Human-certificate verification method and device

Abstract

The invention provides a human-certificate verification method and device, and relates to the technical field of computer vision and biological recognition, and the method comprises the steps: continuously carrying out the image collection of a user, stopping the image collection until a physical card number in a target certificate of the user is obtained, and carrying out the verification of the physical card number. The image acquisition is to acquire a plurality of historical face images of a user in a moving process in a preset area; performing feature extraction on the plurality of historical face images to obtain a face feature queue; decoding the target certificate of the user to obtain an identity head portrait of the user; and finally, based on the physical card number, the face feature queue and the identity head portrait, obtaining a person-card verification result. According to the human and certificate verification method provided by the invention, the human and certificate consistency is comprehensively judged in combination with the physical card number, the face feature queue and the identity head portrait, so that efficient and accurate human and certificate verification is completed without deliberate cooperation of the user, and the user experience is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer vision and biometric technology, and particularly relates to a person and certificate verification method and device. BACKGROUND

[0002] At present, there are person and certificate comparison systems widely used in specific personnel identity verification systems, which provide services of verifying the same person and certificate in scenes such as train stations, enterprises and institutions, schools or scenic spots.

[0003] The existing person and certificate comparison system usually has a large read certificate delay in the process of person and certificate comparison, which leads to slow verification response, reduces the efficiency of person and certificate verification, and also needs more personnel to cooperate when collecting the user's face image. If the cooperation is not proper, the time spent will be prolonged, resulting in poor user experience. SUMMARY

[0004] The present application provides a person and certificate verification method and device to solve the technical problem of low person and certificate verification efficiency in the prior art, which realizes efficient person and certificate verification and improves user experience.

[0005] The present application provides a person and certificate verification method, comprising the following steps: Continuously collecting images of the user until the physical card number in the target certificate of the user is obtained, and stopping the image collection; the image collection is collecting a plurality of historical face images of the user in the movement process in a preset area; Extracting features from the plurality of historical face images to obtain a face feature queue; Decoding the target certificate of the user to obtain an identity portrait of the user; Obtaining a person and certificate verification result based on the physical card number, the face feature queue and the identity portrait.

[0006] According to the person and certificate verification method provided by the present application, the features of the plurality of historical face images are extracted to obtain a face feature queue, which comprises: Respectively extracting features from each historical face image to obtain corresponding historical face features; Determining the arrangement order of the historical face features based on the collection time corresponding to each historical face image; According to the arrangement order, the historical face features are sorted to obtain the face feature queue.

[0007] According to the person and certificate verification method provided by the present application, the arrangement order of the historical face features is determined based on the collection time corresponding to each historical face image, which comprises: arranging the each historical face image in order from late to early according to the collection time; using the arrangement order of the arranged each historical face image as the arrangement order of the historical face feature corresponding to the each historical face image.

[0008] According to the person certificate verification method provided by the application, the person certificate verification result is obtained based on the physical card number, the face feature queue and the identity portrait, and the method comprises the following steps: determining the target certificate as a valid certificate or an invalid certificate based on the physical card number; in the case that the target certificate is an invalid certificate, the person certificate verification result is not passed; in the case that the target certificate is a valid certificate, determining the person certificate verification result based on the comparison result of the historical face feature in the face feature queue and the face feature in the identity portrait.

[0009] According to the person certificate verification method provided by the application, the person certificate verification result is obtained based on the comparison result of the historical face feature in the face feature queue and the face feature in the identity portrait, and the method comprises the following steps: arranging the historical face feature in the face feature queue and the face feature in the identity portrait in order according to the arrangement order of the historical face feature in the face feature queue; in the case that any one of the historical face feature and the face feature in the identity portrait is compared successfully, the person certificate verification result is passed; in the case that all the historical face features and the face feature in the identity portrait are compared unsuccessfully, the person certificate verification result is not passed.

[0010] According to the person certificate verification method provided by the application, after the person certificate verification result is not passed, the method further comprises the following steps: collecting the current face image of the user; extracting the feature of the current face image to obtain the corresponding current face feature; determining the person certificate verification result based on the comparison result of the current face feature and the face feature in the identity portrait.

[0011] According to the person certificate verification method provided by the application, the person certificate verification result is obtained based on the comparison result of the current face feature and the face feature in the identity portrait, and the method comprises the following steps: in the case that the current face feature and the face feature in the identity portrait are compared successfully, the person certificate verification result is passed; In a case where the current face feature fails to be compared with the face feature in the identity portrait, the person-certificate verification result is not passed.

