Method for secure processing of user images, terminal, server, system and medium

Abstract

The application discloses a kind of security processing method of user image, terminal, server, system and medium, belong to image processing field.The method includes: first fragment image with the same resolution as the resolution of the collected face image is randomly generated and stored;According to the pixel operation of the collected face image and the first fragment image, the second fragment image is obtained;The collected face image and the second fragment image are sent to the server, so that the server uses the collected face image to carry out face recognition service, discards the collected face image after face recognition service ends, and stores the second fragment image.According to the embodiment of the application, the security of face image use can be improved.

Description

Technical Field

[0001] This application belongs to the field of image processing, and in particular relates to a method, terminal, server, system and medium for secure processing of user images. Background Technology

[0002] With the development of electronic information technology, the application scope of facial recognition technology is constantly expanding. Facial recognition requires the collection of users' facial images, and facial images have a very high security level, requiring higher storage standards compared to other data. From an information security perspective, collected facial images are, in principle, not stored, even encrypted ones. However, in scenarios such as payment, check-in, and access control, misidentification of facial images may occur, leading to user complaints. If the collected facial images are not stored, it becomes difficult to analyze these misidentifications. Therefore, there is an urgent need for an image processing method that can guarantee the security of facial images. Summary of the Invention

[0003] This application provides a method, terminal, server, system, and medium for secure processing of user images, which can improve the security of using facial images.

[0004] In a first aspect, embodiments of this application provide a secure processing method for user images, applied to a recognition terminal. The method includes: randomly generating and storing a first fragment image with the same resolution as the acquired face image; performing pixel calculations based on the acquired face image and the first fragment image to obtain a second fragment image; sending the acquired face image and the second fragment image to a server so that the server can use the acquired face image to perform face recognition services; discarding the acquired face image and storing the second fragment image after the face recognition service is completed.

[0005] Secondly, embodiments of this application provide a secure processing method for user images, applied to a server. The method includes: receiving a collected face image and a second fragment image sent by a recognition terminal; the second fragment image is obtained by pixel calculation based on the collected face image and the first fragment image; the first fragment image is randomly generated and stored in the recognition terminal; the resolution of the first fragment image is the same as the resolution of the collected face image; performing face recognition services using the collected face image; discarding the collected face image and storing the second fragment image after the face recognition service is completed.

[0006] Thirdly, embodiments of this application provide a recognition terminal, comprising: a first image generation module, configured to randomly generate and store a first fragment image with the same resolution as the acquired face image; a second image generation module, configured to perform pixel calculations based on the acquired face image and the first fragment image to obtain a second fragment image; and a sending module, configured to send the acquired face image and the second fragment image to a server, so that the server can use the acquired face image to perform face recognition services, discard the acquired face image after the face recognition service is completed, and store the second fragment image.

[0007] Fourthly, embodiments of this application provide a server, comprising: a receiving module, configured to receive a collected face image and a second fragment image sent by a recognition terminal, wherein the second fragment image is obtained by pixel calculation based on the collected face image and the first fragment image, the first fragment image is randomly generated and stored in the recognition terminal, and the resolution of the first fragment image is the same as the resolution of the collected face image; a processing module, configured to perform face recognition services using the collected face image, and discard the collected face image after the face recognition service is completed; and a storage module, configured to store the second fragment image.

[0008] Fifthly, embodiments of this application provide an identification terminal, including: a processor and a memory storing computer program instructions; the processor executes the computer program instructions to implement the user image security processing method of the first aspect.

[0009] In a sixth aspect, embodiments of this application provide a server, including: a processor and a memory storing computer program instructions; the processor executes the computer program instructions to implement the user image security processing method of the second aspect.

[0010] In a seventh aspect, embodiments of this application provide a secure image processing system for users, comprising: a recognition terminal as described in the fifth aspect; and a server as described in the sixth aspect.

[0011] Eighthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the user image security processing method of the first aspect or the user image security processing method of the second aspect.

[0012] This application provides a secure processing method, terminal, server, system, and medium for user images. The recognition terminal can randomly generate a first fragment image with the same resolution as the acquired face image. A second fragment image is obtained through pixel operations between the face image and the first fragment image. The first fragment image is stored in the recognition terminal, and the second fragment image is stored in the server. Neither the recognition terminal nor the server stores the acquired face image. If the recognition terminal is attacked, the first fragment image is leaked. Since the first fragment image contains zero information about the acquired face image, the attacker cannot obtain the face image from the first fragment image. If the server is attacked, the second fragment image is leaked. Since the second fragment image does not contain any information about the acquired face image, the attacker cannot obtain the face image from the second fragment image. However, when user authorization is obtained to reconstruct the face image, the first and second fragment images can be legally obtained, and the originally acquired face image can be reconstructed from the first and second fragment images, satisfying the face image acquisition requirements and improving the security of face image usage. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 A schematic diagram of the architecture of an example of a user image security processing system provided in an embodiment of this application;

[0015] Figure 2 A flowchart illustrating a secure processing method for user images provided in the first aspect of this application;

[0016] Figure 3 A schematic diagram of an example of a first fragment image provided in an embodiment of this application.

