A method, device, equipment and storage medium for verifying face video

Abstract

The present disclosure is about a facial video verification method, device, equipment and storage medium, and relates to the field of Internet technology. The method includes: receiving a facial video to be identified including a picture to be identified and generation information corresponding to the picture to be identified sent by a terminal; based on the generation information, performing frame extraction processing on the facial video to be identified to obtain a target picture; when the similarity between the target picture and the picture to be identified is greater than or equal to a similarity threshold, determining that the facial video to be identified is a facial video corresponding to a target account. In the present disclosure, the server can improve the verification accuracy of facial videos. Furthermore, when the facial video to be identified is a facial video corresponding to a target account, the server can effectively verify whether the current account has abnormal use of the real account, which can improve the accuracy of account verification.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and in particular to a face video verification method, device, equipment and storage medium. Background Art

[0002] Currently, the terminal can send a face video of a certain account and a face picture of the account to the server, so that the server can perform face verification on the account, specifically verifying the legitimacy of the account.

[0003] However, the above face picture may be a tampered picture, for example, the face picture of the target person is processed to obtain the face picture of the above account. This makes it impossible for the server to accurately verify the account that currently sends the face picture, reducing the accuracy of account verification. Summary of the invention

[0004] The present invention provides a facial video verification method, device, equipment and storage medium, which solves the technical problem in the prior art that the server cannot accurately verify the account currently sending the facial image, thereby reducing the accuracy of account verification.

[0005] The technical solution of the embodiment of the present disclosure is as follows:

[0006] According to the first aspect of the embodiments of the present disclosure, a method for verifying a face video is provided. The method may include: receiving a face video to be identified including a picture to be identified and generation information corresponding to the picture to be identified sent by a receiving terminal, the picture to be identified is one of a plurality of pictures, the plurality of pictures are pictures in a plurality of video frames corresponding to the face video to be identified, the generation information is used to characterize a target video frame corresponding to the picture to be identified, the picture to be identified includes a face region corresponding to a target account; based on the generation information, the face video to be identified is subjected to frame extraction processing to obtain a target picture; when the similarity between the target picture and the picture to be identified is greater than or equal to a similarity threshold, determining that the face video to be identified is a face video corresponding to the target account.

[0007] Optionally, the above-mentioned facial video to be identified including the picture to be identified is obtained by the terminal adding target additional information to the facial video to be identified, and the target additional information is one of multiple additional information corresponding to the facial video to be identified. The above-mentioned facial video verification method also includes: when the target additional information does not exist in the facial video to be identified including the picture to be identified, determining that the facial video to be identified is not the facial video corresponding to the target account.

[0008] Optionally, the above-mentioned facial video verification method also includes: determining whether the target video frame belongs to the multiple video frames; when the target video frame does not belong to the multiple video frames, determining that the generated information corresponding to the image to be identified is abnormal.

[0009] Optionally, the above-mentioned facial video verification method also includes: when the similarity between the target image and the image to be identified is less than the similarity threshold, determining that the facial video to be identified is not the facial video corresponding to the target account.

[0010] According to the second aspect of the embodiment of the present disclosure, a method for verifying a face video is provided. The method may include: obtaining a face video to be identified; determining generation information corresponding to a picture to be identified, the picture to be identified is one of a plurality of pictures, the plurality of pictures are pictures in a plurality of video frames corresponding to the face video to be identified, the generation information is used to characterize a target video frame corresponding to the picture to be identified, the picture to be identified includes a face area corresponding to a target account; adding the picture to be identified to the face video to be identified, obtaining a face video to be identified including the picture to be identified; sending the face video to be identified including the picture to be identified and the generation information to a server.

[0011] Optionally, the above-mentioned adding the picture to be identified to the face video to be identified to obtain the face video to be identified including the picture to be identified specifically includes: adding the picture to be identified to target additional information, the target additional information being one of multiple additional information corresponding to the face video to be identified; adding the target additional information to the face video to be identified to obtain the face video to be identified including the picture to be identified.

[0012] According to the third aspect of the embodiments of the present disclosure, a facial video verification device is provided. The device may include a receiving module, a processing module, and a determining module; the receiving module is configured to receive a facial video to be identified including a picture to be identified and generation information corresponding to the picture to be identified, sent by a terminal, the picture to be identified is one of a plurality of pictures, the plurality of pictures are pictures in a plurality of video frames corresponding to the facial video to be identified, the generation information is used to characterize a target video frame corresponding to the picture to be identified, and the picture to be identified includes a facial region corresponding to a target account; the processing module is configured to perform frame extraction processing on the facial video to be identified based on the generation information to obtain a target picture; the determining module is configured to determine that the facial video to be identified is a facial video corresponding to the target account when the similarity between the target picture and the picture to be identified is greater than or equal to a similarity threshold.

[0013] Optionally, the above-mentioned face video to be identified including the picture to be identified is obtained by the terminal adding target additional information to the face video to be identified, and the target additional information is one of multiple additional information corresponding to the face video to be identified.

[0014] The determination module is also configured to determine that the face video to be identified is not the face video corresponding to the target account when the target attached information does not exist in the face video to be identified that includes the picture to be identified.

[0015] Optionally, the determination module is further configured to determine whether the target video frame belongs to the multiple video frames; the determination module is further configured to determine that the generation information corresponding to the picture to be identified is abnormal when the target video frame does not belong to the multiple video frames.

[0016] Optionally, the determination module is further configured to determine that the face video to be identified is not the face video corresponding to the target account when the similarity between the target image and the image to be identified is less than the similarity threshold.

