Examinee identity verification method, device and system based on face recognition technology

Abstract

The invention discloses an examinee identity verification method, equipment and system based on a face recognition technology, and relates to the technical field of image processing. The method comprises the following steps: acquiring a plurality of real-time face images of a to-be-detected examinee under a plurality of preset light source intensities in a plurality of preset light source directions; performing region division on each real-time face image based on the reference face image to obtain a plurality of face detection regions in each real-time face image; for each face detection area, the following steps are respectively executed: according to the gray value of each pixel point in the face detection area of each real-time face image, the illumination consistency of the face detection area is determined, and the illumination consistency is used for representing the consistency degree of illumination influence on each pixel point in the face detection area; determining the reliability probability of the to-be-detected examinee according to the illumination consistency of each face detection area; and when the reliability probability of the to-be-detected examinee is greater than a preset reliability threshold, determining that the identity verification of the to-be-detected examinee is successful.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a test taker identity verification method, device and system based on face recognition technology. Background Art

[0002] At present, face recognition technology has been widely used in the examination security system. The identity verification of examinees based on face recognition technology is to compare the face image on the examinee's admission ticket with the face image obtained by the face recognition device to determine whether the examinee is the examinee himself.

[0003] The existing method uses multi-light source face recognition technology based on active near-infrared light. By emitting infrared light of different angles and intensities, multiple face images under different lighting directions and conditions are obtained. The best face image is selected from the multiple face images and compared with the face image on the candidate's admission ticket to determine whether the candidate is the real person.

[0004] However, since different parts of the face are affected by light to different degrees, some areas of the face image are already exposed, while some areas are not illuminated enough. The overall quality of the face image obtained by the face recognition device is not high, resulting in low accuracy of the candidate's identity verification. Summary of the invention

[0005] The embodiments of the present invention provide a method, device and system for candidate identity authentication based on face recognition technology, which can improve the accuracy of candidate identity authentication.

[0006] A first aspect of an embodiment of the present invention provides a method for verifying the identity of a candidate based on face recognition technology, comprising:

[0007] Acquire multiple real-time facial images of the examinee to be tested under multiple preset light source directions and multiple preset light source intensities;

[0008] Based on the reference facial image, each real-time facial image is divided into regions to obtain multiple facial detection regions in each real-time facial image. The reference facial image is used to represent the correct facial image for the identity verification of the examinee.

[0009] For each face detection area, respectively perform: determining the illumination consistency of the face detection area according to the grayscale value of each pixel in the face detection area of ​​each real-time face image, where the illumination consistency is used to characterize the consistency degree of illumination influence on each pixel in the face detection area;

[0010] Determine the reliability probability of the candidate to be tested based on the consistency of illumination in each face detection area;

[0011] When the reliability probability of the candidate to be tested is greater than a preset reliability threshold, it is determined that the identity authentication of the candidate to be tested is successful.

[0012] According to a second aspect of an embodiment of the present invention, there is provided a candidate identity verification device based on face recognition technology, the device comprising: a memory and a program or instruction stored in the memory and executable on a processor, wherein when the program or instruction is executed by the processor, the candidate identity verification method based on face recognition technology as provided in any one of the above-mentioned embodiments of the present application is implemented.

[0013] A third aspect of the embodiments of the present invention provides a candidate identity verification system based on face recognition technology, including:

[0014] An image acquisition module is used to acquire multiple real-time facial images of the examinee under multiple preset light source directions and multiple preset light source intensities;

[0015] A region division module is used to divide each real-time facial image into regions based on a reference facial image to obtain multiple facial detection regions in each real-time facial image. The reference facial image is used to represent the correct facial image for the identity verification of the examinee.

[0016] The area calculation module is used to respectively perform, for each face detection area: determining the illumination consistency of the face detection area according to the grayscale value of each pixel point in the face detection area of ​​each real-time face image, where the illumination consistency is used to characterize the consistency degree of each pixel point in the face detection area affected by illumination;

[0017] A probability calculation module, used to determine the reliability probability of the candidate to be tested according to the consistency of illumination in each face detection area;

[0018] The identity authentication module is used to determine that the identity authentication of the candidate to be detected is successful when the reliability probability of the candidate to be detected is greater than a preset reliability threshold.

[0019] In the examinee identity verification method based on face recognition technology provided by an embodiment of the present invention, based on the reference face image, the real-time face image is divided into regions to obtain multiple face detection regions. Then, for each face detection region, the illumination consistency of the face detection region is determined according to the grayscale value of each pixel in the face detection region of each real-time face image, and the illumination consistency is used to characterize the consistency degree of the influence of illumination on each pixel in the face detection region. Finally, the identity of the examinee to be detected is verified according to the illumination consistency of each face detection region. In this way, the present invention divides the real-time face image into multiple face detection regions based on the reference face image, and evaluates the influence of illumination on the pixels in each face detection region, so as to accurately determine whether the identity verification of the examinee to be detected is successful. It can avoid the problem of low accuracy caused by direct judgment from the overall face image, and improve the accuracy of the examinee's identity verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A schematic diagram of a flow chart of a first method for identity verification of examinees based on face recognition technology provided by an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a flow chart of a second method for identity verification of examinees based on face recognition technology provided by an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of the results of a candidate identity verification system based on face recognition technology provided by an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of the results of a candidate identity verification device based on face recognition technology provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following, in combination with the accompanying drawings and preferred embodiments, describes in detail the specific implementation methods, structures, features and effects of a candidate identity verification method, device and system based on face recognition technology proposed by the present invention. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0026] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0027] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of laws and regulations.

