number of first identification failures exceeds a first preset number of thresholds.
- the present disclosure is in the second aspect
- the method further includes:
- a fourth identification module configured to repeatedly obtain first biometric information of the object to be identified in response to the second identity identification failure, and perform first identity identification on the object to be identified based on the first biometric information Or, repeatedly acquiring second biometric information of the object to be identified, and performing second identity recognition on the object to be identified according to the second biometric information;
- the execution module is configured to execute a preset authorization operation in response to the success of the second identification.
- the present disclosure further includes:
- the second triggering module is configured to trigger a second preset alarm operation when the number of first identification failures exceeds a second preset number of thresholds.
- an embodiment of the present application provides an electronic device including a memory and a processor, where the memory is configured to store one or more computer instructions that support an identity recognition device to execute the identity recognition method in the above first aspect, where The processor is configured to execute computer instructions stored in the memory.
- the identity recognition device may further include a communication interface for the identity recognition device to communicate with other equipment or a communication network.
- an embodiment of the present application provides a computer-readable storage medium for storing computer instructions used by an identity recognition device, which includes a computer for executing the identity recognition method in the first aspect as the identity recognition device instruction.
- the above technical solution uses mixed biometric information for comprehensive identification, that is, a dual identity recognition mechanism. This technical solution can effectively improve the accuracy of identification without increasing the complexity of the operation, thereby enhancing the security of the security system. To improve the user experience.
- FIG. 1 shows a flowchart of an identification method according to an embodiment of the present application
- FIG. 2 shows a flowchart of step S102 of the identification method according to the embodiment shown in FIG. 1;
- FIG. 3 shows a flowchart of an identification method according to another embodiment of the present application.
- FIG. 5 shows a structural block diagram of an identity recognition device according to an embodiment of the present application
- FIG. 6 shows a structural block diagram of the obtaining module 502 of the identity recognition device according to the embodiment shown in FIG. 5;
- FIG. 7 shows a structural block diagram of an identity recognition device according to another embodiment of the present application.
- FIG. 8 shows a structural block diagram of an identity recognition device according to still another embodiment of the present application.
- FIG. 9 shows a structural block diagram of an electronic device according to an embodiment of the present application.
- FIG. 10 is a schematic structural diagram of a computer system suitable for implementing an identification method according to an embodiment of the present application.
- the technical solution provided by the embodiment of the present application adopts mixed biometric information for comprehensive identification.
- the technical solution can effectively improve the accuracy of identification without increasing the complexity of the operation, thereby enhancing the security of the security system and improving User experience.
- FIG. 1 shows a flowchart of an identification method according to an embodiment of the present application.
- the method may be applied to a server side or a terminal side.
- the identification method includes the following steps S101-S103 :
- step S101 first biometric information of an object to be identified is acquired, and first identity recognition is performed on the object to be identified according to the first biometric information;
- step S102 in response to the success of the first identity recognition, acquiring second biometric information of the object to be identified;
- step S103 a second identity is performed on the object to be identified according to the second biometric information.
- the identity recognition in security systems usually uses 2D recognition technologies such as face recognition, fingerprint recognition, or pupil recognition, but due to the high misrecognition rate of the 2D recognition technology, it is far from meeting the increasing requirements of the public for security systems. .
- an identification method uses mixed biometric information for comprehensive identification, that is, adopts a dual identification mechanism.
- This technical solution does not increase the complexity of the operation. It can effectively improve the accuracy of identity recognition, thereby enhancing the security of the security system and improving the user experience.
- the first biometric information includes one or more of the following feature information: a face image, a pupil image, and a fingerprint image, wherein the face image, the pupil, Both the image and the fingerprint image can be a three-dimensional image or a two-dimensional image.
- the three-dimensional image has a high accuracy rate but a large amount of calculation, and a two-dimensional image has a small amount of calculation but a low accuracy rate.
- Those skilled in the art can provide a first biological
- the feature information is selected, which is not specifically limited in this application.
- the second biometric information is voiceprint data
- the voiceprint data refers to a sound wave spectrum carrying speech information displayed by an electroacoustic instrument. Because the vocal organs used by people in speech: tongue, teeth, throat, lungs, and nasal cavity are all different in size and shape, that is, the voiceprint patterns of any two people are also different, and the acoustic characteristics of each person's speech It has both relative stability and variability. Therefore, voiceprint data can be used to achieve identity recognition.
- the acquisition of the first biometric information may be performed by using an image acquisition device such as a camera or a camera.
- the image acquisition device may be an image acquisition device in a mobile electronic device, such as A smart phone, a camera provided with a smart tablet, and the like; at the same time, the image acquisition device may also be an image acquisition device in a fixed electronic device, such as a camera on a gate.
- the first biometric information may be obtained by an image acquisition device of the terminal and sent to the server side; if the identity recognition method is applied to the terminal side, the terminal may The first biometric information is directly acquired by means of an image acquisition device. In an optional implementation manner of this embodiment, when acquiring the first biometric information, the terminal may start acquiring the first biometric information when detecting that the distance between the object to be identified and the terminal is less than a preset distance threshold.
- a feature matching method when performing first identity recognition on the object to be identified according to the first biometric information, a feature matching method may be adopted. Specifically, the first biometric is first extracted. The feature data of the feature information is then matched with a pre-stored trained feature model, and the output of the successfully matched model corresponds to the recognition result of the first identity recognition.
- the step S102 that is, the step of obtaining the second biometric information of the object to be identified in response to the success of the first identification, includes the following steps: S201-S202:
- step S201 in response to the first identity recognition being successful, outputting second biometric prompt information
- step S202 second biometric information of the object to be identified is obtained, wherein the second biometric information corresponds to the second biometric prompt information.
- the object to be identified is guided to output the second biometric information which is beneficial to the identification.
- the second biometric prompt information is output, wherein the second biometric prompt information is used to guide the object to be identified; and the second biometric information of the object to be identified is obtained.
- the second biometric information corresponds to the second biometric prompt information.
- the second biometric prompt information may be, for example, textual information or voice information, so that an object to be identified can read the textual information or repeat the voice information, and further Obtaining second biometric information.
- the second biometric prompt information may be output by the output device of the terminal according to the server-side instruction, that is, the step S201 may include: in response to the success of the first identification, Send a second biometric prompt information output instruction to the terminal, where the second biometric prompt information output instruction is used to trigger the terminal to output the second biometric prompt information; if the identity recognition method is applied to the terminal side, then The terminal may directly output the second biometric prompt information by using an output device.
- the obtaining of the second biometric information may be performed by using a sound collection device such as a microphone or a recorder.
- the second biometric information can be obtained by the terminal's sound collection device and sent to the server side, that is, the step S202 can include: responding to the second biometric prompt information Output the second biometric information acquisition instruction to the terminal; receive the second biometric information sent by the terminal; if the identity recognition method is applied to the terminal, the terminal outputs the second biometric prompt
- the second biometric information can be directly obtained by using a sound collection device.
- the step S101 is to obtain first biometric information of an object to be identified, and perform first identity identification on the object to be identified based on the first biometric information.
- the method further includes the step of repeating the first identity identification when the first identity identification fails, that is, as shown in FIG. 3, the method includes the following steps S301-S304:
- step S301 first biometric information of an object to be identified is obtained, and first identity recognition is performed on the object to be identified according to the first biometric information;
- step S302 in response to the failure of the first identity recognition, repeatedly acquiring the first biometric information of the object to be identified, and performing the first identity recognition on the object to be identified according to the first biometric information;
- step S303 in response to the successful identification of the first identity, acquiring second biometric information of the object to be identified;
- step S304 a second identity is performed on the object to be identified according to the second biometric information.