[0017] According to the fourth aspect of the embodiments of the present disclosure, a facial video verification device is provided. The device may include: an acquisition module, a determination module, a processing module, and a sending module; the acquisition module is configured to acquire a facial video to be identified; the determination module is configured to determine the generation information corresponding to the image to be identified, the image to be identified is one of a plurality of images, the plurality of images are images in a plurality of video frames corresponding to the facial video to be identified, the generation information is used to characterize the target video frame corresponding to the image to be identified, the image to be identified includes a facial region corresponding to a target account; the processing module is configured to add the image to be identified to the facial video to be identified, and obtain the facial video to be identified including the image to be identified; the sending module is configured to send the facial video to be identified including the image to be identified and the generation information to the server.

[0018] Optionally, the processing module is specifically configured to add the picture to be identified to the target subsidiary information, and the target subsidiary information is one of multiple subsidiary information corresponding to the face video to be identified; the processing module is also specifically configured to add the target subsidiary information to the face video to be identified to obtain the face video to be identified including the picture to be identified.

[0019] According to a fifth aspect of an embodiment of the present disclosure, a server is provided, which may include: a processor and a memory configured to store processor executable instructions; wherein the processor is configured to execute the instructions to implement any one of the optional facial video verification methods in the above-mentioned first aspect.

[0020] According to the sixth aspect of an embodiment of the present disclosure, a terminal is provided, which may include: a processor and a memory configured to store processor executable instructions; wherein the processor is configured to execute the instructions to implement any one of the optional facial video verification methods in the above-mentioned second aspect.

[0021] According to the seventh aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which instructions are stored. When the instructions in the computer-readable storage medium are executed by a device, the device is enabled to execute any one of the optional face video verification methods in the above-mentioned first aspect, or execute any one of the optional face video verification methods in the above-mentioned second aspect.

[0022] According to an eighth aspect of an embodiment of the present disclosure, a computer program product is provided, which includes computer instructions. When the computer instructions are executed on a device, the device executes any optional facial video verification method as described in the first aspect, or executes any optional facial video verification method as described in the second aspect.

[0023] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0024] Based on any of the above aspects, in the present disclosure, the server can receive a face video to be identified including a picture to be identified and the generation information corresponding to the picture to be identified, and based on the generation information, perform frame extraction processing on the face video to be identified to obtain a target picture. Since the generation information corresponding to the picture to be identified is used to characterize the target video frame corresponding to the picture to be identified, the server can perform frame extraction processing on the face video to be identified to obtain a picture (i.e., a target picture) corresponding to the same video frame as the target video frame from multiple video frames corresponding to the face video to be identified, and determine the similarity between the target picture and the picture to be identified. When the similarity is greater than or equal to the similarity threshold, it means that the similarity between the target picture and the picture to be identified is large, and the picture to be identified does not have the risk of being tampered with. In this way, the server can determine that the face video to be identified is the face video corresponding to the target account, which can improve the verification accuracy of the face video. Furthermore, when the facial video to be identified is the facial video corresponding to the target account, it means that the current account (specifically, the account that instructs the terminal to send the facial video to be identified to the server) is not a real account (i.e., the target account). In this way, the server can effectively verify whether the current account has any abnormal use of the real account, thereby improving the accuracy of account verification.

[0025] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0027] Figure 1 A schematic diagram of a face video verification system provided by an embodiment of the present disclosure is shown;

[0028] Figure 2 A schematic diagram of a flow chart of a face video verification method provided by an embodiment of the present disclosure is shown;

[0029] Figure 3 A schematic diagram showing a flow chart of another method for verifying a face video provided by an embodiment of the present disclosure;

[0030] Figure 4 A schematic diagram showing a flow chart of another method for verifying a face video provided by an embodiment of the present disclosure;

[0031] Figure 5 A schematic diagram showing a flow chart of another method for verifying a face video provided by an embodiment of the present disclosure;

[0032] Figure 6 A schematic diagram showing a flow chart of another method for verifying a face video provided by an embodiment of the present disclosure;

[0033] Figure 7 A schematic diagram showing a flow chart of another method for verifying a face video provided by an embodiment of the present disclosure;

[0034] Figure 8 A schematic diagram showing a flow chart of another method for verifying a face video provided by an embodiment of the present disclosure;

[0035] Fig. 9 A schematic diagram of the structure of a face video verification device provided by an embodiment of the present disclosure is shown;

[0036] Fig.10 A schematic diagram of the structure of another face video verification device provided by an embodiment of the present disclosure is shown;

[0037] Fig.11 A schematic diagram of the structure of a face video verification device provided by an embodiment of the present disclosure is shown;

[0038] Fig.12 A schematic structural diagram of another face video verification device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0039] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0040] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0041] It should also be understood that the term “comprising” indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or components.

[0042] The data involved in the present disclosure may be data authorized by the user or fully authorized by all parties.

[0043] As described in the background technology, since the face picture sent by the terminal to the server in the prior art may be a picture obtained after tampering, the server cannot accurately verify the account that currently sends the face picture, which reduces the accuracy of account verification (specifically, it may not be able to accurately verify whether the current account is a legitimate account). Based on this, the embodiment of the present disclosure provides a method for verifying a face video. When the similarity is greater than or equal to the similarity threshold, it means that the similarity between the target picture and the picture to be identified is large, and there is no risk of tampering with the picture to be identified. In this way, the server can determine that the face video to be identified is the face video corresponding to the target account, which can improve the verification accuracy of the face video. Furthermore, when the face video to be identified is the face video corresponding to the target account, it means that the current account (specifically, the account that instructs the terminal to send the face video to be identified to the server) is not a real account (i.e., the target account). In this way, the server can effectively verify whether the current account has abnormal behavior of using the real account, which can improve the accuracy of account verification.