[0028] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present invention, but it does not mean that the applicant has or will necessarily use the solution.

[0029] In the existing method, multi-light source face recognition technology based on active near-infrared light is used. By emitting infrared light of different angles and intensities, multiple face images with different lighting directions and under different lighting conditions are obtained. The best face image is selected from the multiple face images and compared with the face image on the candidate's admission ticket to determine whether the candidate is the person himself. However, the overall quality of the face images obtained by the face recognition device is not high, resulting in low accuracy of the candidate's identity verification.

[0030] The object of the present invention is to provide a candidate identity verification method, device and system based on face recognition technology. In the candidate identity verification method based on face recognition technology provided by the embodiment of the present invention, based on the reference face image, the real-time face image is divided into regions to obtain multiple face detection regions. Then, for each face detection region, the illumination consistency of the face detection region is determined according to the grayscale value of each pixel in the face detection region of each real-time face image, and the illumination consistency is used to characterize the consistency degree of each pixel in the face detection region affected by illumination. Finally, according to the illumination consistency of each face detection region, the identity of the candidate to be detected is verified. In this way, the present invention divides the real-time face image into multiple face detection regions based on the reference face image, and evaluates the degree of influence of illumination on the pixels in each face detection region, so as to accurately determine whether the identity verification of the candidate to be detected is successful. It can avoid the problem of low accuracy caused by direct judgment from the overall face image, and improve the accuracy of the candidate identity verification.

[0031] The following is a specific implementation of a candidate identity verification method, device and system based on face recognition technology provided by an embodiment of the present invention.

[0032] The following first introduces a candidate identity authentication method based on face recognition technology provided by an embodiment of the present invention.

[0033] Figure 1 A flow chart of a candidate identity authentication method based on face recognition technology is provided. The candidate identity authentication method based on face recognition technology can be applied to a server. The candidate identity authentication method based on face recognition technology can include the following S101 to S105.

[0034] S101, obtaining a plurality of real-time facial images of the examinee to be tested under a plurality of preset light source directions and a plurality of preset light source intensities;

[0035] In this embodiment, the preset light source direction is used to represent the preset light source direction when capturing the facial image. For example, the preset light source direction may include the front, side, and top directions.

[0036] The preset light source intensity is used to represent the preset light intensity when capturing the facial image. For example, the preset light source intensity may include a high-level light source intensity, a medium-level light source intensity, and a low-level light source intensity.

[0037] As an example, the server uses a facial recognition device with adjustable light source direction and adjustable light source intensity to continuously or sequentially capture real-time facial images of the examinee to be tested under different combinations of light source directions and light source intensities, and annotates each real-time facial image of the examinee to be tested with the corresponding light source direction and light source intensity.

[0038] S102, based on the reference facial image, each real-time facial image is divided into regions to obtain a plurality of facial detection regions in each real-time facial image, wherein the reference facial image is used to represent the correct facial image for the identity verification of the examinee;

[0039] In this embodiment, the reference facial image is used to represent a pre-stored and verified correct facial image of the examinee, which is usually acquired during registration. For example, the reference facial image may be the facial image on the admission ticket.

[0040] As an example, the server uses a facial recognition algorithm (such as Haar features, HOG+SVM, deep learning model, etc.) to identify and divide multiple face detection areas in the reference face image. For example, the face detection area may include a right eye detection area, a left eye detection area, a left cheek detection area, and a right cheek detection area.

[0041] Then, according to the position of each face detection area in the reference face image, each real-time face image is divided into regions to obtain the corresponding face detection area in each real-time face image.

[0042] S103, for each face detection area, respectively performing: determining the illumination consistency of the face detection area according to the grayscale value of each pixel in the face detection area of ​​each real-time face image, where the illumination consistency is used to characterize the consistency degree of illumination influence on each pixel in the face detection area;

[0043] In this embodiment, illumination consistency is used to characterize the consistency of the influence of illumination on each pixel in the face detection area, that is, the uniformity of the grayscale value of each pixel in the face detection area.

[0044] As an example, the server calculates the variance or standard deviation of the grayscale values ​​of the pixels in each real-time facial image for each face detection area, and calculates the mean of the variance or the inverse of the standard deviation of the grayscale values ​​of each pixel as the lighting consistency of the face detection area, thereby being used to evaluate the local lighting changes in the face detection area.

[0045] Specifically, the larger the variance or standard deviation of the grayscale value of the pixel point is, the greater the floating degree between the grayscale values ​​of the pixels in the face detection area is, and at this time, the smaller the illumination consistency of the face detection area is.

[0046] S104, determining the reliability probability of the examinee to be detected according to the illumination consistency of each face detection area;

[0047] In this embodiment, the server combines the illumination consistency of each face detection area and uses a weighted average, a voting mechanism, or a machine learning model to evaluate the reliability probability of the candidate to be detected.

[0048] Specifically, when the candidate to be tested is himself, the face detection area of ​​the real-time face image should be consistent with the face detection area of ​​the reference face image, that is, the face detection area finally divided by the real-time face image is also the correct right eye detection area, left eye detection area, left cheek detection area and right cheek detection area.