[0012] The present application also provides a person-certificate verification device, comprising the following modules: The acquisition module is configured to continuously acquire images of the user until a physical card number in a target certificate of the user is acquired, and stop the image acquisition; the image acquisition is to acquire a plurality of historical face images of the user during movement in a preset area; The feature module is configured to extract features from the plurality of historical face images to obtain a face feature queue; The certificate reading module is configured to decode the target certificate of the user to obtain an identity portrait of the user; The verification module is configured to obtain a person-certificate verification result based on the physical card number, the face feature queue, and the identity portrait.

[0013] The present application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the person-certificate verification method according to any one of the above when executing the computer program.

[0014] The present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the person-certificate verification method according to any one of the above.

[0015] The present application also provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the person-certificate verification method according to any one of the above.

[0016] The application provides a person certificate verification method, which comprises the following steps: continuously collecting images of a user until a physical card number in a target certificate of the user is obtained, and stopping the image collection; the image collection is collecting a plurality of historical face images of the user in a moving process in a preset area, so that the face images are collected and cached in advance without the user's awareness, the man-machine interaction time during subsequent person certificate verification is shortened, and the system resources are all used for reading other information of the target certificate when the face images are stopped from being collected after the physical card number in the target certificate of the user is obtained, so that the subsequent certificate reading time is further shortened, the efficiency is improved through the time-sharing processing mode, and the user experience is improved; then feature extraction is performed on the plurality of historical face images to obtain a face feature queue, so that the subsequent person certificate verification speed is improved through the pre-performed feature extraction and the cached feature queue; then the target certificate of the user is decoded to obtain an identity portrait of the user; finally, a person certificate verification result is obtained based on the physical card number, the face feature queue and the identity portrait, so that the person certificate consistency is comprehensively judged by combining the physical card number (certificate anti-forgery verification), the face feature queue (dynamic behavior verification) and the identity portrait (static comparison), efficient and accurate person certificate verification is realized without the user's deliberate cooperation, and the user experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 is a flowchart of the person certificate verification method provided by the application.

[0019] Figure 2 is a schematic view of a person certificate verification gate channel provided by the application.

[0020] Figure 3 is a structural schematic view of a person certificate verification device provided by the application.

[0021] Figure 4 is a structural schematic view of an electronic device provided by the application. DETAILED DESCRIPTION

[0022] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in conjunction with the drawings in the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort belong to the protection scope of the present application.

[0023] The technical solutions of the present application will be described below in conjunction with the drawings in the present application. Figures 1 to 4 A person certificate verification method and device are described.

[0024] Figure 1 A flowchart of a person certificate verification method provided by the present application is shown in FIG. 1, which comprises the following steps. Figure 1 Step 101: continuously collecting images of a user until a physical card number in a target certificate of the user is obtained, and stopping the image collection; the image collection is collecting a plurality of historical face images of the user in a moving process in a preset area.

[0025] Specifically, the person certificate comparison system has been widely applied to various scenes, such as train stations, enterprises and institutions, schools or scenic spots, etc., and can provide a service of verifying the same person and certificate.

[0026] Taking any high-speed rail station as an example, Figure 2 A person certificate verification gate channel provided by the present application is shown in FIG. 2, which comprises two completely same gate host devices A1 and A2. Figure 2 The processing control unit 1 is a camera module responsible for frame taking; the processing control unit 2 is a face feature extraction module; the processing control unit 3 is an identity card reading module; the processing control unit 4 is a portrait feature comparison module; the processing control unit 5 is an interface display module; and the processing control unit 6 is a channel door control module. B1 and B2 are doors on the gate, which are controlled to be opened by the channel door control module after the person certificate comparison passes. C1 and C2 are areas where the face can be recognized, and when the person walks to the area between C2 and A1 / A2, the face cannot be recognized. The area between D1 and D2 is a pedestrian channel, and the door will only be opened when the person certificate comparison is performed in the channel.