[0044] The face video verification method, device, equipment and storage medium provided by the embodiments of the present disclosure are applied to the scenario of verifying the legitimacy of a certain account. When the server receives the face video to be identified including the picture to be identified and the generation information corresponding to the picture to be identified sent by the terminal, it can determine whether the face video to be identified is the face video corresponding to the target account according to the method provided by the embodiments of the present disclosure, and then determine whether the account of the face video to be identified is legal.

[0045] The following is an exemplary description of the face video verification method provided by the embodiment of the present disclosure in conjunction with the accompanying drawings:

[0046] Figure 1 A schematic diagram of a face video verification system provided by an embodiment of the present disclosure, such as Figure 1 As shown, the face video verification system may include a terminal 101 and a server 102, and the terminal 101 may establish a connection with the server 102 via a wired network or a wireless network.

[0047] The terminal 101 may be a mobile phone, tablet computer, desktop, laptop, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, cellular phone, personal digital assistant (PDA), augmented reality (AR) and virtual reality (VR) devices, etc., which can install and use content community applications. The present disclosure does not impose any special restrictions on the specific form of the terminal. It can interact with the user through one or more methods such as keyboard, touchpad, touch screen, remote control, voice interaction or handwriting device.

[0048] Specifically, the terminal 101 may obtain a video of a face to be identified. In the disclosed embodiment, the terminal 101 may also send a target file and generation information corresponding to the picture to be identified to the server 102.

[0049] The server 102 may receive the target file sent by the terminal 101 and the generation information corresponding to the image to be identified.

[0050] like Figure 2 As shown, when the face video verification method is applied to the above-mentioned terminal 101, the method may include S101-S104.

[0051] S101. The terminal obtains a video of a face to be recognized.

[0052] It should be understood that the face video to be identified is a video including the face area of ​​the target account. The terminal obtaining the face video to be identified can also be understood as collecting (or recording) the face video to be identified.

[0053] In one implementation of the disclosed embodiment, the above-mentioned face video to be identified is used to characterize the process of face liveness detection of the target account. Specifically, when the terminal needs to perform face liveness detection on the target account, it will issue some verification instructions (such as "open mouth", "blink", etc.), and the terminal will record the face liveness detection process, that is, the face video to be identified can be obtained.

[0054] S102: The terminal determines generation information corresponding to the image to be identified.

[0055] Among them, the picture to be identified is one of multiple pictures, the multiple pictures are pictures in multiple video frames corresponding to the face video to be identified, the generated information is used to characterize the target video frame corresponding to the picture to be identified, and the picture to be identified includes the face area corresponding to the target account.

[0056] It is understandable that the terminal can perform frame extraction processing on the face video to be recognized to obtain each of the multiple pictures (it can also be understood as obtaining a picture of each frame in the multiple video frames). And the video frame corresponding to each picture can be recorded (it can also be understood as determining which frame in the multiple video frames each picture corresponds to), that is, the generation information corresponding to each picture in the multiple pictures can be obtained.

[0057] It should be noted that the picture to be identified is a picture with higher definition among the multiple pictures.

[0058] S103: The terminal adds the picture to be recognized to the video of the face to be recognized, and obtains the video of the face to be recognized including the picture to be recognized.

[0059] It should be understood that after the terminal obtains the video of the face to be recognized including the picture to be recognized, it can send the video of the face to be recognized including the picture to be recognized to the server.

[0060] It should be noted that the embodiments of the present disclosure do not limit the execution order of the above S102 and S103. For example, S102 may be executed first and then S103, or S103 may be executed first and then S102, or S102 and S103 may be executed simultaneously. Figure 2 The explanation is given by first executing S102 and then executing S103.

[0061] S104: The terminal sends a video of a face to be identified including a picture to be identified and generation information corresponding to the picture to be identified to the server.

[0062] It should be understood that the terminal sends the video of the face to be identified including the picture to be identified and the generation information corresponding to the picture to be identified to the server, that is, sends the picture to be identified, the video of the face to be identified and the generation information corresponding to the picture to be identified to the server, so that the server can obtain the three items of content, specifically, the picture to be identified is included in the video of the face to be identified.

[0063] The technical solution provided by the above embodiment can at least bring the following beneficial effects: As can be seen from S101-S104, the terminal can obtain the face video to be identified and determine the generation information corresponding to the picture to be identified; then the terminal adds the picture to be identified to the face video to be identified, obtains the face video to be identified including the picture to be identified, and sends the face video to be identified including the picture to be identified and the generation information to the server. In this way, the terminal can ensure that the server can obtain the face video to be identified, the picture to be identified, and the generation information of the picture to be identified.

[0064] Furthermore, since the generated information is used to characterize the target video frame corresponding to the picture to be identified, the server can, after receiving the face video to be identified including the picture to be identified, perform frame extraction processing on the face video to be identified based on the generated information to obtain the target picture, and determine the similarity between the target picture and the picture to be identified, and then determine whether the face video to be identified is the face video corresponding to the target account based on the similarity, thereby improving the verification accuracy of the face video.

[0065] Combination Figure 2 ,like Figure 3 As shown, in one implementation of the embodiment of the present disclosure, the above-mentioned adding of the picture to be identified to the face video to be identified to obtain the face video to be identified including the picture to be identified, including S1031-S1032.