- the first identity recognition fails, the first biometric information of the object to be identified is obtained again. To perform the first identification again. However, the first identification cannot be repeated indefinitely.
- the number of first identification failures exceeds a preset first preset number of thresholds, the identification of the object to be identified is confirmed. If it fails, the object to be identified is considered to be an illegal object, and a first preset alarm operation is triggered.
- the first preset alarm operation may include one or more of the following operations: sound and light alarm, audio alarm, video alarm, information alarm, mail alarm, and so on.
- the audible and visual alarm operation can be started immediately, the alarm audio can be played on the spot to turn on the optical device for alarm, or the alarm information can be sent to the administrator immediately to prompt it to be illegal.
- Object for processing when an object to be identified is found to be an illegal object, the audible and visual alarm operation can be started immediately, the alarm audio can be played on the spot to turn on the optical device for alarm, or the alarm information can be sent to the administrator immediately to prompt it to be illegal.
- Object for processing can be started immediately, the alarm audio can be played on the spot to turn on the optical device for alarm, or the alarm information can be sent to the administrator immediately to prompt it to be illegal.
- the first preset number of times threshold can be set according to actual application requirements, for example, it can be set to three times.
- step S103 that is, the step of performing a second identity identification on the object to be identified according to the second biometric information
- the method further includes executing according to a second identity identification result.
- step S401 acquiring first biometric information of an object to be identified, and performing first identity recognition on the object to be identified according to the first biometric information;
- step S402 in response to the successful identification of the first identity, acquiring second biometric information of the object to be identified;
- step S403 performing a second identity recognition on the object to be identified according to the second biometric information
- step S404 in response to the failure of the second identity recognition, repeatedly acquiring the first biometric information of the object to be identified, and performing the first identity recognition on the object to be identified according to the first biometric information, or Repeatedly acquiring second biometric information of the object to be identified, and performing second identity recognition on the object to be identified according to the second biometric information;
- step S405 in response to the success of the second identification, a preset authorization operation is performed.
- the first biometric information may be repeatedly obtained for the first identity recognition.
- the second biometric information is repeatedly obtained for the second identity recognition, or in order to save the calculation amount and the calculation time, the second biometric information may also be obtained directly for the second identity recognition. If both the first identification and the second identification are successful, the object to be identified is considered to be a legal object, and the preset authorization operation is triggered to be executed.
- the preset authorization operation may include one or more of the following operations: sending a channel opening instruction, sending a startup instruction, sending a trigger instruction, and the like. It should be noted that the authorization operation has different contents in different application scenarios. Therefore, those skilled in the art can set the preset authorization operation content according to the actual application requirements and the characteristics of the application scenario. This application It is not specifically limited.
- the second preset alarm operation may also include one or more of the following operations: sound and light alarm, audio alarm, video alarm, information alarm, mail alarm, etc. Wait.
- the second preset alarm operation may be the same as or different from the first preset alarm operation, which is not specifically limited in this application.
- the second preset number of times threshold may be the same as the first preset number of times threshold, or may be different. Similar to the first preset number of times threshold, the second preset number of times threshold may be based on actual application. Need to be set, for example, it can be set to twice.
- FIG. 5 shows a structural block diagram of an identification device according to an embodiment of the present application.
- the device may be implemented as part or all of an electronic device through software, hardware, or a combination of the two, and may be implemented as a server or a terminal.
- the identity recognition device includes:
- a first identification module 501 configured to obtain first biometric information of an object to be identified, and perform first identity identification on the object to be identified according to the first biometric information;
- the obtaining module 502 is configured to obtain second biometric information of the object to be identified in response to the success of the first identification
- the second identification module 503 is configured to perform a second identity identification on the object to be identified according to the second biometric information.
- the identity recognition in security systems usually uses 2D recognition technologies such as face recognition, fingerprint recognition, or pupil recognition, but due to the high misrecognition rate of the 2D recognition technology, it is far from meeting the increasing requirements of the public for security systems. .
- an identity recognition device uses mixed biometric information for comprehensive identity recognition, that is, a dual identity recognition mechanism.
- This technical solution does not increase the complexity of the operation. It can effectively improve the accuracy of identity recognition, thereby enhancing the security of the security system and improving the user experience.
- the first biometric information includes one or more of the following feature information: a face image, a pupil image, and a fingerprint image, wherein the face image, the pupil, Both the image and the fingerprint image can be a three-dimensional image or a two-dimensional image.
- the three-dimensional image has a high accuracy but a large amount of calculations, and a two-dimensional image has a small amount of calculations but a low accuracy.
- Those skilled in the art can perform a The feature information is selected, which is not specifically limited in this application.
- the second biometric information is voiceprint data
- the voiceprint data refers to a sound wave spectrum carrying speech information displayed by an electroacoustic instrument. Because the vocal organs used by people in speech: tongue, teeth, throat, lungs, and nasal cavity are all different in size and shape, that is, the voiceprint patterns of any two people are also different, and the acoustic characteristics of each person's speech It has both relative stability and variability. Therefore, voiceprint data can be used to achieve identity recognition.
- the acquisition of the first biometric information may be performed by using an image acquisition device such as a camera or a camera.
- the image acquisition device may be an image acquisition device on a mobile electronic device, for example, Smart phones, smart cameras, and other cameras; meanwhile, the image acquisition device may also be an image acquisition device on a fixed electronic device, such as a camera on a gate.
- the first biometric information may be acquired by an image acquisition device of the terminal and sent to the first recognition module 501; if the identity identification device is implemented as a terminal, the first An identification module 501 can directly obtain the first biometric information.
- the terminal or the first identification module 501 may start acquiring the address when it is detected that the distance between the object to be identified and the terminal is less than a preset distance threshold. The first biometric information is described.
- the first identification module 501 when the first identification module 501 performs first identity identification on the object to be identified according to the first biometric information, a feature matching method may be adopted.
- the The first recognition module 501 may be configured to: first extract feature data of the first biometric information, and then match it with a pre-stored trained feature model, and the output of the successfully matched model corresponds to the first identity recognition Recognition results.
- Feature matching methods or other identification methods may be used, and details are not described herein again.
- the obtaining module 502 includes:
- An output sub-module 601 configured to output second biometric prompt information in response to the success of the first identification
- the obtaining sub-module 602 is configured to obtain second biometric information of the object to be identified, wherein the second biometric information corresponds to the second biometric prompt information.
- the second biometric prompt information is output through the output sub-module 601 to guide the object to be identified so that it outputs a second biometric that is good for identification.
- Feature information Specifically, when the first identification is successful, the output submodule 601 outputs second biometric prompt information, wherein the second biometric prompt information is used to guide the object to be identified; the acquisition submodule 602 acquires the pending The second biometric information of the identification object, wherein the second biometric information corresponds to the second biometric prompt information.
- the second biometric prompt information may be, for example, textual information or voice information, so that an object to be identified can read the textual information or repeat the voice information, and further Obtaining second biometric information.
- the second biometric prompt information may be output by the output device of the terminal according to the instruction of the output submodule 601, that is, the output submodule 601 may be configured to respond to the first Upon successful identification, a second biometric prompt information output instruction is sent to the terminal, wherein the second biometric prompt information output instruction is used to trigger the terminal to output the second biometric prompt information; if the identity recognition device applies At the terminal, the output sub-module 601 may directly output the second biometric prompt information.
- the obtaining of the second biometric information may be performed by using a sound collection device such as a microphone or a recorder.