[0049] When a face detection area contains pixels on the same part of a face, the degree to which they are affected by illumination should be the same, that is, the greater the illumination consistency, the higher the consistency between the face detection area of ​​the real-time face image and the face detection area of ​​the reference face image, that is, the greater the reliability probability of the candidate to be detected.

[0050] S105, when the reliability probability of the candidate to be tested is greater than a preset reliability threshold, it is determined that the identity authentication of the candidate to be tested is successful.

[0051] In this embodiment, the server pre-sets a preset reliability threshold. Then the reliability probability of the candidate to be tested determined above is compared with the preset reliability threshold. When the reliability probability of the candidate to be tested is greater than the preset reliability threshold, it is determined that the identity authentication of the candidate to be tested is successful, that is, the candidate to be tested is the candidate himself; when the reliability probability of the candidate to be tested is less than or equal to the preset reliability threshold, it is determined that the identity authentication of the candidate to be tested has failed, that is, the candidate to be tested is not the candidate himself.

[0052] In the candidate identity verification method based on face recognition technology provided in the present embodiment, based on the reference face image, the real-time face image is divided into regions to obtain multiple face detection regions. Then, for each face detection region, the illumination consistency of the face detection region is determined according to the grayscale value of each pixel in the face detection region of each real-time face image, and the illumination consistency is used to characterize the consistency degree of the influence of illumination on each pixel in the face detection region. Finally, the identity of the candidate to be detected is verified according to the illumination consistency of each face detection region. In this way, the present invention divides the real-time face image into multiple face detection regions based on the reference face image, and evaluates the degree of influence of illumination on the pixels in each face detection region, so as to accurately determine whether the identity verification of the candidate to be detected is successful. It can avoid the problem of low accuracy caused by direct judgment from the overall face image, and improve the accuracy of the candidate's identity verification.

[0053] As an optional embodiment, before S102, the examinee identity verification method based on face recognition technology may also include:

[0054] Calculating the similarity between each real-time facial image and the reference facial image to obtain the image similarity between each real-time facial image and the reference facial image;

[0055] When the maximum similarity among the image similarities is greater than the first similarity threshold, it is determined that the identity authentication of the candidate to be tested is successful;

[0056] When the maximum similarity among the image similarities is less than the second similarity threshold, it is determined that the identity authentication of the candidate to be detected has failed, and the second similarity threshold is less than the first similarity threshold;

[0057] S102 may specifically include:

[0058] When the maximum similarity among the image similarities is not greater than the first similarity threshold and not less than the second similarity threshold, each real-time facial image is region-divided based on the reference facial image to obtain a plurality of facial detection regions in each real-time facial image.

[0059] In this embodiment, the first similarity threshold is used to determine whether the candidate to be detected is the candidate himself, and the second similarity threshold is used to determine whether the candidate to be detected is not the candidate himself. The second similarity threshold is smaller than the first similarity threshold.

[0060] As an example, the server uses a facial recognition algorithm (such as a deep learning model) to extract the first feature vector of the reference facial image, and uses the same facial recognition algorithm to extract the second feature vector of each real-time facial image. Then, the target similarity calculation method (such as cosine similarity, Euclidean distance, and Manhattan distance, etc.) is used to compare the similarity between the feature vector of the real-time facial image and the feature vector of the reference facial image to obtain the image similarity between each real-time facial image and the reference facial image.

[0061] Then, the maximum similarity is found among the similarities of each image, and the maximum similarity is compared with the first similarity threshold and the second similarity threshold, respectively. When the maximum similarity is greater than the first similarity threshold, it is directly determined that the identity authentication of the candidate to be detected is successful, that is, the candidate to be detected belongs to the candidate himself; when the maximum similarity is less than the second similarity threshold, it is directly determined that the identity authentication of the candidate to be detected fails, that is, the candidate to be detected does not belong to the candidate himself; and when the maximum similarity is not greater than the first similarity threshold and not less than the second similarity threshold, it is impossible to directly determine whether the candidate to be detected belongs to the candidate himself, then each real-time facial image is divided into regions, and the identity authentication of the candidate to be detected is performed according to the candidate identity authentication method based on face recognition technology.

[0062] Through this embodiment, a first similarity threshold and a second similarity threshold are set, and then the maximum similarity among the image similarities between each real-time facial image and the reference facial image is compared with the first similarity threshold and the second similarity threshold, respectively. In this way, the identity verification of the candidate to be detected can be directly and simply completed when the candidate to be detected obviously belongs to the candidate himself or the candidate to be detected obviously does not belong to the candidate himself, thereby improving the efficiency of the identity verification of the candidate to be detected.

[0063] As an optional embodiment, S102 may specifically include:

[0064] Based on the size of the facial region in the reference facial image, resize each real-time facial image so that the size of the facial region in each real-time facial image is equal to the size of the facial region in the reference facial image, thereby obtaining each real-time facial image after resizing;

[0065] By using an edge detection algorithm, the reference facial image is divided into regions to obtain a plurality of facial detection regions in the reference facial image;

[0066] Based on the region position of each face detection region in the reference face image, each real-time face image after the size adjustment is divided into regions to obtain a plurality of face detection regions in each real-time face image.