[0027] In the prior art, the person certificate verification needs to wait for the user to approach the device, read the identity card information first, and then perform the face collection, feature value extraction and person certificate comparison in a specified timeout time (for example, within 15 seconds) in a loop. After the comparison passes, the comparison is stopped, and the door opening action is performed. After the comparison timeout, the comparison is stopped, and a failure is prompted. There are the following problems in this process: ​1) From the brush certificate to the display of the person certificate comparison interface is slow. According to statistics, the polling interval of reading the certificate (reading the physical card number of the identity card) is 200ms, the reading certificate time is 900ms; the decoding time of the identity card portrait is 185ms, so the longest waiting time of the user is 200+900+185=1285ms.

[0028] 2) The user needs to cooperate with the face recognition and adjust the posture for many times. In actual application, between D1 and E1 or between D2 and E2, it is the area where the camera can collect a high-quality face image, that is, the area where the person certificate comparison is most likely to pass. However, people are used to walking in the middle channel, which affects the efficiency of the person certificate comparison. When the user brushes the certificate, the person may have walked to the area between C2 and A1 / A2, the face is not in the camera picture; or the person is about to walk to the position of C2, the face angle is relatively biased. In addition, users with a height of more than 1.8 meters need to retreat and lower their heads to cooperate, and users with an angle bias need to move left and right to cooperate. According to statistics, the average time of the person certificate comparison passing is 5000ms.

[0029] Therefore, a user needs 1285ms+5000ms=6285ms from brushing the certificate to the person certificate comparison passing, which is low in efficiency, gives a strong sluggish feeling, and needs the user to cooperate well to pass the channel quickly, resulting in poor user experience.

[0030] Therefore, the embodiment of the present application continuously collects the image of the user in advance until the physical card number in the target certificate of the user is obtained, and stops the image collection, wherein the image collection is to collect multiple historical face images of the user in the moving process in the preset area, and the target certificate can be an identity card, a passport or a social security card, etc. which represents a unique identity.

[0031] Taking the above high-speed rail station as an example, the target identity certificate is the user's identity card. When the user enters the preset area (the area between C1 and C2), the camera can start to continuously collect the face image of the user.

[0032] For example, the user walks from far to near to C1 line, and starts to brush the identity card at A1 or A2 gate host device from C1, so when the user moves in the area between C1 and C2, the camera module starts to continuously collect multiple historical face images of the user in this period of time (for example, it can collect a predetermined number of historical face images according to a predetermined time interval, such as 5 or 8, or it can continuously collect multiple frames of images in a preset time period), until the user starts to brush the identity card, and the device reads the physical card number in the identity card (which takes about 5ms), then stops collecting the face image, so as to use all system resources to read other information of the target certificate, avoid excessive collection of face images and occupation of system resources, thereby further shortening the reading certificate time through time-sharing processing.

[0033] The embodiment of the present application shortens the subsequent person-certificate verification time by collecting multiple historical face images in advance during the movement of the user in the preset area, realizes time saving by space, collects the face image in advance without the user's perception, improves the efficiency, and improves the user experience.

[0034] Step 102, feature extraction is performed on the multiple historical face images to obtain a face feature queue.

[0035] Specifically, after collecting the multiple historical face images of the user during the movement in the preset area, the face feature extraction can be performed synchronously by the processing control unit 2 to obtain multiple historical face features, and the multiple historical face features are arranged in time sequence to obtain a face feature queue.

[0036] Step 103, decoding the target certificate of the user to obtain the identity portrait of the user.

[0037] Specifically, when the physical card number in the target certificate (for example, an ID card) provided by the user is read, the face image collection is stopped first, and then the reading and decoding of other information of the ID card are performed, so that the system resources are all used to obtain other information of the ID card, such as reading other personal information (such as birth date, place of origin or address, etc.) in the ID card, and decoding the ID card portrait, improving the speed of obtaining the ID card portrait, and providing a data basis for subsequent person-certificate verification.

[0038] Step 104, obtaining a person-certificate verification result based on the physical card number, the face feature queue, and the identity portrait.

[0039] Specifically, first, the physical card number of the target certificate (for example, an ID card) can be used for anti-fake verification, such as verifying whether the ID card is valid, to reduce the risk of certificate forgery; then the feature extraction (such as using a convolutional neural network model) is performed on the decoded ID card portrait to obtain the face feature in the ID card portrait, and then the face feature in the ID card portrait is compared with the historical face features in the face feature queue, and after the feature comparison is successful, it means that the person-certificate verification is passed, and the gate is opened. At the same time, the cached historical face features are cleared to avoid unnecessary comparison when the person who swipes the certificate and the person who enters the channel are different, which wastes time.