- the second biometric information may be acquired by the terminal's sound collection device and sent to the acquisition submodule 602, that is, the acquisition submodule 602 may be configured to respond to the first Output the second biometric prompt information, and send a second biometric information acquisition instruction to the terminal; receive the second biometric information sent by the terminal; if the identity recognition device is applied to the terminal, output the second in the output submodule 601 After the biometric prompt information, the acquiring sub-module 602 may directly acquire the second biometric information.
- the device further includes a part that repeatedly performs the first identity identification when the first identity identification fails, that is, as shown in FIG. 7, the device includes:
- a first recognition module 701 configured to obtain first biometric information of an object to be identified, and perform first identity recognition on the object to be identified according to the first biometric information;
- the third identification module 702 is configured to repeatedly obtain first biometric information of the object to be identified in response to the failure of the first identity identification, and perform a first identity on the object to be identified based on the first biometric information. Identify
- the obtaining module 703 is configured to obtain second biometric information of the object to be identified in response to the success of the first identification
- the second identification module 704 is configured to perform a second identity identification on the object to be identified according to the second biometric information.
- the third recognition module 702 obtains the identity of the object to be recognized again.
- the first biometric information is firstly identified again.
- the first identity recognition cannot be repeated indefinitely.
- a first trigger module may be set so that it is configured to trigger a first preset alarm when the number of failures of the first identity recognition exceeds a preset first preset number of thresholds operating.
- the first preset alarm operation may include one or more of the following operations: sound and light alarm, audio alarm, video alarm, information alarm, mail alarm, and so on.
- the first triggering module can immediately start the audible and visual alarm operation, play the alarm audio on-site to turn on the optical device for alarm, or immediately send an alarm message to the administrator to promote it in the first place. Handle illegal objects for a while.
- the first preset number of times threshold can be set according to actual application requirements, for example, it can be set to three times.
- the device further includes a part that performs a corresponding operation according to a second identity recognition result, that is, as shown in FIG. 8, the device includes:
- a first identification module 801 configured to obtain first biometric information of an object to be identified, and perform first identity identification on the object to be identified according to the first biometric information;
- the obtaining module 802 is configured to obtain second biometric information of the object to be identified in response to the success of the first identification
- a second identification module 803 configured to perform second identity identification on the object to be identified according to the second biometric information
- the fourth identification module 804 is configured to repeatedly obtain the first biometric information of the object to be identified in response to the failure of the second identification, and perform the first identity on the object to be identified according to the first biometric information. Identify, or repeatedly obtain second biometric information of the object to be identified, and perform second identity recognition on the object to be identified according to the second biometric information;
- the execution module 805 is configured to execute a preset authorization operation in response to the success of the second identification.
- the fourth identification module 804 may repeatedly acquire the first biometric information Perform the first identity recognition, and repeatedly obtain the second biometric information for the second identity after the first identity recognition is successful, or, in order to save the calculation amount and the calculation time, the second biometric information may be directly and repeatedly acquired for the second identity Identity identification; if both the first identity identification and the second identity identification are successful, the object to be identified is considered to be a legitimate object, and the execution module 805 triggers the execution of the preset authorization operation.
- the preset authorization operation may include one or more of the following operations: sending a channel opening instruction, sending a startup instruction, sending a trigger instruction, and the like. It should be noted that the authorization operation has different contents in different application scenarios. Therefore, those skilled in the art can set the preset authorization operation content according to the actual application requirements and the characteristics of the application scenario. This application It is not specifically limited.
- a second trigger module may be set so that it is configured to trigger a second preset alarm operation.
- the second preset alarm operation may also include one or more of the following operations: sound and light alarm, audio alarm, video alarm, information alarm, mail alarm, etc. Wait.
- the second preset alarm operation may be the same as or different from the first preset alarm operation, which is not specifically limited in this application.
- the second preset number of times threshold may be the same as the first preset number of times threshold, or may be different. Similar to the first preset number of times threshold, the second preset number of times threshold may be based on actual application. Need to be set, for example, it can be set to twice.
- FIG. 9 shows a structural block diagram of an electronic device according to an embodiment of the present application.
- the electronic device 900 includes a memory 901 and a processor 902;
- the memory 901 is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 902 to implement any one of the foregoing method steps.
- FIG. 10 is a schematic structural diagram of a computer system suitable for implementing an identity recognition method according to an embodiment of the present application.
- the computer system 1000 includes a central processing unit (CPU) 1001, which can be loaded into a random access memory (RAM) 1003 according to a program stored in a read-only memory (ROM) 1002 or from a storage portion 1008. Instead, various processes in the above-mentioned embodiments are executed. In the RAM 1003, various programs and data required for the operation of the system 1000 are also stored.
- the CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004.
- An input / output (I / O) interface 1005 is also connected to the bus 1004.
- the following components are connected to the I / O interface 1005: an input portion 1006 including a keyboard, a mouse, etc .; an output portion 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc .; and a speaker; a storage portion 1008 including a hard disk, etc. ; And a communication section 1009 including a network interface card such as a LAN card, a modem, and the like. The communication section 1009 performs communication processing via a network such as the Internet.
- the driver 1010 is also connected to the I / O interface 1005 as needed.
- a removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed.
- the method described above may be implemented as a computer software program.
- embodiments of the present application include a computer program product including a computer program tangibly embodied on a readable medium thereon, the computer program containing program code for performing the identification method.
- the computer program may be downloaded and installed from a network through the communication portion 1009, and / or installed from a removable medium 1011.
- each block in the roadmap or block diagram may represent a module, program segment, or portion of code that contains one or more components that implement a specified logical function Executable instructions.
- the functions noted in the blocks may also occur in a different order than those marked in the drawings. For example, two successively represented boxes may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved.
- each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts can be implemented by a dedicated hardware-based system that performs the specified function or operation , Or it can be implemented with a combination of dedicated hardware and computer instructions.
- the units or modules described in the embodiments of the present application can be implemented by software, and can also be implemented by hardware.
- the described units or modules may also be provided in the processor, and the names of these units or modules do not, in some cases, define the unit or module itself.
- an embodiment of the present application further provides a computer-readable storage medium.
- the computer-readable storage medium may be a computer-readable storage medium included in the device described in the foregoing implementation manner; or may exist separately.