[0067] In this embodiment, the server uses a facial detection algorithm (such as Haar features, HOG+SVM, deep learning model, etc.) to identify facial regions in the reference facial image and the real-time facial image. For each real-time facial image, the width and height of its facial region are calculated, and then the scaling ratio to the reference size of the facial region in the reference facial image is calculated. Then, an image scaling algorithm (such as bilinear interpolation, nearest neighbor interpolation, etc.) is used to scale each real-time facial image so that the size of its facial region is equal to the reference size of the facial region in the reference facial image.

[0068] Then, edge detection is performed on the reference facial image using an edge detection algorithm (such as Canny edge detector, Sobel operator, Laplacian operator, etc.) to obtain edge information of the facial region in the reference facial image. Based on the edge information, the reference facial image is divided into multiple regions according to facial features.

[0069] Finally, based on the position information (e.g., center coordinates, width, height, etc.) of each face detection area in the reference face image, a mapping relationship between these face detection areas and the corresponding areas in the real-time face image is established. Thus, based on the mapping relationship, the area corresponding to the face detection area in the reference face image is divided in the real-time face image after the size adjustment.

[0070] Through this embodiment, each real-time facial image is first resized so that the size of the facial area in each real-time facial image is equal to the size of the facial area in the reference facial image. Then, each real-time facial image is divided into regions according to the multiple facial detection regions in the reference facial image. In this way, the region division of the real-time facial image can be completed accurately, which is helpful for the subsequent verification of the candidate's identity according to the facial detection region of the real-time facial image.

[0071] As an optional embodiment, Figure 2As shown, S103 may specifically include: for each face detection area, respectively executing the following S201 to S205.

[0072] S201, determining the illumination influence of each pixel in each preset light source direction according to the gray value of each pixel in the face detection area in each real-time face image, where the illumination influence is used to characterize the degree to which the pixel is affected by the light intensity;

[0073] S202, determining the local illumination consistency of the face detection area under each preset light source direction according to the illumination influence of each pixel point under each preset light source direction;

[0074] S203, setting weights for the preset light source directions based on the mean grayscale values ​​of the pixels in the face detection area at the maximum light source intensity in the preset light source directions;

[0075] S204, clustering the preset light source directions based on the weights of the preset light source directions to obtain at least one light source direction cluster;

[0076] S205 , determining the illumination consistency of the face detection area according to the local illumination consistency of the face detection area under each preset light source direction and the light source direction cluster.

[0077] In this embodiment, the illumination influence degree is used to characterize the degree to which a pixel point is affected by the illumination intensity in a preset light source direction.

[0078] Local illumination consistency is used to characterize the local illumination consistency of the face detection area only under a certain preset light source direction.

[0079] As an example, for each face detection area, the server performs the following steps respectively:

[0080] First, for each pixel point in the face detection area, obtain the grayscale value in the real-time face image corresponding to different preset light source intensities under the same preset light source direction. According to the change of the grayscale value of the pixel point in different preset light source intensities under the preset light source direction, the illumination influence of the pixel point in the preset light source direction can be determined. Specifically, the greater the change of the grayscale value of the pixel point in different preset light source intensities under the preset light source direction, the greater the illumination influence; the smaller the change of the grayscale value of the pixel point in different preset light source intensities under the preset light source direction, the smaller the illumination influence. In this way, the illumination influence of each pixel point in the face detection area under each preset light source direction can be obtained through the above steps.

[0081] Then, for each preset light source direction, the variance or standard deviation of the illumination influences of all pixels in the face detection area under the preset light source direction is calculated, and the inverse of the variance or standard deviation is used as the local illumination consistency of the face detection area under the preset light source direction. Specifically, the smaller the difference between the illumination influences of the pixels in the face detection area under the preset light source direction, the greater the local illumination consistency of the face detection area under the preset light source direction; the greater the difference between the illumination influences of the pixels in the face detection area under the preset light source direction, the smaller the local illumination consistency of the face detection area under the preset light source direction.

[0082] Then, the grayscale mean of the pixels in the maximum light intensity of the face detection area under each preset light source direction is calculated, and the weight of the face detection area in each preset light source direction is set by the following formula 1:

[0083] Formula 1

[0084] In formula 1, It is used to represent the weight of the a-th face detection area in the b-th preset light source direction. It is used to represent the average grayscale value of the pixels in the a-th face detection area with the maximum light intensity in the b-th preset light source direction. Used to characterize the weight normalization function.

[0085] Then, the server selects a suitable clustering algorithm according to actual needs, such as K-means, hierarchical clustering, etc. Using the selected clustering algorithm, cluster each preset light source direction according to the weight of the face detection area in each preset light source direction, and obtain at least one light source direction cluster, each cluster containing multiple preset light source directions with similar weights.

[0086] Finally, for each light source direction cluster, the local illumination consistency of the face detection area under each preset light source direction within the cluster is evaluated. Specifically, the local illumination consistency of the face detection area under each preset light source direction within the light source direction cluster can be statistically analyzed to obtain the local illumination consistency corresponding to the light source direction cluster. Thus, according to the local illumination consistency corresponding to each light source direction cluster, a weighted average, voting mechanism, or machine learning model is used to evaluate the illumination consistency of the face detection area.

[0087] Through this embodiment, the illumination consistency of the pixels in the face detection area affected by illumination is comprehensively determined based on the grayscale values ​​of the pixels in the real-time face image at each preset light source direction and each preset light source intensity in the face detection area. In this way, comprehensive analysis from multiple preset light source directions and multiple preset light source intensities can accurately evaluate the illumination consistency of the pixels in the face detection area affected by illumination, thereby improving the accuracy of the examinee's identity verification.