[0040] In actual testing, the decoding of the ID photo takes 185 ms, and the feature comparison takes 110 ms, so the total time from the user swiping the ID card is only 5+200+900+185+110=1400 ms, which is 4885 ms (nearly 5 seconds) less than the 6285 ms required by the prior art, significantly reducing the user waiting time and improving the user experience.

[0041] The embodiment of the present application performs preliminary certificate anti-counterfeiting verification through the physical card number, and performs identity verification by comparing the historical face features in the pre-cached face feature queue with the face features in the ID photo, which not only improves the accuracy and reliability of the verification result, but also shortens the verification time, so that the user can complete the person-certificate verification naturally without deliberately staying, and the user experience is improved.

[0042] The person-certificate verification method provided by the present application acquires the physical card number in the target certificate of the user by continuously collecting images of the user until the physical card number is acquired, and stops image collection, so that multiple historical face images of the user during movement in a preset area are collected, thereby collecting and caching face images in advance without the user's awareness, shortening the human-computer interaction time during subsequent person-certificate verification, and stopping the collection of face images when the physical card number in the target certificate of the user is acquired, so that all system resources are used to read other information of the target certificate, further shortening the subsequent certificate reading time, improving the efficiency through asynchronous processing, and improving the user experience; then feature extraction is performed on the multiple historical face images to obtain a face feature queue, so that the speed of subsequent person-certificate verification is improved through pre-extracted features and cached feature queues; then the target certificate of the user is decoded to obtain an ID photo of the user; finally, based on the physical card number, the face feature queue, and the ID photo, a person-certificate verification result is obtained, so that the consistency of the person and the certificate is comprehensively determined by combining the physical card number (certificate anti-counterfeiting verification), the face feature queue (dynamic behavior verification), and the ID photo (static comparison), efficient and accurate person-certificate verification is achieved without the user's deliberate cooperation, and the user experience is improved.

[0043] Further, the feature extraction on the multiple historical face images to obtain a face feature queue comprises: respectively extracting features from each historical face image to obtain corresponding historical face features; determining the arrangement order of the historical face features based on the collection time corresponding to each historical face image; sorting the historical face features according to the arrangement order to obtain the face feature queue.

[0044] Further, the arrangement order of the historical face features is determined based on the collection time corresponding to each historical face image, including: arranging the historical face images in order from late to early according to the collection time; arranging the historical face images in order from late to early according to the collection time;

[0045] Specifically, first, the features of each historical face image are extracted independently (for example, the same convolutional neural network model as in step 104 is used for feature extraction), and then the arrangement order of the historical face features is determined based on the collection time corresponding to each historical face image.

[0046] Since the user is approaching the brush certificate device from far to near in the preset area, the closer to the brush certificate point, the better the face angle (such as higher probability of frontal face), and the camera module will gradually collect higher quality face images, therefore, the historical face features are arranged in order from late to early according to the collection time, to ensure that the latest image is preferentially involved in comparison, thereby improving the one-time comparison success probability in the subsequent person-certificate comparison process, reducing the number of repeated comparisons, shortening the comparison time, and further improving the person-certificate verification efficiency.

[0047] Further, the person-certificate verification result is obtained based on the physical card number, the face feature queue, and the identity portrait, including: determining that the target certificate is a valid certificate or an invalid certificate based on the physical card number; in the case that the target certificate is an invalid certificate, the person-certificate verification result is not passed; in the case that the target certificate is a valid certificate, determining the person-certificate verification result based on the comparison result of the historical face features in the face feature queue and the face features in the identity portrait.

[0048] Specifically, after reading all the information of the identity card, the person-certificate comparison interface is displayed immediately, without decoding the identity portrait, thereby reducing the response delay and improving the user experience.

[0049] Then, based on the physical card number, it is determined whether the target certificate (for example, an identity card) provided by the user is a valid certificate according to the citizen identity information record in the system, thereby verifying the authenticity of the certificate, in the case that the target certificate is an invalid certificate, the person-certificate verification result is not passed; in the case that the target certificate is a valid certificate, the face features in the identity portrait are compared with the historical face features in the face feature queue in turn for secondary verification.

[0050] The embodiment of the application provides a double verification mechanism, which firstly verifies whether a certificate is valid, and then performs person-certificate verification, thereby improving the reliability and accuracy of a verification result.