- the computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the methods described in the embodiments of the present application.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Security & Cryptography (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
一种身份识别方法、装置、电子设备及计算机可读存储介质,所述方法包括:获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别(S101);响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息(S102);根据所述第二生物特征信息对于所述待识别对象进行第二身份识别(S103)。在不增加操作复杂度的情况下,能够有效提高身份识别的准确率,进而增强了安防***的安全性,提升了用户的使用体验。
Description
本申请实施例涉及数据处理技术领域,具体涉及一种身份识别方法、装置、电子设备及计算机可读存储介质。
随着数据技术的发展以及社会的进步,大众对于安防***的要求越来越高。目前安防***中的身份识别通常使用人脸识别、指纹识别或瞳孔识别等2D识别技术,但由于所述2D识别技术的误识率较高,因此远远不能满足大众对于安防***日益提高的要求。
发明内容
本申请实施例提供一种身份识别方法、装置、电子设备及计算机可读存储介质。
第一方面,本申请实施例中提供了一种身份识别方法。
具体的,所述身份识别方法,包括:
获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;
根据所述第二生物特征信息对于所述待识别对象进行第二身份识别。
结合第一方面,本申请实施例在第一方面的第一种实现方式中,所述第一生物特征信息为三维脸部图像、三维瞳孔图像或三维指纹图像;和/或,所述第二生物特征信息为声纹数据。
结合第一方面和第一方面的第一种实现方式,本申请实施例在第一方面的第二种实现方式中,所述响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息,包括:
响应于第一身份识别成功,输出第二生物特征提示信息;
获取所述待识别对象的第二生物特征信息,其中,所述第二生物特征信 息与所述第二生物特征提示信息相对应。
结合第一方面、第一方面的第一种实现方式和第一方面的第二种实现方式,本公开在第一方面的第三种实现方式中,所述获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别之后,还包括:
响应于第一身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别。
结合第一方面、第一方面的第一种实现方式、第一方面的第二种实现方式和第一方面的第三种实现方式,本公开在第一方面的第四种实现方式中,所述响应于第一身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别之后,还包括:
当第一身份识别失败次数超过第一预设次数阈值时,触发第一预设报警操作。
结合第一方面、第一方面的第一种实现方式、第一方面的第二种实现方式、第一方面的第三种实现方式和第一方面的第四种实现方式,本公开在第一方面的第五种实现方式中,所述根据所述第二生物特征信息对于所述待识别对象进行第二身份识别之后,还包括:
响应于第二身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别,或者,重复获取所述待识别对象的第二生物特征信息,并根据所述第二生物特征信息对于所述待识别对象进行第二身份识别;
响应于第二身份识别成功,执行预设授权操作。
结合第一方面、第一方面的第一种实现方式、第一方面的第二种实现方式、第一方面的第三种实现方式、第一方面的第四种实现方式和第一方面的第五种实现方式,本公开在第一方面的第六种实现方式中,所述响应于第二身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别,或者,重复获取所述待识别对象的第二生物特征信息,并根据所述第二生物特征信息对于所述待识别对象进行第二身份识别之后,还包括:
当第一身份识别失败次数超过第二预设次数阈值时,触发第二预设报警操作。
第二方面,本申请实施例中提供了一种身份识别装置。
具体的,所述身份识别装置,包括:
第一识别模块,被配置为获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
获取模块,被配置为响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;
第二识别模块,被配置为根据所述第二生物特征信息对于所述待识别对象进行第二身份识别。
结合第二方面,本申请实施例在第二方面的第一种实现方式中,所述第一生物特征信息为三维脸部图像、三维瞳孔图像或三维指纹图像;和/或,所述第二生物特征信息为声纹数据。
结合第二方面和第二方面的第一种实现方式,本申请实施例在第二方面的第二种实现方式中,所述获取模块包括:
输出子模块,被配置为响应于第一身份识别成功,输出第二生物特征提示信息;
获取子模块,被配置为获取所述待识别对象的第二生物特征信息,其中,所述第二生物特征信息与所述第二生物特征提示信息相对应。
结合第二方面、第二方面的第一种实现方式和第二方面的第二种实现方式,本公开在第二方面的第三种实现方式中,还包括:
第三识别模块,被配置为响应于第一身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别。
结合第二方面、第二方面的第一种实现方式、第二方面的第二种实现方式和第二方面的第三种实现方式,本公开在第二方面的第四种实现方式中,还包括:
第一触发模块,被配置为当第一身份识别失败次数超过第一预设次数阈值时,触发第一预设报警操作。
结合第二方面、第二方面的第一种实现方式、第二方面的第二种实现方 式、第二方面的第三种实现方式和第二方面的第四种实现方式,本公开在第二方面的第五种实现方式中,还包括:
第四识别模块,被配置为响应于第二身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别,或者,重复获取所述待识别对象的第二生物特征信息,并根据所述第二生物特征信息对于所述待识别对象进行第二身份识别;
执行模块,被配置为响应于第二身份识别成功,执行预设授权操作。
结合第二方面、第二方面的第一种实现方式、第二方面的第二种实现方式、第二方面的第三种实现方式、第二方面的第四种实现方式和第二方面的第五种实现方式,本公开在第二方面的第六种实现方式中,还包括:
第二触发模块,被配置为当第一身份识别失败次数超过第二预设次数阈值时,触发第二预设报警操作。
第三方面,本申请实施例提供了一种电子设备,包括存储器和处理器,所述存储器用于存储一条或多条支持身份识别装置执行上述第一方面中身份识别方法的计算机指令,所述处理器被配置为用于执行所述存储器中存储的计算机指令。所述身份识别装置还可以包括通信接口,用于身份识别装置与其他设备或通信网络通信。
第四方面,本申请实施例提供了一种计算机可读存储介质,用于存储身份识别装置所用的计算机指令,其包含用于执行上述第一方面中身份识别方法为身份识别装置所涉及的计算机指令。
本申请实施例提供的技术方案可以包括以下有益效果:
上述技术方案采用混合生物特征信息进行综合身份识别,即采用双重身份识别机制,该技术方案在不增加操作复杂度的情况下,能够有效提高身份识别的准确率,进而增强了安防***的安全性,提升了用户的使用体验。
应当理解的是,以上的一般描述和后文的细节描述仅是示例性和解释性的,并不能限制本申请实施例。
结合附图,通过以下非限制性实施方式的详细描述,本申请实施例的其它特征、目的和优点将变得更加明显。在附图中:
图1示出根据本申请一实施方式的身份识别方法的流程图;
图2示出根据图1所示实施方式的身份识别方法的步骤S102的流程图;
图3示出根据本申请另一实施方式的身份识别方法的流程图;
图4示出根据本申请再一实施方式的身份识别方法的流程图;
图5示出根据本申请一实施方式的身份识别装置的结构框图;
图6示出根据图5所示实施方式的身份识别装置的获取模块502的结构框图;
图7示出根据本申请另一实施方式的身份识别装置的结构框图;
图8示出根据本申请再一实施方式的身份识别装置的结构框图;
图9示出根据本申请一实施方式的电子设备的结构框图;
图10是适于用来实现根据本申请一实施方式的身份识别方法的计算机***的结构示意图。
下文中,将参考附图详细描述本申请实施例的示例性实施方式,以使本领域技术人员可容易地实现它们。此外,为了清楚起见,在附图中省略了与描述示例性实施方式无关的部分。
在本申请实施例中,应理解,诸如“包括”或“具有”等的术语旨在指示本说明书中所公开的特征、数字、步骤、行为、部件、部分或其组合的存在,并且不欲排除一个或多个其他特征、数字、步骤、行为、部件、部分或其组合存在或被添加的可能性。
另外还需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请实施例。
本申请实施例提供的技术方案采用混合生物特征信息进行综合身份识别,该技术方案在不增加操作复杂度的情况下,能够有效提高身份识别的准确率,进而增强了安防***的安全性,提升了用户的使用体验。