[0088] As an optional embodiment, S201 may specifically include:

[0089] For each pixel, perform the following steps under each preset light source direction:

[0090] The grayscale value of the pixel point at the d-th preset light source intensity in the preset light source direction is subtracted from the grayscale value of the pixel point at the d-1-th preset light source intensity in the preset light source direction to obtain the d-th grayscale value difference, where d is a positive integer;

[0091] Divide the d-th grayscale value difference by the target grayscale value to obtain the local illumination influence of the pixel point under the d-th preset light source intensity in the preset light source direction, and the target grayscale value is the grayscale value of the pixel point under the maximum preset light source intensity in the preset light source direction;

[0092] The local illumination influence of the pixel point under each preset light source intensities in the preset light source direction is averaged to obtain the illumination influence of the pixel point under the preset light source direction.

[0093] In this embodiment, the local illumination influence of a pixel point in a preset light source direction can be specifically determined by the following formula 2:

[0094] Formula 2

[0095] In formula 2, Used to represent the dth local illumination influence of the ith pixel in the ath face detection area under the bth preset light source direction. It is used to represent the gray value of the ith pixel in the ath face detection area under the dth preset light source intensity under the bth preset light source direction. Used to represent the grayscale value of the ith pixel in the ath face detection area under the d-1th preset light source intensity in the bth preset light source direction. The gray value used to represent the i-th pixel point in the a-th face detection area under the maximum preset light source intensity under the b-th preset light source direction is not 0.

[0096] Among them, as the intensity of the light source becomes stronger, the grayscale value of the pixel also increases. The larger the value of , the greater the influence of the i-th pixel in the a-th face detection area by the b-th preset light source direction, and the greater the illumination influence of the i-th pixel in the a-th face detection area under the b-th preset light source direction.

[0097] After obtaining each local illumination influence degree of the pixel point under the preset light source direction, the illumination influence degree of the pixel point under the preset light source direction can be obtained by performing mean calculation on each local illumination influence degree.

[0098] Through this embodiment, according to the difference between the grayscale values ​​of the pixel points under each preset light source intensity in the preset light source direction, the illumination influence of the pixel points under the preset light source direction can be accurately evaluated. In this way, by accurately calculating the illumination influence of each pixel point under each preset light source direction, the accuracy of the candidate's identity verification can be improved.

[0099] As an optional embodiment, S202 may specifically include:

[0100] For the face detection area, perform the following steps under each preset light source direction:

[0101] Based on the illumination influence of each pixel point under the preset light source direction, clustering each pixel point to obtain at least one pixel point cluster;

[0102] The number of pixels in the largest pixel cluster is divided by the total number of pixels in the face detection area to obtain the local illumination consistency of the face detection area under the preset light source direction.

[0103] In this embodiment, for the face detection area, the server performs the following steps respectively under each preset light source direction:

[0104] First, the server uses a density-based clustering algorithm to cluster each pixel in the face detection area based on the illumination influence of each pixel in the preset light source direction to obtain at least one pixel cluster, each pixel cluster containing multiple pixels with similar illumination influence.

[0105] Then, the local illumination consistency of the face detection area under the preset light source direction is determined by the following formula 3:

[0106] Formula 3

[0107] In formula 3, Used to characterize the local illumination consistency of the a-th face detection area under the b-th preset light source direction. It is used to represent the number of pixels in the largest pixel cluster of the a-th face detection area under the b-th preset light source direction. Used to represent the total number of pixels in the a-th face detection area.

[0108] in, The larger it is, the more similar the degree to which the pixels in the ath face detection area under the bth preset light source direction are affected by lighting, that is, the greater the possibility that the pixels in the ath face detection area belong to the same part of the face, the higher the consistency between the face detection area of ​​the real-time face image and the face detection area of ​​the reference face image, and thus the greater the reliability probability of the candidate to be tested.

[0109] Through this embodiment, based on the illumination influence of each pixel in the face detection area under the preset light source direction, the local illumination consistency of the face detection area under the preset light source direction can be accurately evaluated. In this way, by accurately calculating the local illumination consistency of the face detection area under each preset light source direction, the accuracy of the candidate's identity verification can be improved.

[0110] As an optional embodiment, S205 may specifically include:

[0111] The variance of the local illumination consistency of the face detection area under the preset light source direction in each light source direction cluster is calculated respectively to obtain the illumination consistency fluctuation of the face detection area in each light source direction cluster;

[0112] Determining the continuity of the light source directions corresponding to the face detection area and each light source direction cluster according to the number of preset light source directions of the face detection area in each light source direction cluster;

[0113] The illumination consistency of the face detection area is determined based on the local illumination consistency, the fluctuation of the illumination consistency, and the continuity of the light source direction.

[0114] In this embodiment, the server performs variance calculation on the local illumination consistency of the face detection area under each preset light source direction in the light source direction cluster to obtain the illumination consistency fluctuation of the face detection area in the light source direction cluster.

[0115] Then, the number of preset light source directions of the face detection area in the light source direction cluster is subtracted by 2 to obtain the light source direction continuity corresponding to the face detection area and the light source direction cluster.