[0051] Further, the person-certificate verification result is determined based on a comparison result of the historical face features in the face feature queue and the face feature in the identity portrait. The historical face features are compared with the face feature in the identity portrait in sequence according to the arrangement order of the historical face features in the face feature queue. In a case where any one of the historical face features is successfully compared with the face feature in the identity portrait, the person-certificate verification result is passed. In a case where all the historical face features fail to be compared with the face feature in the identity portrait, the person-certificate verification result is not passed.

[0052] Specifically, in a case where the identity portrait is a real image, the historical face features in the face feature queue are further compared with the face feature in the identity portrait one by one.

[0053] The historical face features are compared with the face feature in the identity portrait in sequence according to the arrangement order of the historical face features in the face feature queue, a comparison result is obtained, and then it is judged whether the person-certificate verification is passed.

[0054] Taking a high-speed rail station gate as an example, the following operations can be performed: A 10-millisecond timer is started, and in a timer processing function: (1) decode the identity card portrait (185ms) (2) traverse the historical face features in the cached face feature queue, compare the historical face features with the face feature in the identity portrait in sequence according to the arrangement order of the historical face features, in a case where any one of the identity portraits is successfully compared, the person-certificate verification result is passed, or in a case where all the identity portraits fail to be compared, the person-certificate verification result is not passed. According to statistics, in a case where the identity card is real, 99% of the cases are passed by the first comparison, and only 110ms is consumed.

[0055] (3) clear the cached face feature value, so as to avoid unnecessary comparison and time waste when the person who swipes the card and the person who walks into the channel are different.

[0056] (4) after the person-certificate verification is passed, hide the person-certificate comparison interface, open the glass door, and the user passes the gate.

[0057] The embodiment of the present application arranges the order of historical face features according to the principle of giving priority to the latest image to participate in comparison, so that when the feature comparison is performed in turn according to the arrangement order, the probability of passing the first comparison is improved, the number of repeated comparisons is reduced, the user waiting time is reduced, the face and certificate verification is quickly completed, and the probability of passing the comparison is improved by the way of traversing all historical face features to perform feature comparison, so that the reliability is improved, the user experience is improved, and the algorithm misjudgment is avoided.

[0058] Further, after the face and certificate verification result is not passed, the method further comprises: collecting a current face image of the user; extracting features from the current face image to obtain corresponding current face features; determining the face and certificate verification result based on the comparison result of the current face features and the face features in the identity portrait.

[0059] Further, the determination of the face and certificate verification result based on the comparison result of the current face features and the face features in the identity portrait comprises: in the case that the current face features and the face features in the identity portrait are successfully compared, the face and certificate verification result is passed; in the case that the current face features and the face features in the identity portrait fail to be compared, the face and certificate verification result is not passed.

[0060] Specifically, the embodiment of the present application also provides a redundant design for improving fault tolerance, in the case that the target certificate is a valid certificate, if the face and certificate verification of the user is not passed, the current face image of the user can be collected in real time, then the current face image is extracted to obtain corresponding current face features, and finally the face and certificate verification result is determined based on the comparison result of the current face features and the face features in the identity portrait.

[0061] For example, the user walks with his head down, resulting in that the quality of the historical face images collected by the camera is poor, and the face cannot be accurately recognized, so that all historical face features and the face features in the identity portrait fail to be compared, the user can still take a new photo in front of the camera, and the face features are compared, in the case that the comparison is successful, the face and certificate verification result is passed, and the user can still smoothly pass the gate machine, and if the comparison fails, the face and certificate verification result is not passed.

[0062] Taking the high-speed rail station gate machine as an example, in actual operation, a 15-second comparison timeout timer can be started, the current face image of the user is collected in real time from the camera, the current face features are extracted, and the current face features are compared with the face features of the extracted identity portrait.

[0063] If the person-certificate comparison is successful within 15 seconds, the comparison is stopped immediately, the person-certificate comparison interface is hidden, the glass door is opened, and the user passes the gate machine.

[0064] If the person-certificate comparison fails within 15 seconds, the current face image of the user is continuously collected, the current face features are extracted, and the person-certificate comparison is performed.