图1示出根据本申请一实施方式的身份识别方法的流程图,所述方法可应用于服务器侧也可应用于终端侧,如图1所示,所述身份识别方法包括以下步骤S101-S103:
在步骤S101中,获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
在步骤S102中,响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;
在步骤S103中,根据所述第二生物特征信息对于所述待识别对象进行第二身份识别。
上文提及,随着数据技术的发展以及社会的进步,大众对于安防***的要求越来越高。目前安防***中的身份识别通常使用人脸识别、指纹识别或瞳孔识别等2D识别技术,但由于所述2D识别技术的误识率较高,因此远远不能满足大众对于安防***日益提高的要求。
考虑到上述问题,在该实施方式中,提出一种身份识别方法,该方法采用混合生物特征信息进行综合身份识别,即采用双重身份识别机制,该技术方案在不增加操作复杂度的情况下,能够有效提高身份识别的准确率,进而增强了安防***的安全性,提升了用户的使用体验。
在本实施例的一个可选实现方式中,所述第一生物特征信息包括以下特征信息中的一种或多种:脸部图像、瞳孔图像和指纹图像,其中,所述脸部图像、瞳孔图像和指纹图像均可为三维图像或二维图像,三维图像准确率高,但运算量大,二维图像运算量小但准确率低,本领域技术人员可根据实际应用的需要对于第一生物特征信息进行选择,本申请对其不作具体限定。
在本实施例的一个可选实现方式中,所述第二生物特征信息为声纹数据,所述声纹数据指的是用电声学仪器显示的携带言语信息的声波频谱。由于人在讲话时使用的发声器官:舌、牙齿、喉头、肺、鼻腔在尺寸和形态方面均存在一定的差异,即任何两个人的声纹图谱也都不尽相同,每个人的语音声学特征既有相对稳定性,又有变异性,因此,可利用声纹数据来实现身份识别。
在本实施例的一个可选实现方式中,所述第一生物特征信息的获取可采用摄像头、照相机等图像采集设备来完成,所述图像采集设备可以为移动电子设备中的图像采集设备,例如智能手机、智能平板电脑自带的摄像头等;同时所述图像采集设备也可以为固定电子设备中的图像采集设备,例如闸机头上的摄像头等。
其中,若所述身份识别方法应用于服务器侧,则所述第一生物特征信息可由终端的图像采集设备获取并发送至服务器侧;若所述身份识别方法应用于终端侧,则所述终端可借助图像采集设备直接获取所述第一生物特征信息。在本实施例的一个可选实现方式中,终端在获取第一生物特征信息时,可在检测到待识别对象与终端之间的距离小于预设距离阈值时启动第一生物特征信息的获取。
在本实施例的一个可选实现方式中,在根据所述第一生物特征信息对于所述待识别对象进行第一身份识别时,可采用特征匹配方法,具体地,首先提取所述第一生物特征信息的特征数据,然后将其与预先存储的训练好的特征模型进行匹配,匹配成功的模型输出就对应于第一身份识别的识别结果。当然,在实际应用中,如果进行的是三维人脸识别,在有深度的情况下,则需要对三维人脸图像的X、Y、Z轴分别进行深度对比匹配,这样相对于三维活体识别的仅仅识别出来Z轴存在来说,三维人脸识别分别将在X、Y、Z轴对识别出来的人脸图像与预先存储的训练好的模型进行对别匹配,这样进一步大大提高了人脸识别的安全性与准确性。本领域技术人员还可以选择其它身份识别方法,以上仅为示例性说明,不能够被理解为是对本申请的限制。
在本实施例的一个可选实现方式中,与所述第一身份识别类似,在根据所述第二生物特征信息对于所述待识别对象进行第二身份识别时,也可采用特征匹配方法或其他身份识别方法,在此不再赘述。
在本实施例的一个可选实现方式中,如图2所示,所述步骤S102,即响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息的步骤,包括以下步骤S201-S202:
在步骤S201中,响应于第一身份识别成功,输出第二生物特征提示信息;
在步骤S202中,获取所述待识别对象的第二生物特征信息,其中,所述第二生物特征信息与所述第二生物特征提示信息相对应。
为了提高第二生物特征信息的规范性和普适性,在该实施方式中,通过对于待识别对象进行引导使其输出利于身份识别的第二生物特征信息。具体地,当第一身份识别成功时,输出第二生物特征提示信息,其中,所述第二生物特征提示信息用于对于待识别对象进行引导;获取所述待识别对象的第二生物特征信息,其中,所述第二生物特征信息与所述第二生物特征提示信 息相对应。
在本实施例的一个可选实现方式中,所述第二生物特征提示信息比如可以为文字性信息或者语音信息,使得待识别对象能够读出所述文字性信息或者重复所述语音信息,进而获得第二生物特征信息。
其中,若所述身份识别方法应用于服务器侧,则所述第二生物特征提示信息可由终端的输出设备根据服务器侧的指令输出,即所述步骤S201可包括:响应于第一身份识别成功,向终端发送第二生物特征提示信息输出指令,其中,所述第二生物特征提示信息输出指令用于触发所述终端输出第二生物特征提示信息;若所述身份识别方法应用于终端侧,则所述终端可借助输出设备直接输出所述第二生物特征提示信息。
在本实施例的一个可选实现方式中,所述第二生物特征信息的获取可采用收声器、录音机等声音采集设备来完成。
其中,若所述身份识别方法应用于服务器侧,则所述第二生物特征信息可由终端的声音采集设备获取并发送至服务器侧,即所述步骤S202可包括:响应于第二生物特征提示信息的输出,向终端发送第二生物特征信息获取指令;接收所述终端发送的第二生物特征信息;若所述身份识别方法应用于终端侧,则所述终端在输出第二生物特征提示信息后可借助声音采集设备直接获取所述第二生物特征信息。
在本实施例的一个可选实现方式中,所述步骤S101,即获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别的步骤之后,还包括当第一身份识别失败时重复进行第一身份识别的步骤,即如图3所示,所述方法包括以下步骤S301-S304:
在步骤S301中,获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
在步骤S302中,响应于第一身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
在步骤S303中,响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;
在步骤S304中,根据所述第二生物特征信息对于所述待识别对象进行第 二身份识别。
为了避免噪声、光线、设备污点或者其他意外事件的影响,提高身份识别的鲁棒性,在该实施方式中,若第一身份识别失败,则再次获取所述待识别对象的第一生物特征信息,再次进行第一身份识别。但第一身份识别不能无限制地重复进行,在本实施例的一个可选实现方式中,当第一身份识别失败次数超过预设第一预设次数阈值时,就确认所述待识别对象识别失败,即认为所述待识别对象为非法对象,则触发第一预设报警操作。其中,所述第一预设报警操作可包括以下操作中的一种或多种:声光报警、音频报警、视频报警、信息报警、邮件报警等等。比如,当发现某一待识别对象为非法对象时,可立即启动声光报警操作,现场播放报警音频开启光学设备进行报警,也可立即向管理员发送报警信息以促使其在第一时间对于非法对象进行处理。
其中,所述第一预设次数阈值可根据实际应用的需要进行设置,比如可设置为三次。
在本实施例的一个可选实现方式中,所述步骤S103,即根据所述第二生物特征信息对于所述待识别对象进行第二身份识别的步骤之后,还包括根据第二身份识别结果执行相应操作的步骤,即如图4所示,所述方法包括以下步骤S401-S405:
在步骤S401中,获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
在步骤S402中,响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;
在步骤S403中,根据所述第二生物特征信息对于所述待识别对象进行第二身份识别;
在步骤S404中,响应于第二身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别,或者,重复获取所述待识别对象的第二生物特征信息,并根据所述第二生物特征信息对于所述待识别对象进行第二身份识别;
在步骤S405中,响应于第二身份识别成功,执行预设授权操作。
在该实施方式中,若第一身份识别成功第二身份识别失败,则暂时认为 有可能是在获取生物特征信息的时候出现了影响事件,因此可重复获取第一生物特征信息进行第一身份识别,第一身份识别成功后再重复获取第二生物特征信息进行第二身份识别,或者,为了节省计算量,节省计算时间,也可直接重复获取第二生物特征信息进行第二身份识别;若第一身份识别和第二身份识别均成功,则认为所述待识别对象为合法对象,则触发执行所述预设授权操作。
在本实施例的一个可选实现方式中,所述预设授权操作可包括以下操作中的一种或多种:发送通道开启指令、发送启动指令、发送触发指令等等。需要说明的是,在不同的应用场景下,授权操作具有不同的内容,因此,本领域技术人员可根据实际应用的需要以及应用场景的特点,对于所述预设授权操作内容进行设置,本申请对其不作具体限定。
在本实施例的一个可选实现方式中,当第二身份识别失败次数超过预设第二预设次数阈值时,就确认所述待识别对象识别失败,即认为所述待识别对象为非法对象,则触发第二预设报警操作。其中,与所述第一预设报警操作类似,所述第二预设报警操作也可包括以下操作中的一种或多种:声光报警、音频报警、视频报警、信息报警、邮件报警等等。其中,所述第二预设报警操作可与所述第一预设报警操作相同,也可以不同,本申请对其不作具体限定。