[0116] Finally, according to the consistency of each local illumination, the fluctuation of each illumination consistency, and the continuity of each light source direction, the illumination consistency of the face detection area is determined by the following formula 4:

[0117] Formula 4

[0118] In formula 4, Used to characterize the illumination consistency of the a-th face detection area, Used to characterize the local illumination consistency of the a-th face detection area under the b-th preset light source direction. is used to represent the weight of the a-th face detection area in the b-th preset light source direction, and n is used to represent the total number of preset light source directions. The mean value used to characterize the continuity of the directions of the light sources in the a-th face detection area is not 0. It is used to represent the mean of the consistent fluctuations of the illumination of the a-th face detection area, and exp is used to represent the exponential operation.

[0119] in, The smaller the value of is, the more consistent it is with the feature that when the pixels of the a-th face detection area belong to the same part of the face, multiple connected preset light source directions will be clustered into a similar cluster, and the greater the illumination consistency of the a-th face detection area; The smaller the value of is, the more it conforms to the characteristic that when the pixels of the a-th face detection area belong to the same part of the face, the local illumination consistency of all preset light source directions in the light source direction cluster is closer, and the greater the illumination consistency of the a-th face detection area.

[0120] Through this embodiment, according to the illumination consistency fluctuation of the face detection area in each light source direction cluster, the continuity of the light source direction corresponding to the face detection area and each light source direction cluster, and the local illumination consistency of the face detection area under the preset light source direction, the illumination consistency of the face detection area can be accurately evaluated. In this way, by accurately calculating the illumination consistency of the face detection area, the accuracy of the candidate's identity verification can be improved.

[0121] As an optional embodiment, S104 may specifically include:

[0122] Determine a reference detection area for each face detection area according to the number of pixels in each face detection area, the reference detection area being an area whose difference in the number of pixels between the reference detection area and the face detection area is less than a pixel difference threshold;

[0123] The reliability probability of the examinee to be tested is determined based on the illumination consistency of each face detection area and the illumination consistency of the corresponding control detection area.

[0124] In this embodiment, since the human face is a bilaterally symmetrical image, if the examinee to be detected is the examinee himself, there will be some face detection areas with similar illumination consistency. For example, the illumination consistency of the left eye detection area is similar to that of the right eye detection area.

[0125] Therefore, the server first obtains the number of pixels in each face detection area. Then, for each face detection area, other face detection areas whose difference in the number of pixels with the face detection area is less than 5 are determined as the comparison detection area of ​​the face detection area. For example, if there are multiple other face detection areas that meet this condition, the one with the smallest difference is determined as the comparison detection area of ​​the face detection area. In this way, the comparison detection area of ​​each face detection area can be obtained.

[0126] Then, according to the illumination consistency of each face detection area and the illumination consistency of the corresponding control detection area, the reliability probability of the candidate to be detected is determined by the following formula 5:

[0127] Formula 5

[0128] In formula 5, S is used to represent the reliability probability of the examinee to be tested. Used to characterize the illumination consistency of the b-th face detection area, It is used to characterize the illumination consistency of the control detection area of ​​the b-th face detection area, and M is used to characterize the number of face detection areas where the control detection areas exist. It is used to represent the total number of pixels in the a-th face detection area. It is used to represent the illumination consistency of the a-th face detection area. exp is used to represent the exponential operation. It is used to represent the weight normalization function, and j is used to represent the total number of face detection areas.

[0129] in, The larger the value of , the greater the illumination consistency of multiple face detection areas of the candidate to be detected, which means that the possibility that the candidate to be detected is the candidate himself is greater, that is, the greater the reliability probability of the candidate to be detected; The smaller the value is, the more the facial detection area of ​​the candidate to be tested and its corresponding control detection area conform to the left-right symmetry of the face, which means that the possibility that the candidate to be tested is the candidate himself is greater, that is, the greater the reliability probability of the candidate to be tested.

[0130] Through this embodiment, the reliability probability of the candidate to be detected can be accurately evaluated according to the illumination consistency of each face detection area and the illumination consistency of the corresponding control detection area. In this way, the accuracy of the candidate's identity verification can be improved by accurately calculating the reliability probability of the candidate to be detected.

[0131] According to the examinee identity verification method based on face recognition technology, the present invention also provides a specific embodiment of an examinee identity verification system based on face recognition technology.

[0132] Figure 3A structural diagram of the candidate identity verification system based on face recognition technology provided in an embodiment of the present application is shown. The candidate identity verification system 300 based on face recognition technology may include an image acquisition module 310, a region division module 320, a region calculation module 330, a probability calculation module 340 and an identity verification module 350.

[0133] The image acquisition module 310 is used to acquire a plurality of real-time facial images of the examinee to be tested under a plurality of preset light source directions and a plurality of preset light source intensities;

[0134] A region division module 320 is used to divide each real-time facial image into regions based on the reference facial image to obtain a plurality of facial detection regions in each real-time facial image, wherein the reference facial image is used to represent the correct facial image for the identity verification of the examinee;

[0135] The region calculation module 330 is used to respectively perform, for each face detection region: determining the illumination consistency of the face detection region according to the grayscale value of each pixel in the face detection region of each real-time face image, where the illumination consistency is used to characterize the consistency degree of illumination influence on each pixel in the face detection region;

[0136] The probability calculation module 340 is used to determine the reliability probability of the examinee to be detected according to the illumination consistency of each face detection area;

[0137] The identity authentication module 350 is used to determine that the identity authentication of the candidate to be detected is successful when the reliability probability of the candidate to be detected is greater than a preset reliability threshold.