[0065] If the person-certificate comparison is still unsuccessful after timeout, after the timeout is prompted, the person-certificate comparison interface is hidden, and the user needs to go to other channels or manual windows for verification, so as to avoid long waiting of subsequent users and blockage of channels.

[0066] The embodiment of the application performs real-time face collection and re-performs face feature comparison in the extreme case that the user still fails to verify using a valid certificate, avoids misjudgment of the person-certificate verification result, ensures the verification coverage, improves the reliability of the person-certificate verification result, and thus improves the user experience.

[0067] A person-certificate verification device provided by the application is described below, and the person-certificate verification device described below can be mutually referred to the person-certificate verification method described above.

[0068] Based on any of the above embodiments, Figure 3 is a structural schematic diagram of a person-certificate verification device provided by the application, as Figure 3 shown. The embodiment of the application provides a person-certificate verification device, which comprises an acquisition module 301, a feature module 302, a certificate reading module 303, and a verification module 304, wherein: The acquisition module 301 is used for continuously collecting images of a user until a physical card number in a target certificate of the user is obtained, and the image collection is stopped; the image collection is to collect a plurality of historical face images of the user in a moving process in a preset area; the feature module 302 is used for extracting features from the plurality of historical face images to obtain a face feature queue; the certificate reading module 303 is used for decoding the target certificate of the user to obtain an identity portrait of the user; and the verification module 304 is used for obtaining a person-certificate verification result based on the physical card number, the face feature queue, and the identity portrait.

[0069] The application provides a human certificate verification device, which continuously collects images of a user until a physical card number in a target certificate of the user is acquired, stops image collection, collects a plurality of historical human face images of the user in the process of moving in a preset area, so that the human face images are collected and cached in advance without the user's awareness, the human-computer interaction time in subsequent human certificate verification is shortened, and the system resources are all used for reading other information of the target certificate when the physical card number in the target certificate of the user is acquired, so that the subsequent certificate reading time is further shortened, the efficiency is improved through the asynchronous processing mode, and the user experience is improved; then feature extraction is performed on the plurality of historical human face images to obtain a human face feature queue, so that the subsequent human certificate verification speed is improved through the pre-performed feature extraction and the cached feature queue; then the target certificate of the user is decoded to obtain an identity portrait of the user; finally, a human certificate verification result is obtained based on the physical card number, the human face feature queue and the identity portrait, so that the human certificate consistency is comprehensively judged by combining the physical card number (certificate anti-forgery verification), the human face feature queue (dynamic behavior verification) and the identity portrait (static comparison), efficient and accurate human certificate verification is completed without the user's deliberate cooperation, and the user experience is improved.

[0070] Figure 4 An example of a schematic diagram of a physical structure of an electronic device is shown in Figure 4 The electronic device can include a processor 410, a communications interface 420, a memory 430 and a communications bus 440, wherein the processor 410, the communications interface 420 and the memory 430 can communicate with each other through the communications bus 440. The processor 410 can call logical instructions in the memory 430 to execute a human certificate verification method, which includes the following steps. Continuously collecting images of a user until a physical card number in a target certificate of the user is acquired, stopping the image collection; the image collection is to collect a plurality of historical human face images of the user in the process of moving in a preset area; Feature extraction is performed on the plurality of historical human face images to obtain a human face feature queue; The target certificate of the user is decoded to obtain an identity portrait of the user; A human certificate verification result is obtained based on the physical card number, the human face feature queue and the identity portrait.

[0071] Further, the logic instructions in the memory 430 described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0072] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program can be executed by a processor to enable a computer to execute the person-identity verification method provided by the above-mentioned methods, and the method comprises: continuously performing image acquisition on the user until a physical card number in a target identity document of the user is acquired, and stopping the image acquisition; the image acquisition is to acquire a plurality of historical face images of the user in a movement process in a preset area; performing feature extraction on the plurality of historical face images to obtain a face feature queue; decoding the target identity document of the user to obtain an identity portrait of the user; obtaining a person-identity verification result based on the physical card number, the face feature queue and the identity portrait.

[0073] In another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the person-identity verification method provided by the above-mentioned methods, and the method comprises: continuously performing image acquisition on the user until a physical card number in a target identity document of the user is acquired, and stopping the image acquisition; the image acquisition is to acquire a plurality of historical face images of the user in a movement process in a preset area; performing feature extraction on the plurality of historical face images to obtain a face feature queue; decoding the target identity document of the user to obtain an identity portrait of the user; obtaining a person-identity verification result based on the physical card number, the face feature queue and the identity portrait.