[0066] S1031. The terminal adds the image to be identified to the target auxiliary information.

[0067] Among them, the target additional information is one of the multiple additional information corresponding to the face video to be identified.

[0068] It is understandable that for a video (e.g., a video of a face to be identified), the video may correspond to multiple pieces of attached information. Specifically, an attached information may represent the author of the video, the album to which the video belongs, or the cover of the video. In the disclosed embodiment, the target attached information may represent the cover of the video of the face to be identified, that is, the terminal may add the picture to be identified to the cover of the video of the face to be identified.

[0069] S1032: The terminal adds the target additional information to the face video to be identified, so as to obtain the face video to be identified including the picture to be identified.

[0070] The technical solution provided by the above embodiment can at least bring the following beneficial effects: As can be seen from S1031-S1032, the terminal can add the picture to be identified to the target supplementary information (i.e., one of the multiple supplementary information corresponding to the face video to be identified), and then add the target supplementary information to the face video to be identified, so as to obtain the face video to be identified including the picture to be identified. In the embodiment of the present disclosure, the terminal can add the picture to be identified to a certain supplementary information corresponding to the face video to be identified and add the supplementary information to the face video to be identified, so as to conveniently and quickly obtain the face video to be identified including the picture to be identified, thereby improving the sending efficiency of the face video to be identified.

[0071] like Figure 4 As shown, when the face video verification method is applied to the above-mentioned server 102, the face video verification method may include S201-S203.

[0072] S201. A server receives a video of a face to be identified including a picture to be identified and generation information corresponding to the picture to be identified, sent by a terminal.

[0073] In combination with the description of the above embodiments, it should be understood that the picture to be identified is one of multiple pictures, and the multiple pictures are pictures in multiple video frames corresponding to the face video to be identified, and the generated information is used to characterize the target video frame corresponding to the picture to be identified, and the picture to be identified includes the face area corresponding to the target account.

[0074] S202: The server extracts frames of the face video to be identified based on the generated information corresponding to the image to be identified to obtain a target image.

[0075] It should be understood that the server can also obtain multiple pictures (which can also be understood as pictures in multiple video frames) by extracting frames from the video of the face to be identified. And the server can also record (or determine) the generation information corresponding to each picture (or each frame of the picture) in the multiple pictures. In the embodiment of the present disclosure, the server obtains the target picture based on the generation information corresponding to the picture to be identified, that is, the picture corresponding to the generation information that is the same as the generation information corresponding to the picture to be identified among the multiple pictures obtained by the server is determined as the target picture.

[0076] Exemplarily, assuming that the video frame represented by the generated information corresponding to the picture to be identified is the 10th frame among the multiple video frames, the server extracts the frame of the face video to be identified and determines the picture in the obtained 10th frame as the above-mentioned target picture.

[0077] S203. When the similarity between the target image and the image to be identified is greater than or equal to the similarity threshold, the server determines that the face video to be identified is the face video corresponding to the target account.

[0078] It should be understood that the server can determine the similarity between the target image and the image to be identified. When the similarity between the target image and the image to be identified is greater than or equal to the similarity threshold, it means that the similarity between the target image and the image to be identified is large, and the image to be identified does not have the risk of being tampered with. In this way, the server can determine that the face video to be identified is the face video corresponding to the target account (it can also be understood that the face video to be identified including the image to be identified is normal). Furthermore, the server can determine that the current account (specifically, the account that instructs the terminal to send the face video to be identified to the server) is a real account (ie, the target account), and issue corresponding access or operation permissions to the terminal (or the current account).

[0079] The technical solution provided by the above embodiment can at least bring the following beneficial effects: As can be seen from S201-S203, the server can receive the face video to be identified including the picture to be identified and the generation information corresponding to the picture to be identified sent by the terminal, and based on the generation information, the face video to be identified is subjected to frame extraction processing to obtain the target picture. Since the generation information corresponding to the picture to be identified is used to characterize the target video frame corresponding to the picture to be identified, the server can perform frame extraction processing on the face video to be identified to obtain the picture corresponding to the video frame identical to the target video frame from the multiple video frames corresponding to the face video to be identified (i.e., the target picture), and determine the similarity between the target picture and the picture to be identified. When the similarity is greater than or equal to the similarity threshold, it means that the similarity between the target picture and the picture to be identified is large, and the picture to be identified does not have the risk of being tampered with. In this way, the server can determine that the face video to be identified is the face video corresponding to the target account, which can improve the verification accuracy of the face video. Furthermore, when the facial video to be identified is the facial video corresponding to the target account, it means that the current account (specifically, the account that instructs the terminal to send the facial video to be identified to the server) is not a real account (i.e., the target account). In this way, the server can effectively verify whether the current account has any abnormal use of the real account, thereby improving the accuracy of account verification.

[0080] Combination Figure 4 ,like Figure 5 As shown, in one implementation of the embodiment of the present disclosure, the above-mentioned face video to be identified including the picture to be identified is obtained by the terminal adding target additional information to the face video to be identified, and the target additional information is one of the multiple additional information corresponding to the face video to be identified. The face video verification method provided by the embodiment of the present disclosure also includes S204.

[0081] S204: When the target attached information does not exist in the face video to be identified that includes the picture to be identified, the server determines that the face video to be identified is not the face video corresponding to the target account.

[0082] It is understandable that the face video to be identified sent by the terminal to the server includes the target attached information (specifically the picture to be identified) and the face video to be identified. When the target attached information does not exist in the face video to be identified including the picture to be identified sent by the server, it means that the face video to be identified is incomplete or may have been tampered with. In this way, the server can determine that the face video to be identified is not the face video corresponding to the target account, which can also be understood as the face video to be identified is abnormal.