其中,所述第二预设次数阈值可与所述第一预设次数阈值相同,也可以不同,与所述第一预设次数阈值类似,所述第二预设次数阈值可根据实际应用的需要进行设置,比如可设置为两次。
下述为本申请装置实施例,可以用于执行本申请方法实施例。
图5示出根据本申请一实施方式的身份识别装置的结构框图,该装置可以通过软件、硬件或者两者的结合实现成为电子设备的部分或者全部,可实现为服务器也可实现为终端。如图5所示,所述身份识别装置包括:
第一识别模块501,被配置为获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
获取模块502,被配置为响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;
第二识别模块503,被配置为根据所述第二生物特征信息对于所述待识 别对象进行第二身份识别。
上文提及,随着数据技术的发展以及社会的进步,大众对于安防***的要求越来越高。目前安防***中的身份识别通常使用人脸识别、指纹识别或瞳孔识别等2D识别技术,但由于所述2D识别技术的误识率较高,因此远远不能满足大众对于安防***日益提高的要求。
考虑到上述问题,在该实施方式中,提出一种身份识别装置,该装置采用混合生物特征信息进行综合身份识别,即采用双重身份识别机制,该技术方案在不增加操作复杂度的情况下,能够有效提高身份识别的准确率,进而增强了安防***的安全性,提升了用户的使用体验。
在本实施例的一个可选实现方式中,所述第一生物特征信息包括以下特征信息中的一种或多种:脸部图像、瞳孔图像和指纹图像,其中,所述脸部图像、瞳孔图像和指纹图像均可为三维图像或二维图像,三维图像准确率高,但运算量大,二维图像运算量小但准确率低,本领域技术人员可根据实际应用的需要对于第一生物特征信息进行选择,本申请对其不作具体限定。
在本实施例的一个可选实现方式中,所述第二生物特征信息为声纹数据,所述声纹数据指的是用电声学仪器显示的携带言语信息的声波频谱。由于人在讲话时使用的发声器官:舌、牙齿、喉头、肺、鼻腔在尺寸和形态方面均存在一定的差异,即任何两个人的声纹图谱也都不尽相同,每个人的语音声学特征既有相对稳定性,又有变异性,因此,可利用声纹数据来实现身份识别。
在本实施例的一个可选实现方式中,所述第一生物特征信息的获取可采用摄像头、照相机等图像采集设备来完成,所述图像采集设备可以为移动电子设备上的图像采集设备,例如智能手机、智能平板电脑自带的摄像头等;同时所述图像采集设备也可以为固定电子设备上的图像采集设备,例如闸机头上的摄像头等。
其中,若所述身份识别装置实现为服务器,则所述第一生物特征信息可由终端的图像采集设备获取并发送至第一识别模块501;若所述身份识别装置实现为终端,则所述第一识别模块501可直接获取所述第一生物特征信息。在本实施例的一个可选实现方式中,终端或第一识别模块501在获取第一生物特征信息时,可在检测到待识别对象与终端之间的距离小于预设距离阈值 时启动获取所述第一生物特征信息。
在本实施例的一个可选实现方式中,在第一识别模块501根据所述第一生物特征信息对于所述待识别对象进行第一身份识别时,可采用特征匹配方法,具体地,所述第一识别模块501可被配置为:首先提取所述第一生物特征信息的特征数据,然后将其与预先存储的训练好的特征模型进行匹配,匹配成功的模型输出就对应于第一身份识别的识别结果。当然,在实际应用中,如果进行的是三维人脸识别,在有深度的情况下,则需要对三维人脸图像的X、Y、Z轴分别进行深度对比匹配,这样相对于三维活体识别的仅仅识别出来Z轴存在来说,三维人脸识别分别将在X、Y、Z轴对识别出来的人脸图像与预先存储的训练好的模型进行对别匹配,这样进一步大大提高了人脸识别的安全性与准确性。本领域技术人员还可以选择其它身份识别方法,以上仅为示例性说明,不能够被理解为是对本申请的限制。
在本实施例的一个可选实现方式中,与所述第一识别模块501类似,第二识别模块503在根据所述第二生物特征信息对于所述待识别对象进行第二身份识别时,也可采用特征匹配方法或其他身份识别方法,在此不再赘述。
在本实施例的一个可选实现方式中,如图6所示,所述获取模块502包括:
输出子模块601,被配置为响应于第一身份识别成功,输出第二生物特征提示信息;
获取子模块602,被配置为获取所述待识别对象的第二生物特征信息,其中,所述第二生物特征信息与所述第二生物特征提示信息相对应。
为了提高第二生物特征信息的规范性和普适性,在该实施方式中,通过输出子模块601输出第二生物特征提示信息以对于待识别对象进行引导使其输出利于身份识别的第二生物特征信息。具体地,当第一身份识别成功时,输出子模块601输出第二生物特征提示信息,其中,所述第二生物特征提示信息用于对于待识别对象进行引导;获取子模块602获取所述待识别对象的第二生物特征信息,其中,所述第二生物特征信息与所述第二生物特征提示信息相对应。
在本实施例的一个可选实现方式中,所述第二生物特征提示信息比如可以为文字性信息或者语音信息,使得待识别对象能够读出所述文字性信息或 者重复所述语音信息,进而获得第二生物特征信息。
其中,若所述身份识别装置实现为服务器,则所述第二生物特征提示信息可由终端的输出设备根据输出子模块601的指令输出,即所述输出子模块601可被配置为:响应于第一身份识别成功,向终端发送第二生物特征提示信息输出指令,其中,所述第二生物特征提示信息输出指令用于触发所述终端输出第二生物特征提示信息;若所述身份识别装置应用于终端,则所述输出子模块601可直接输出所述第二生物特征提示信息。
在本实施例的一个可选实现方式中,所述第二生物特征信息的获取可采用收声器、录音机等声音采集设备来完成。
其中,若所述身份识别装置应用于服务器,则所述第二生物特征信息可由终端的声音采集设备获取并发送至获取子模块602,即所述获取子模块602可被配置为:响应于第二生物特征提示信息的输出,向终端发送第二生物特征信息获取指令;接收所述终端发送的第二生物特征信息;若所述身份识别装置应用于终端,则在输出子模块601输出第二生物特征提示信息后所述获取子模块602可直接获取所述第二生物特征信息。
在本实施例的一个可选实现方式中,所述装置还包括当第一身份识别失败时重复进行第一身份识别的部分,即如图7所示,所述装置包括:
第一识别模块701,被配置为获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
第三识别模块702,被配置为响应于第一身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
获取模块703,被配置为响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;
第二识别模块704,被配置为根据所述第二生物特征信息对于所述待识别对象进行第二身份识别。
为了避免噪声、光线、设备污点或者其他意外事件的影响,提高身份识别的鲁棒性,在该实施方式中,若第一身份识别失败,则第三识别模块702再次获取所述待识别对象的第一生物特征信息,再次进行第一身份识别。但第一身份识别不能无限制地重复进行,在本实施例的一个可选实现方式中, 当第一身份识别失败次数超过预设第一预设次数阈值时,就确认所述待识别对象识别失败,即认为所述待识别对象为非法对象,则可设置第一触发模块,使其被配置为当第一身份识别失败次数超过预设第一预设次数阈值时,触发第一预设报警操作。其中,所述第一预设报警操作可包括以下操作中的一种或多种:声光报警、音频报警、视频报警、信息报警、邮件报警等等。比如,当发现某一待识别对象为非法对象时,第一触发模块可立即启动声光报警操作,现场播放报警音频开启光学设备进行报警,也可立即向管理员发送报警信息以促使其在第一时间对于非法对象进行处理。
其中,所述第一预设次数阈值可根据实际应用的需要进行设置,比如可设置为三次。
在本实施例的一个可选实现方式中,所述装置还包括根据第二身份识别结果执行相应操作的部分,即如图8所示,所述装置包括:
第一识别模块801,被配置为获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;
获取模块802,被配置为响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;
第二识别模块803,被配置为根据所述第二生物特征信息对于所述待识别对象进行第二身份识别;
第四识别模块804,被配置为响应于第二身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别,或者,重复获取所述待识别对象的第二生物特征信息,并根据所述第二生物特征信息对于所述待识别对象进行第二身份识别;
执行模块805,被配置为响应于第二身份识别成功,执行预设授权操作。
在该实施方式中,若第一身份识别成功第二身份识别失败,则暂时认为有可能是在获取生物特征信息的时候出现了影响事件,因此第四识别模块804可重复获取第一生物特征信息进行第一身份识别,第一身份识别成功后再重复获取第二生物特征信息进行第二身份识别,或者,为了节省计算量,节省计算时间,也可直接重复获取第二生物特征信息进行第二身份识别;若第一身份识别和第二身份识别均成功,则认为所述待识别对象为合法对象,则执 行模块805触发执行所述预设授权操作。
在本实施例的一个可选实现方式中,所述预设授权操作可包括以下操作中的一种或多种:发送通道开启指令、发送启动指令、发送触发指令等等。需要说明的是,在不同的应用场景下,授权操作具有不同的内容,因此,本领域技术人员可根据实际应用的需要以及应用场景的特点,对于所述预设授权操作内容进行设置,本申请对其不作具体限定。