[0074] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0075] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and necessary universal hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in the embodiments or some parts of the embodiments.

[0076] It should be noted that in this document, the terms "comprise", "comprise", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles, or devices including a series of elements not only include those elements, but also include other elements not explicitly listed, or include elements inherent to such processes, methods, articles, or devices. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, article, or device that includes the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to the order of performing the functions as shown or discussed, but can also include performing the functions in a substantially simultaneous manner or in reverse order, for example, the described method can be performed in an order different from the described order, and various steps can also be added, omitted, or combined. In addition, the features described with reference to some examples can be combined in other examples.

[0077] In addition, it should be noted that the terms "target", "first", "second", etc. in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second" are usually a class, and do not limit the number of objects, for example, the first object can be one or more.

[0078] The "determining B based on A" in the embodiments of the present application means that A is considered as a factor when determining B. It is not limited to "determining B based on A only", but also includes "determining B based on A and C", "determining B based on A, C and E", "determining C based on A, and determining B based on C further", and the like. In addition, it can also include A as a condition for determining B, for example, "when A meets the first condition, determining B using the first method"; for example, "when A meets the second condition, determining B"; for example, "when A meets the third condition, determining B based on the first parameter"; and the like. Of course, A can also be a condition for determining B as a factor, for example, "when A meets the first condition, determining C using the first method, and determining B further based on C"; and the like.

[0079] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A human identity verification method, characterized in that, The method comprises the following steps: continuously capturing images of the user until a physical card number in a target certificate of the user is obtained, and stopping the image capturing; the image capturing is capturing a plurality of historical face images of the user during movement in a preset area; extracting features from the plurality of historical face images to obtain a face feature queue; decoding the target certificate of the user to obtain an identity portrait of the user; based on the physical card number, the face feature queue and the identity portrait, obtaining a person-certificate verification result.

2. The method according to claim 1, wherein, The method comprises the following steps: extracting features from each historical face image to obtain corresponding historical face features; determining the arrangement order of the historical face features based on the capture time corresponding to each historical face image; arranging the historical face features according to the arrangement order to obtain the face feature queue.

3. The method according to claim 2, wherein, The method comprises the following steps: arranging each historical face image in the order from late to early according to the capture time; arranging the historical face features corresponding to each historical face image in the order of the arranged historical face images.

4. The method of claim 1, wherein, The method comprises the following steps: based on the physical card number, determining whether the target certificate is a valid certificate or an invalid certificate; if the target certificate is an invalid certificate, the person-certificate verification result is failed; if the target certificate is a valid certificate, determining the person-certificate verification result based on the comparison result of the historical face features in the face feature queue and the face features in the identity portrait.

5. The method of claim 4, wherein, The method comprises the following steps: arranging the historical face features in the face feature queue in the order and comparing the historical face features with the face features in the identity portrait in the order; if any of the historical face features is successfully compared with the face features in the identity portrait, the person-certificate verification result is passed; if all the historical face features fail to be compared with the face features in the identity portrait, the person-certificate verification result is failed.

6. The method of claim 5, wherein, After the person-certificate verification result is failed, the method further comprises the following steps: capturing a current face image of the user; extracting features from the current face image to obtain corresponding current face features; determining the person-certificate verification result based on the comparison result of the current face features and the face features in the identity portrait.

7. The method of claim 6, wherein, The method comprises the following steps: if the current face features are successfully compared with the face features in the identity portrait, the person-certificate verification result is passed; In a case where the current face feature fails to be compared with the face feature in the identity portrait, the person-certificate verification result is not passed.

8. A person authentication device, characterized by comprising: Comprise: The acquisition module is used for continuously collecting images of the user until a physical card number in a target certificate of the user is acquired, and the image collection is stopped; The image collection is to collect a plurality of historical face images of the user during movement in a preset area; The feature module is used for extracting features of the plurality of historical face images to obtain a face feature queue; The certificate reading module is used for decoding the target certificate of the user to obtain an identity portrait of the user; The verification module is used for obtaining a person-certificate verification result based on the physical card number, the face feature queue, and the identity portrait.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, The processor executes the computer program to realize the person-certificate verification method in any one of claims 1 to 7. 10.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the person-certificate verification method in any one of claims 1 to 7.

Images