[0083] The technical solution provided by the above embodiment can at least bring the following beneficial effects: As can be seen from S204, when the target additional information does not exist in the face video to be identified including the picture to be identified, it means that the face video to be identified is incomplete or the face video to be identified may have been tampered with, so the server can determine that the face video to be identified is not the face video corresponding to the target account. It can ensure that the server can verify the legitimacy of the account based on the complete face video to be identified, thereby improving the verification efficiency of the face video.

[0084] Combination Figure 4 ,like Figure 6 As shown, the face video verification method provided by the embodiment of the present disclosure also includes S205-S206.

[0085] S205: The server determines whether the target video frame belongs to multiple video frames corresponding to the face video to be recognized.

[0086] It should be understood that after the server receives the video of the face to be identified including the picture to be identified and the generation information corresponding to the picture to be identified sent by the terminal, it can determine whether the video frame represented by the generation information (that is, the target video frame corresponding to the picture to be identified) belongs to the multiple video frames (that is, the video frame corresponding to the video of the face to be identified).

[0087] S206: When the target video frame does not belong to the multiple video frames, the server determines that the generation information corresponding to the picture to be identified is abnormal.

[0088] It should be understood that when the target video frame does not belong to the multiple video frames, it means that the generated information is not the generated information corresponding to the multiple pictures corresponding to the face video to be identified (specifically the pictures in the multiple video frames). At this time, the server can determine that the generated information corresponding to the picture to be identified is abnormal.

[0089] Exemplarily, assuming that the video frame represented by the generated information is the 30th frame, and the above-mentioned face video to be identified corresponds to 25 video frames, the server determines that the target video frame does not belong to the multiple video frames.

[0090] The technical solution provided by the above embodiment can at least bring the following beneficial effects: as can be seen from S205-S206, the server can determine whether the target video frame belongs to the multiple video frames corresponding to the face video to be identified; when the target video frame does not belong to the multiple video frames, it means that the generation information corresponding to the picture to be identified is not the generation information corresponding to the picture in the multiple video frames corresponding to the face video to be identified (that is, the multiple pictures corresponding to the face video to be identified), so the server can determine that the generation information corresponding to the picture to be identified is abnormal, and can accurately determine whether the generation information corresponding to a certain picture received by the server is abnormal, thereby improving the verification accuracy of the face video.

[0091] Combination Figure 4 ,like Figure 7 As shown, the face video verification method provided by the embodiment of the present disclosure also includes S207.

[0092] S207: When the similarity between the target image and the image to be identified is less than the similarity threshold, the server determines that the face video to be identified is not the face video corresponding to the target account.

[0093] It should be understood that when the similarity between the target image and the image to be identified is less than the similarity threshold, it means that the similarity between the target image and the image to be identified is small. In the disclosed embodiment, when the similarity between the target image and the image to be identified is small, it means that the image to be identified is at risk of being tampered with, and the server can determine that the face video to be identified is not the face video corresponding to the target account.

[0094] Optionally, when the face video to be identified is not the face video corresponding to the target account, the server may determine that the face video to be identified including the picture to be identified is abnormal, specifically, the picture to be identified is abnormal.

[0095] It can be understood that when the video of the face to be identified including the picture to be identified is abnormal (specifically, the picture to be identified is abnormal), the server can determine that the current account is not a real account. In this way, the server can effectively verify that the current account has abnormal use of the real account, which can improve the accuracy of account verification.

[0096] The technical solution provided by the above embodiment can at least bring the following beneficial effects: As can be seen from S207, when the similarity between the target image and the image to be identified is less than the similarity threshold, it means that the similarity between the target image and the image to be identified is small, and the image to be identified is at risk of being tampered with. In this way, the server can determine that the face video to be identified is not the face video corresponding to the target account, which can improve the accuracy of face video verification. Furthermore, when the face video to be identified is not the face video corresponding to the target account, it means that the current account is not a real account. In this way, the server can effectively verify whether the current account has abnormal use of the real account, which can improve the accuracy of account verification.

[0097] like Figure 8 As shown, when the face video verification method is based on the interaction process between the terminal 101 and the server 102, the face video verification method may include S301-S307.

[0098] S301. The terminal obtains a video of a face to be recognized.

[0099] S302: The terminal determines generation information corresponding to the image to be identified.

[0100] Among them, the picture to be identified is one of multiple pictures, the multiple pictures are pictures in multiple video frames corresponding to the face video to be identified, the generated information is used to characterize the target video frame corresponding to the picture to be identified, and the picture to be identified includes the face area corresponding to the target account.

[0101] S303: The terminal adds the picture to be recognized to the video of the face to be recognized, and obtains the video of the face to be recognized including the picture to be recognized.

[0102] S304: The terminal sends a video of a face to be identified including a picture to be identified and generation information corresponding to the picture to be identified to the server.

[0103] S305: The server receives the face video to be identified including the picture to be identified and the generation information corresponding to the picture to be identified, which is sent by the terminal.

[0104] S306: The server extracts frames of the face video to be identified based on the generated information corresponding to the image to be identified to obtain a target image.

[0105] S307: When the similarity between the target image and the image to be identified is greater than or equal to the similarity threshold, the server determines that the face video to be identified is the face video corresponding to the target account.

[0106] It should be understood that the explanation of S301-S307 can be found in the description of the above embodiment and will not be repeated here.