在本实施例的一个可选实现方式中,当第二身份识别失败次数超过预设第二预设次数阈值时,就确认所述待识别对象识别失败,即认为所述待识别对象为非法对象,则可设置第二触发模块,使其被配置为触发第二预设报警操作。其中,与所述第一预设报警操作类似,所述第二预设报警操作也可包括以下操作中的一种或多种:声光报警、音频报警、视频报警、信息报警、邮件报警等等。其中,所述第二预设报警操作可与所述第一预设报警操作相同,也可以不同,本申请对其不作具体限定。
其中,所述第二预设次数阈值可与所述第一预设次数阈值相同,也可以不同,与所述第一预设次数阈值类似,所述第二预设次数阈值可根据实际应用的需要进行设置,比如可设置为两次。
本申请实施例还公开了一种电子设备,图9示出根据本申请一实施方式的电子设备的结构框图,如图9所示,所述电子设备900包括存储器901和处理器902;其中,
所述存储器901用于存储一条或多条计算机指令,其中,所述一条或多条计算机指令被所述处理器902执行以实现上述任一方法步骤。
图10适于用来实现根据本申请实施方式的身份识别方法的计算机***的结构示意图。
如图10所示,计算机***1000包括中央处理单元(CPU)1001,其可以根据存储在只读存储器(ROM)1002中的程序或者从存储部分1008加载到随机访问存储器(RAM)1003中的程序而执行上述实施方式中的各种处理。在RAM1003中,还存储有***1000操作所需的各种程序和数据。CPU1001、ROM1002以及RAM1003通过总线1004彼此相连。输入/输出(I/O)接口1005也连接至总线1004。
以下部件连接至I/O接口1005:包括键盘、鼠标等的输入部分1006;包 括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分1007;包括硬盘等的存储部分1008;以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分1009。通信部分1009经由诸如因特网的网络执行通信处理。驱动器1010也根据需要连接至I/O接口1005。可拆卸介质1011,诸如磁盘、光盘、磁光盘、半导体存储器等等,根据需要安装在驱动器1010上,以便于从其上读出的计算机程序根据需要被安装入存储部分1008。
特别地,根据本申请的实施方式,上文描述的方法可以被实现为计算机软件程序。例如,本申请的实施方式包括一种计算机程序产品,其包括有形地包含在及其可读介质上的计算机程序,所述计算机程序包含用于执行所述身份识别方法的程序代码。在这样的实施方式中,该计算机程序可以通过通信部分1009从网络上被下载和安装,和/或从可拆卸介质1011被安装。
附图中的流程图和框图,图示了按照本申请各种实施方式的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,路程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分,所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的***来实现,或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施方式中所涉及到的单元或模块可以通过软件的方式实现,也可以通过硬件的方式来实现。所描述的单元或模块也可以设置在处理器中,这些单元或模块的名称在某种情况下并不构成对该单元或模块本身的限定。
作为另一方面,本申请实施例还提供了一种计算机可读存储介质,该计算机可读存储介质可以是上述实施方式中所述装置中所包含的计算机可读存储介质;也可以是单独存在,未装配入设备中的计算机可读存储介质。计算机可读存储介质存储有一个或者一个以上程序,所述程序被一个或者一个以上的处理器用来执行描述于本申请实施例的方法。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解,本申请实施例中所涉及的发明范围,并不限于上述技术特征的特定组合而成的技术方案,同时也应涵盖在不脱离所述发明构思的情况下,由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请实施例中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
Claims (14)
- 一种身份识别方法,其特征在于,包括:获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;根据所述第二生物特征信息对于所述待识别对象进行第二身份识别;所述第一生物特征信息为三维脸部图像、三维瞳孔图像或三维指纹图像;和/或,所述第二生物特征信息为声纹数据。
- 根据权利要求1所述的方法,其特征在于,所述响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息,包括:响应于第一身份识别成功,输出第二生物特征提示信息;获取所述待识别对象的第二生物特征信息,其中,所述第二生物特征信息与所述第二生物特征提示信息相对应。
- 根据权利要求1或2所述的方法,其特征在于,所述获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别之后,还包括:响应于第一身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别。
- 根据权利要求3所述的方法,其特征在于,所述响应于第一身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别之后,还包括:当第一身份识别失败次数超过第一预设次数阈值时,触发第一预设报警操作。
- 根据权利要求1-4任一所述的方法,其特征在于,所述根据所述第二生物特征信息对于所述待识别对象进行第二身份识别之后,还包括:响应于第二身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别,或者,重复获取所述待识别对象的第二生物特征信息,并根据所述第二生物 特征信息对于所述待识别对象进行第二身份识别;响应于第二身份识别成功,执行预设授权操作。
- 根据权利要求5所述的方法,其特征在于,所述响应于第二身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别,或者,重复获取所述待识别对象的第二生物特征信息,并根据所述第二生物特征信息对于所述待识别对象进行第二身份识别之后,还包括:当第一身份识别失败次数超过第二预设次数阈值时,触发第二预设报警操作。
- 一种身份识别装置,其特征在于,包括:第一识别模块,被配置为获取待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别;获取模块,被配置为响应于第一身份识别成功,获取所述待识别对象的第二生物特征信息;第二识别模块,被配置为根据所述第二生物特征信息对于所述待识别对象进行第二身份识别;所述第一生物特征信息为三维脸部图像、三维瞳孔图像或三维指纹图像;和/或,所述第二生物特征信息为声纹数据。
- 根据权利要求7所述的装置,其特征在于,所述获取模块包括:输出子模块,被配置为响应于第一身份识别成功,输出第二生物特征提示信息;获取子模块,被配置为获取所述待识别对象的第二生物特征信息,其中,所述第二生物特征信息与所述第二生物特征提示信息相对应。
- 根据权利要求7或8所述的装置,其特征在于,还包括:第三识别模块,被配置为响应于第一身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别。
- 根据权利要求9所述的装置,其特征在于,还包括:第一触发模块,被配置为当第一身份识别失败次数超过第一预设次数阈值时,触发第一预设报警操作。
- 根据权利要求7-10任一所述的装置,其特征在于,还包括:第四识别模块,被配置为响应于第二身份识别失败,重复获取所述待识别对象的第一生物特征信息,并根据所述第一生物特征信息对于所述待识别对象进行第一身份识别,或者,重复获取所述待识别对象的第二生物特征信息,并根据所述第二生物特征信息对于所述待识别对象进行第二身份识别;执行模块,被配置为响应于第二身份识别成功,执行预设授权操作。
- 根据权利要求11所述的装置,其特征在于,还包括:第二触发模块,被配置为当第一身份识别失败次数超过第二预设次数阈值时,触发第二预设报警操作。
- 一种电子设备,其特征在于,包括存储器和处理器;其中,所述存储器用于存储一条或多条计算机指令,其中,所述一条或多条计算机指令被所述处理器执行以实现权利要求1-6任一项所述的方法步骤。
- 一种计算机可读存储介质,其上存储有计算机指令,其特征在于,该计算机指令被处理器执行时实现权利要求1-6任一项所述的方法步骤。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811075545.3A CN108920928A (zh) | 2018-09-14 | 2018-09-14 | 身份识别方法、装置、电子设备及计算机可读存储介质 |
CN201811075545.3 | 2018-09-14 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020051971A1 true WO2020051971A1 (zh) | 2020-03-19 |
Family
ID=64408234