[0138] In the candidate identity verification system based on face recognition technology provided by the present embodiment, based on the reference face image, the real-time face image is divided into regions to obtain multiple face detection regions. Then, for each face detection region, the illumination consistency of the face detection region is determined according to the grayscale value of each pixel in the face detection region of each real-time face image, and the illumination consistency is used to characterize the consistency degree of the influence of illumination on each pixel in the face detection region. Finally, the identity of the candidate to be detected is verified according to the illumination consistency of each face detection region. In this way, the present invention divides the real-time face image into multiple face detection regions based on the reference face image, and evaluates the influence of illumination on the pixels in each face detection region, so as to accurately determine whether the identity verification of the candidate to be detected is successful. It can avoid the problem of low accuracy caused by direct judgment from the overall face image, and improve the accuracy of the candidate's identity verification.

[0139] According to the examinee identity verification method based on face recognition technology, the present invention also provides a specific embodiment of an examinee identity verification device based on face recognition technology.

[0140] Figure 4 A schematic diagram of the hardware structure of a candidate identity verification device based on face recognition technology provided in an embodiment of the present invention is shown.

[0141] The examinee identity verification device based on face recognition technology may include a processor 401 and a memory 402 storing computer program instructions.

[0142] Specifically, the processor 401 may include a central processing unit, or a specific integrated circuit, or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0143] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive, a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus drive, or a combination of two or more of these. Where appropriate, memory 402 may include a removable or non-removable (or fixed) medium. Where appropriate, memory 402 may be inside or outside the integrated gateway disaster recovery device. In a particular embodiment, memory 402 is a non-volatile solid-state memory.

[0144] The memory 402 may include read-only memory, random access memory, magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory 402 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0145] The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any one of the candidate identity verification methods based on face recognition technology in the above-mentioned embodiments.

[0146] In one example, the digital twin model building device in a complex scenario may further include a communication interface 403 and a bus 410. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0147] The communication interface 403 is mainly used to implement communication between each module, device, unit and / or equipment in the embodiment of the present application.

[0148] Bus 410 includes hardware, software or both, and couples the components of the examinee identity verification device based on face recognition technology to each other. For example, but not limitation, the bus may include an accelerated graphics port or other graphics bus, an enhanced industrial standard architecture bus, a front-end bus, a hypertransport interconnect, an industrial standard architecture bus, an infinite bandwidth interconnect, a low pin count bus, a memory bus, a microchannel architecture bus, a peripheral component interconnect bus, a serial advanced technology attachment bus, a video electronics standard association local bus or other suitable bus or a combination of two or more of these. Where appropriate, bus 410 may include one or more buses. Although the present application embodiment describes and illustrates a specific bus, the present application considers any suitable bus or interconnect.

[0149] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0150] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0151] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A candidate identity verification method based on face recognition technology, characterized in that: The method comprises: Acquire multiple real-time facial images of the examinee to be tested under multiple preset light source directions and multiple preset light source intensities; Based on the reference facial image, each of the real-time facial images is divided into regions to obtain a plurality of facial detection regions in each of the real-time facial images, wherein the reference facial image is used to represent the correct facial image for the identity verification of the examinee; For each of the face detection areas, respectively performing: determining the illumination consistency of the face detection area according to the grayscale value of each pixel point in the face detection area of ​​each of the real-time face images, wherein the illumination consistency is used to characterize the consistency degree of each pixel point in the face detection area affected by illumination; Determining the reliability probability of the examinee to be detected according to the illumination consistency of each of the face detection areas; When the reliability probability of the candidate to be tested is greater than a preset reliability threshold, it is determined that the identity authentication of the candidate to be tested is successful.

2. The examinee identity verification method based on face recognition technology according to claim 1 is characterized in that: Before dividing each of the real-time facial images into regions based on the reference facial image to obtain a plurality of facial detection regions in each of the real-time facial images, the method further includes: Calculating the similarity between each of the real-time facial images and the reference facial image to obtain the image similarity between each of the real-time facial images and the reference facial image; When the maximum similarity among the image similarities is greater than the first similarity threshold, it is determined that the identity authentication of the candidate to be detected is successful; In the case where the maximum similarity among the image similarities is less than the second similarity threshold, it is determined that the identity authentication of the candidate to be detected has failed, and the second similarity threshold is less than the first similarity threshold; The step of dividing each of the real-time facial images into regions based on the reference facial image to obtain a plurality of facial detection regions in each of the real-time facial images comprises: When the maximum similarity among the image similarities is not greater than the first similarity threshold and not less than the second similarity threshold, each of the real-time facial images is divided into regions based on a reference facial image to obtain a plurality of facial detection regions in each of the real-time facial images.

3. The examinee identity verification method based on face recognition technology according to claim 1 is characterized in that: The step of dividing each of the real-time facial images into regions based on the reference facial image to obtain a plurality of facial detection regions in each of the real-time facial images comprises: Based on the size of the facial region in the reference facial image, resize each of the real-time facial images so that the size of the facial region in each of the real-time facial images is equal to the size of the facial region in the reference facial image, thereby obtaining each of the real-time facial images after resizing; By using an edge detection algorithm, the reference facial image is divided into regions to obtain a plurality of facial detection regions in the reference facial image; Based on the area position of each face detection area in the reference face image, each of the real-time face images after the size adjustment is respectively divided into areas to obtain a plurality of face detection areas in each of the real-time face images.