[0107] The technical solution provided by the above embodiment can at least bring the following beneficial effects: As can be seen from S301-S307, the terminal can obtain the face video to be identified and determine the generation information corresponding to the picture to be identified; then the terminal adds the picture to be identified to the face video to be identified, obtains the face video to be identified including the picture to be identified, and sends the face video to be identified including the picture to be identified and the generation information to the server. In this way, the terminal can ensure that the server can obtain the face video to be identified, the picture to be identified, and the generation information of the generation time of the picture to be identified.

[0108] Furthermore, the server may receive a face video to be identified including a picture to be identified and generation information corresponding to the picture to be identified, sent by the terminal, and based on the generation information, perform frame extraction processing on the face video to be identified to obtain a target picture. Since the generation information corresponding to the picture to be identified is used to characterize the target video frame corresponding to the picture to be identified, the server can perform frame extraction processing on the face video to be identified to obtain a picture (i.e., target picture) corresponding to the same video frame as the target video frame from multiple video frames corresponding to the face video to be identified, and determine the similarity between the target picture and the picture to be identified. When the similarity is greater than or equal to the similarity threshold, it means that the similarity between the target picture and the picture to be identified is large, and the picture to be identified does not have the risk of being tampered with. In this way, the server can determine that the face video to be identified is the face video corresponding to the target account, which can improve the verification efficiency of the face video. Furthermore, when the facial video to be identified is the facial video corresponding to the target account, it means that the current account (specifically, the account that instructs the terminal to send the facial video to be identified to the server) is not a real account (i.e., the target account). In this way, the server can effectively verify whether the current account has any abnormal use of the real account, thereby improving the accuracy of account verification.

[0109] It can be understood that in actual implementation, the terminal / server described in the embodiment of the present disclosure may include one or more hardware structures and / or software modules for implementing the aforementioned verification method of the corresponding face video, and these execution hardware structures and / or software modules may constitute a terminal / server. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiment disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0110] Based on this understanding, the present disclosure also provides a face video verification device. Fig. 9 FIG. 1 is a schematic diagram showing the structure of a face video verification device provided by an embodiment of the present disclosure. Fig. 9 As shown, the face video verification device 40 may include: a receiving module 401, a processing module 402 and a determining module 403.

[0111] The receiving module 401 is configured to receive a video of a face to be identified including a picture to be identified and generation information corresponding to the picture to be identified, sent by a receiving terminal. The picture to be identified is one of multiple pictures, and the multiple pictures are pictures in multiple video frames corresponding to the video of the face to be identified. The generation information is used to characterize a target video frame corresponding to the picture to be identified, and the picture to be identified includes a face area corresponding to a target account.

[0112] The processing module 402 is configured to perform frame extraction processing on the face video to be identified based on the generated information to obtain a target image.

[0113] The determination module 403 is configured to determine that the face video to be identified is the face video corresponding to the target account when the similarity between the target image and the image to be identified is greater than or equal to a similarity threshold.

[0114] Optionally, the above-mentioned face video to be identified including the picture to be identified is obtained by the terminal adding target additional information to the face video to be identified, and the target additional information is one of multiple additional information corresponding to the face video to be identified.

[0115] The determination module 403 is further configured to determine that the face video to be identified is not the face video corresponding to the target account when the target attached information does not exist in the face video to be identified that includes the picture to be identified.

[0116] Optionally, the determination module 403 is further configured to determine whether the target video frame belongs to the multiple video frames.

[0117] The determination module 403 is further configured to determine that the generation information corresponding to the to-be-recognized picture is abnormal when the target video frame does not belong to the multiple video frames.

[0118] Optionally, the determination module 403 is further configured to determine that the face video to be identified is not the face video corresponding to the target account when the similarity between the target image and the image to be identified is less than the similarity threshold.

[0119] As described above, the embodiment of the present disclosure can divide the functional modules of the face video verification device according to the above method example. Among them, the above integrated modules can be implemented in the form of hardware or in the form of software functional modules. In addition, it should be noted that the division of modules in the embodiment of the present disclosure is schematic and is only a logical function division. There may be other division methods in actual implementation. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module.

[0120] Regarding the face video verification device in the above embodiment, the specific manner in which each module performs operations and the beneficial effects possessed have been described in detail in the aforementioned method embodiment and will not be repeated here.

[0121] Fig.10 FIG. 1 is a schematic diagram of another structure of a face video verification device provided by the present disclosure. Fig.10 The face video verification device 50 may include at least one processor 501 and a memory 503 for storing processor executable instructions. The processor 501 is configured to execute the instructions in the memory 503 to implement the face video verification method in the above embodiment.

[0122] In addition, the facial video verification device 50 may further include a communication bus 502 and at least one communication interface 504 .

[0123] The processor 501 may be a central processing unit (CPU), a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the disclosed solution.

[0124] Communication bus 502 may include a pathway for transmitting information between the above-mentioned components.

[0125] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0126] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may be independent and connected to the processing unit via a bus. The memory may also be integrated with the processing unit.

[0127] The memory 503 is used to store instructions for executing the solution of the present disclosure, and the execution is controlled by the processor 501. The processor 501 is used to execute the instructions stored in the memory 503, so as to realize the functions in the method of the present disclosure.

[0128] In a specific implementation, as an embodiment, the processor 501 may include one or more CPUs, such as Fig.10 CPU0 and CPU1 in.