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2018/110654 WO2020051971A1 (zh) | 2018-09-14 | 2018-10-17 | 身份识别方法、装置、电子设备及计算机可读存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108920928A (zh) |
WO (1) | WO2020051971A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113037757A (zh) * | 2021-03-11 | 2021-06-25 | 拉卡拉支付股份有限公司 | 异常数据判断方法、装置、电子设备、介质及程序产品 |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109711177A (zh) * | 2018-12-14 | 2019-05-03 | 国家电网有限公司 | 基于生物信息识别的数据安全管理方法及终端设备 |
CN110399434A (zh) * | 2019-07-25 | 2019-11-01 | 北京明略软件***有限公司 | 字段分类方法及装置、存储介质、电子装置 |
CN110808966A (zh) * | 2019-10-23 | 2020-02-18 | 天津华来科技有限公司 | 身份信息生成方法、装置及存储介质 |
CN111157813B (zh) * | 2019-12-31 | 2022-09-09 | Oppo广东移动通信有限公司 | 充电电流的确定方法及装置 |
CN111222485A (zh) * | 2020-01-15 | 2020-06-02 | 北京明略软件***有限公司 | 3d人脸识别方法、装置、电子设备和存储介质 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150347841A1 (en) * | 2014-05-30 | 2015-12-03 | Lockheed Martin Corporation | System and method for 3d iris recognition |
CN106295297A (zh) * | 2016-08-05 | 2017-01-04 | 联想(北京)有限公司 | 一种身份识别方法、电子设备以及穿戴设备 |
CN106599660A (zh) * | 2016-12-02 | 2017-04-26 | 宇龙计算机通信科技(深圳)有限公司 | 终端安全验证方法及装置 |
CN108052813A (zh) * | 2017-11-30 | 2018-05-18 | 广东欧珀移动通信有限公司 | 终端设备的解锁方法、装置及移动终端 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105827817A (zh) * | 2015-11-30 | 2016-08-03 | 维沃移动通信有限公司 | 报警方法及移动终端 |
CN207008704U (zh) * | 2017-06-27 | 2018-02-13 | 黑龙江省和为贵科技有限公司 | 司法自助服务装置及*** |
CN107633162B (zh) * | 2017-10-19 | 2020-09-15 | 深圳怡化电脑股份有限公司 | 一种身份认证方法、装置、***、设备及存储介质 |
CN108171032A (zh) * | 2017-12-01 | 2018-06-15 | 平安科技(深圳)有限公司 | 一种身份鉴定方法、电子装置及计算机可读存储介质 |
-
2018
- 2018-09-14 CN CN201811075545.3A patent/CN108920928A/zh active Pending
- 2018-10-17 WO PCT/CN2018/110654 patent/WO2020051971A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150347841A1 (en) * | 2014-05-30 | 2015-12-03 | Lockheed Martin Corporation | System and method for 3d iris recognition |
CN106295297A (zh) * | 2016-08-05 | 2017-01-04 | 联想(北京)有限公司 | 一种身份识别方法、电子设备以及穿戴设备 |
CN106599660A (zh) * | 2016-12-02 | 2017-04-26 | 宇龙计算机通信科技(深圳)有限公司 | 终端安全验证方法及装置 |
CN108052813A (zh) * | 2017-11-30 | 2018-05-18 | 广东欧珀移动通信有限公司 | 终端设备的解锁方法、装置及移动终端 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113037757A (zh) * | 2021-03-11 | 2021-06-25 | 拉卡拉支付股份有限公司 | 异常数据判断方法、装置、电子设备、介质及程序产品 |
Also Published As
Publication number | Publication date |
---|---|
CN108920928A (zh) | 2018-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020051971A1 (zh) | 身份识别方法、装置、电子设备及计算机可读存储介质 | |
US11797659B2 (en) | Authentication device, authentication system, and authentication method | |
US11663307B2 (en) | RtCaptcha: a real-time captcha based liveness detection system | |
CN109726624B (zh) | 身份认证方法、终端设备和计算机可读存储介质 | |
KR102210775B1 (ko) | 인적 상호 증명으로서 말하는 능력을 이용하는 기법 | |
US10586541B2 (en) | Communicating metadata that identifies a current speaker | |
US20190237076A1 (en) | Augmentation of key phrase user recognition | |
CN111033501B (zh) | 虚拟现实中对访问私有数据的安全授权 | |
US9979721B2 (en) | Method, server, client and system for verifying verification codes | |
US10270736B2 (en) | Account adding method, terminal, server, and computer storage medium | |
JP2011203992A (ja) | 情報処理装置、情報処理方法、およびプログラム | |
WO2019019256A1 (zh) | 电子装置、身份验证的方法、***及计算机可读存储介质 | |
WO2017166651A1 (zh) | 语音识别模型训练方法、说话人类型识别方法及装置 | |
WO2017181609A1 (zh) | 一种界面跳转管理的方法及装置 | |
JP7148737B2 (ja) | 生体(liveness)検出検証方法、生体検出検証システム、記録媒体、及び生体検出検証システムの訓練方法 | |
WO2023173686A1 (zh) | 检测方法、装置、电子设备及存储介质 | |
CN110910887A (zh) | 语音唤醒方法和装置 | |
CN109840406B (zh) | 活体验证方法、装置和计算机设备 | |
CN115171227B (zh) | 活体检测方法、装置、电子设备及存储介质 | |
WO2019150708A1 (ja) | 情報処理装置、情報処理システム、および情報処理方法、並びにプログラム | |
JP6571587B2 (ja) | 音声入力装置、その方法、及びプログラム | |
US20230325481A1 (en) | Method and System for Authentication of a Subject by a Trusted Contact | |
CN112836732B (zh) | 数据标注的校验方法、装置、电子设备及存储介质 | |
CN116524957A (zh) | 基于视频交互的认证方法、***以及相关装置 | |
WO2017219925A1 (zh) | 一种信息发送方法、装置及计算机存储介质 |
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: 18933078 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18933078 Country of ref document: EP Kind code of ref document: A1 |