4. The examinee identity verification method based on face recognition technology according to any one of claims 1 to 3, characterized in that: For each of the face detection areas, respectively performing: determining the illumination consistency of the face detection area according to the grayscale value of each pixel in the face detection area of ​​each of the real-time face images, wherein the illumination consistency is used to characterize the consistency degree of each pixel in the face detection area affected by illumination, including: For each of the face detection areas, the following steps are performed respectively: According to the grayscale value of each pixel point in the face detection area in each of the real-time face images, respectively determine the illumination influence degree of each pixel point under each of the preset light source directions, wherein the illumination influence degree is used to characterize the degree to which the pixel point is affected by the light intensity; Determining the local illumination consistency of the face detection area in each of the preset light source directions according to the illumination influence of each of the pixel points in each of the preset light source directions; Based on the mean grayscale value of the pixels in the face detection area under the maximum light intensity in each of the preset light source directions, respectively setting the weight of each of the preset light source directions; Based on the weight of each of the preset light source directions, clustering the preset light source directions to obtain at least one light source direction cluster; The illumination consistency of the face detection area is determined according to the local illumination consistency of the face detection area under each of the preset light source directions and the light source direction cluster.

5. The examinee identity verification method based on face recognition technology according to claim 4 is characterized in that: The step of determining the illumination influence of each pixel in each of the preset light source directions according to the grayscale value of each pixel in the face detection area in each of the real-time face images comprises: For each pixel point, the following steps are performed respectively under each preset light source direction: Subtract the grayscale value of the pixel point at the d-th preset light source intensity in the preset light source direction from the grayscale value of the pixel point at the d-1th preset light source intensity in the preset light source direction to obtain the d-th grayscale value difference, where d is a positive integer; Dividing the d-th grayscale value difference by the target grayscale value, the local illumination influence of the pixel point under the d-th preset light source intensity in the preset light source direction is obtained, and the target grayscale value is the grayscale value of the pixel point under the maximum preset light source intensity in the preset light source direction; The local illumination influence of the pixel point under each of the preset light source intensities in the preset light source direction is averaged to obtain the illumination influence of the pixel point under the preset light source direction.

6. The examinee identity verification method based on face recognition technology according to claim 4 is characterized in that: The determining, according to the illumination influence of each pixel point in each of the preset light source directions, respectively the local illumination consistency of the face detection area in each of the preset light source directions, comprises: For the face detection area, the following steps are performed respectively under each of the preset light source directions: Based on the illumination influence of each pixel point in the preset light source direction, clustering each pixel point to obtain at least one pixel point cluster; The number of pixels in the largest pixel cluster is divided by the total number of pixels in the face detection area to obtain the local illumination consistency of the face detection area in the preset light source direction.

7. The examinee identity verification method based on face recognition technology according to claim 4 is characterized in that: The determining the illumination consistency of the face detection area according to the local illumination consistency of the face detection area under each of the preset light source directions and the light source direction cluster comprises: Performing variance calculations on the local illumination consistency of the face detection area under the preset light source directions in each of the light source direction clusters to obtain illumination consistency fluctuations of the face detection area in each of the light source direction clusters; Determining the continuity of the light source directions corresponding to the face detection area and each of the light source direction clusters according to the number of the preset light source directions of the face detection area in each of the light source direction clusters; The illumination consistency of the face detection area is determined according to the local illumination consistency, the illumination consistency fluctuation and the light source direction continuity.

8. The examinee identity verification method based on face recognition technology according to any one of claims 1 to 3, characterized in that: The step of determining the reliability probability of the examinee to be detected according to the illumination consistency of each of the face detection areas includes: Determine, according to the number of pixels in each face detection area, a control detection area for each face detection area, wherein the control detection area is an area whose difference in the number of pixels between the face detection area and the face detection area is less than a pixel difference threshold; The reliability probability of the examinee to be detected is determined based on the illumination consistency of each of the face detection areas and the illumination consistency of the corresponding control detection area.

9. A candidate identity verification device based on face recognition technology, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the candidate identity authentication method based on face recognition technology as described in any one of claims 1-8.

10. A candidate identity verification system based on face recognition technology, characterized in that: The system comprises: An image acquisition module is used to acquire multiple real-time facial images of the examinee under multiple preset light source directions and multiple preset light source intensities; A region division module, for performing region division on each of the real-time facial images based on a reference facial image, to obtain a plurality of facial detection regions in each of the real-time facial images, wherein the reference facial image is used to represent a correct facial image for identity verification of the examinee; A region calculation module, for each of the face detection regions, respectively performing: determining the illumination consistency of the face detection region according to the grayscale value of each pixel in the face detection region of each of the real-time face images, wherein the illumination consistency is used to characterize the consistency degree of each pixel in the face detection region affected by illumination; A probability calculation module, used to determine the reliability probability of the examinee to be detected according to the illumination consistency of each face detection area; The identity authentication module is used to determine that the identity authentication of the candidate to be detected is successful when the reliability probability of the candidate to be detected is greater than a preset reliability threshold.

Images