[0129] In a specific implementation, as an embodiment, the face video verification device 50 may include multiple processors, such as Fig.10 501 and processor 507 in the embodiment of the present invention. Each of these processors may be a single-CPU processor or a multi-CPU processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0130] In a specific implementation, as an embodiment, the face video verification device 50 may further include an output device 505 and an input device 506. The output device 505 communicates with the processor 501 and may display information in a variety of ways. For example, the output device 505 may be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 506 communicates with the processor 501 and may accept user input in a variety of ways. For example, the input device 506 may be a mouse, a keyboard, a touch screen device, or a sensor device.

[0131] Fig.11 This is a structural example diagram of a face video verification device provided by the present disclosure. Fig.11 As shown, the face video verification device 60 may include: an acquisition module 601, a determination module 602, a processing module 603 and a sending module 604.

[0132] The acquisition module 601 is configured to acquire a video of a face to be recognized.

[0133] Determination module 602 is configured to determine generation information corresponding to a picture to be identified, where the picture to be identified is one of multiple pictures, and the multiple pictures are pictures in multiple video frames corresponding to the face video to be identified, and the generation information is used to characterize the target video frame corresponding to the picture to be identified, and the picture to be identified includes a face area corresponding to a target account.

[0134] The processing module 603 is configured to add the picture to be identified to the face video to be identified, so as to obtain the face video to be identified including the picture to be identified.

[0135] The sending module 604 is configured to send the face video to be identified including the picture to be identified and the generated information to the server.

[0136] Optionally, the processing module 603 is specifically configured to add the image to be identified to target additional information, where the target additional information is one of a plurality of additional information corresponding to the face video to be identified.

[0137] The processing module 603 is further specifically configured to add the target additional information to the face video to be identified, so as to obtain the face video to be identified including the picture to be identified.

[0138] Fig.12 FIG. 1 is a schematic diagram of another structure of a face video verification device provided by the present disclosure. Fig.12The face video verification device 70 may include at least one processor 701 and a memory 703 for storing processor executable instructions. The processor 701 is configured to execute instructions in the memory 703 to implement the face video verification method in the above embodiment.

[0139] In addition, the face video verification device 70 may also include a communication bus 702 and at least one communication interface 704 .

[0140] The processor 701 may be a CPU, a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the disclosed solution.

[0141] The communication bus 702 may include a pathway for transmitting information between the above-mentioned components.

[0142] The communication interface 704 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, RAN, WLAN, etc.

[0143] The memory 703 may be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or an EEPROM, a CD-ROM or other optical disk storage, an optical disk storage (including a compressed optical disk, a laser disk, an optical disk, a digital versatile disk, a Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may be independent and connected to the processing unit via a bus. The memory may also be integrated with the processing unit.

[0144] The memory 703 is used to store instructions for executing the solution of the present disclosure, and the execution is controlled by the processor 701. The processor 701 is used to execute the instructions stored in the memory 703, so as to realize the functions in the method of the present disclosure.

[0145] In a specific implementation, as an embodiment, the processor 701 may include one or more CPUs, such as Fig.12 CPU0 and CPU1 in.

[0146] In a specific implementation, as an embodiment, the face video verification device 70 may include multiple processors, such as Fig.12701 and processor 707 in the embodiment of the present invention. Each of these processors may be a single-CPU processor or a multi-CPU processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0147] In a specific implementation, as an embodiment, the face video verification device 70 may further include an output device 705 and an input device 706. The output device 705 communicates with the processor 701 and may display information in a variety of ways. For example, the output device 705 may be an LCD, LED display device, CRT display device, or a projector. The input device 706 communicates with the processor 701 and may receive user input in a variety of ways. For example, the input device 706 may be a mouse, a keyboard, a touch screen device, or a sensor device.

[0148] Those skilled in the art will appreciate that the above Fig.10 or Fig.12 The structure shown in does not constitute a limitation on the facial video verification device, and may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0149] In addition, the present disclosure also provides a computer-readable storage medium, including instructions, which, when executed by a device, enable the device to execute the facial video verification method provided in the above embodiment.

[0150] In addition, the present disclosure also provides a computer program product, including instructions, which, when executed by a device, enable the device to execute the face video verification method provided in the above embodiment.

[0151] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A face video verification method, applied to a server, characterized in that: include: A receiving terminal sends a picture to be identified, a video of a person to be identified including the picture to be identified, and generation information corresponding to the picture to be identified, wherein the picture to be identified is one of a plurality of pictures, and the plurality of pictures are pictures in a plurality of video frames corresponding to the video of the person to be identified, and the generation information is used to characterize a target video frame corresponding to the picture to be identified, and the picture to be identified includes a face area corresponding to a target account; the generation information is obtained by recording the frame sequence position of a video frame in a plurality of extracted video frames when extracting frames from the video of the person to be identified; the video of the person to be identified is used to characterize a process of liveness detection of a face of a target account; the video of the person to be identified including the picture to be identified is obtained by the terminal adding the picture to be identified to the video of the person to be identified; Based on the generated information, frame extraction is performed on the face video to be identified to obtain a target image; When the similarity between the target image and the image to be identified is greater than or equal to a similarity threshold, it is determined that the face video to be identified is the face video corresponding to the target account.

2. The face video verification method according to claim 1, characterized in that: The face video to be identified including the picture to be identified is obtained by the terminal adding target additional information to the face video to be identified, and the target additional information is one of a plurality of additional information corresponding to the face video to be identified, and the method further includes: When the target attached information does not exist in the face video to be identified that includes the picture to be identified, it is determined that the face video to be identified is not the face video corresponding to the target account.

3. The face video verification method according to claim 1, characterized in that: The method further comprises: determining whether the target video frame belongs to the plurality of video frames; When the target video frame does not belong to the multiple video frames, it is determined that the generated information corresponding to the picture to be identified is abnormal.

4. The face video verification method according to any one of claims 1 to 3, characterized in that: The method further comprises: When the similarity between the target image and the image to be identified is less than the similarity threshold, it is determined that the face video to be identified is not the face video corresponding to the target account.

5. A face video verification method, applied to a terminal, characterized in that: include: Get the face video to be recognized; Determine generation information corresponding to the image to be identified, the image to be identified is one of multiple images, the multiple images are images in multiple video frames corresponding to the face video to be identified, the generation information is used to characterize the target video frame corresponding to the image to be identified, the image to be identified includes the face area corresponding to the target account; the generation information is obtained by recording the frame sequence position of the video frame in the extracted multiple video frames when extracting the frame of the face video to be identified; the face video to be identified is used to characterize the process of face liveness detection of the target account; Adding the picture to be identified to the face video to be identified, to obtain the face video to be identified including the picture to be identified; The picture to be identified, the video of the face to be identified including the picture to be identified, and the generation information are sent to a server.

6. The face video verification method according to claim 5, characterized in that: The step of adding the image to be identified to the face video to be identified to obtain the face video to be identified including the image to be identified includes: Adding the image to be identified to target additional information, where the target additional information is one of a plurality of additional information corresponding to the face video to be identified; The target additional information is added to the face video to be identified, so as to obtain the face video to be identified including the picture to be identified.

7. A face video verification device, characterized in that: include: A receiving module, a processing module and a determining module; The receiving module is configured to receive a picture to be identified, a face video to be identified including the picture to be identified, and generation information corresponding to the picture to be identified, sent by a terminal, wherein the picture to be identified is one of a plurality of pictures, and the plurality of pictures are pictures in a plurality of video frames corresponding to the face video to be identified, and the generation information is used to characterize a target video frame corresponding to the picture to be identified, and the picture to be identified includes a face area corresponding to a target account; the generation information is obtained by recording the frame sequence position of a video frame in a plurality of extracted video frames when extracting frames from the face video to be identified; the face video to be identified is used to characterize a process of face liveness detection of a target account; the face video to be identified including the picture to be identified is obtained by the terminal adding the picture to be identified to the face video to be identified; The processing module is configured to perform frame extraction processing on the face video to be identified based on the generated information to obtain a target image; The determination module is configured to determine that the face video to be identified is the face video corresponding to the target account when the similarity between the target image and the image to be identified is greater than or equal to a similarity threshold.

8. The face video verification device according to claim 7, characterized in that: The face video to be identified including the picture to be identified is obtained by the terminal adding target additional information to the face video to be identified, and the target additional information is one of a plurality of additional information corresponding to the face video to be identified; The determination module is further configured to determine that the face video to be identified is not the face video corresponding to the target account when the target attached information does not exist in the face video to be identified that includes the picture to be identified.

9. The face video verification device according to claim 7, characterized in that: The determination module is further configured to determine whether the target video frame belongs to the multiple video frames; The determination module is further configured to determine that the generation information corresponding to the picture to be identified is abnormal when the target video frame does not belong to the multiple video frames.

10. The face video verification device according to any one of claims 7 to 9, characterized in that: The determination module is further configured to determine that the face video to be identified is not the face video corresponding to the target account when the similarity between the target image and the image to be identified is less than the similarity threshold.

11. A face video verification device, characterized in that: include: An acquisition module, a determination module, a processing module, and a sending module; The acquisition module is configured to acquire a video of a face to be recognized; The determination module is configured to determine the generation information corresponding to the image to be identified, the image to be identified is one of a plurality of images, the plurality of images are images in a plurality of video frames corresponding to the face video to be identified, the generation information is used to characterize the target video frame corresponding to the image to be identified, the image to be identified includes the face area corresponding to the target account; the generation information is obtained by recording the frame sequence position of the video frame in the extracted plurality of video frames when extracting the frame of the face video to be identified; the face video to be identified is used to characterize the process of face liveness detection of the target account; The processing module is configured to add the picture to be identified to the face video to be identified, so as to obtain the face video to be identified including the picture to be identified; The sending module is configured to send the picture to be identified, the face video to be identified including the picture to be identified, and the generation information to the server.

12. The face video verification device according to claim 11, characterized in that: The processing module is specifically configured to add the image to be identified to target additional information, where the target additional information is one of a plurality of additional information corresponding to the face video to be identified; The processing module is further specifically configured to add the target additional information to the face video to be identified, so as to obtain the face video to be identified including the picture to be identified.

13. A face video verification system, characterized in that: The face video verification system includes a server and a terminal; The server is used to execute the face video verification method described in any one of claims 1 to 4 above; The terminal is used to execute the facial video verification method described in claim 5 or 6 above.

14. A server, characterized in that: The server comprises: processor; a memory configured to store instructions executable by the processor; The processor is configured to execute the instruction to implement the face video verification method as described in any one of claims 1-4.

15. A terminal, characterized in that: The terminal comprises: processor; a memory configured to store instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the facial video verification method as described in claim 5 or 6.

16. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions in the computer-readable storage medium are executed by a device, the device is enabled to execute the facial video verification method as described in any one of claims 1 to 4 or the facial video verification method as described in claim 5 or 6.

17. A computer program product, characterized in that The computer program product includes computer instructions, and when the computer instructions are executed on a device, the device executes the facial video verification method as described in any one of claims 1 to 4, or executes the facial video verification method as described in claim 5 or 6.

Images