[0017] Figure 4 A schematic diagram illustrating an example of a second fragment image provided in an embodiment of this application;

[0018] Figure 5 A flowchart illustrating a method for securely processing user images provided in another embodiment of the first aspect of this application;

[0019] Figure 6 A schematic diagram illustrating an example of a patch image provided in an embodiment of this application;

[0020] Figure 7 A schematic diagram illustrating an example of a restored image based on incomplete information, provided in an embodiment of this application;

[0021] Figure 8 A schematic diagram of another example of a patch image provided for an embodiment of this application;

[0022] Figure 9 A schematic diagram illustrating another example of a restored image based on incomplete information provided in an embodiment of this application;

[0023] Figure 10 A flowchart of a user image security processing method provided in yet another embodiment of the first aspect of this application;

[0024] Figure 11 A flowchart illustrating a method for securely processing user images provided in an embodiment of the second aspect of this application;

[0025] Figure 12 A flowchart illustrating a method for securely processing user images provided in another embodiment of the second aspect of this application;

[0026] Figure 13 This is a schematic diagram of the structure of an identification terminal provided in an embodiment of the third aspect of this application;

[0027] Figure 14 This is a schematic diagram of the structure of a server provided in an embodiment of the fourth aspect of this application;

[0028] Figure 15 This is a schematic diagram of the structure of an identification terminal provided in an embodiment of the fifth aspect of this application. Detailed Implementation

[0029] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples. It should be noted that the acquisition, storage, use, and processing of information and data in the embodiments of this application are all authorized by users or relevant organizations and comply with the relevant provisions of national laws and regulations.

[0030] With the development of electronic information technology, the application scope of facial recognition technology is constantly expanding. Facial recognition requires the collection of users' facial images, and facial images have a very high security level, requiring higher storage standards compared to other data. From an information security perspective, collected facial images are, in principle, not stored, even encrypted ones. However, in scenarios such as payment, check-in, and access control, misidentification of facial images may occur, leading to user complaints. If the collected facial images are not stored, it becomes difficult to analyze these misidentifications. Therefore, there is an urgent need for an image processing method that can guarantee the security of facial images.

[0031] This application provides a secure processing method, terminal, server, system, and medium for user images. Based on secret sharing, it stores a randomly generated fragmented image on the recognition terminal side and another fragmented image generated based on this fragmented image and a captured face image on the server side. Neither the recognition terminal nor the server side stores the captured face image. Neither of the two fragmented images contains specific information about the captured face image. Even if the data on either the recognition terminal or the server is compromised, an attacker cannot obtain the original captured face image from the individual fragmented images, thus ensuring the security of the captured face image. However, if it is necessary to obtain the captured face image, both fragmented images can be obtained with user authorization, and the original captured face image can be reconstructed from the two fragmented images.

[0032] For ease of explanation, we will first briefly describe the system architecture involved in the user image security processing method. Figure 1 A schematic diagram of the architecture of an example user image security processing system provided in an embodiment of this application is shown below. Figure 1 As shown, the user image security processing system includes an identification terminal 11 and a server 12.

[0033] The recognition terminal 11 is communicatively connected to the server 12. The recognition terminal 11 can capture the user's facial image and upload it to the server 12, whereby the server 12 performs facial recognition services based on the image. Facial recognition services may include, but are not limited to, payment, access control, and attendance tracking. The recognition terminal 11 can be a terminal device installed in public areas or a personal terminal device; there is no limitation on this. The user image security processing system may include one recognition terminal 11 or two or more terminal devices 11; there is no limitation on this.

[0034] Server 12 can receive facial images sent by recognition terminal 11 and perform facial recognition services based on the facial images. In this embodiment, after the facial recognition service ends, server 12 can discard or delete the facial images sent by server 12, and will not store the facial images sent by recognition terminal 11 for a long time, so that the storage of facial images meets the requirements of information security. The user image security processing system may include one server 12, or it may include two or more servers 12, which is not limited here.

[0035] The following describes the user image security processing method, terminal, server, system, and medium provided in this application.

[0036] The first aspect of this application provides a secure processing method for user images, which can be applied to an identification terminal, i.e., the secure processing method for user images can be executed by the identification terminal. Figure 2 A flowchart of a user image security processing method provided in the first aspect of this application is shown below. Figure 2 As shown, the secure processing method for user images may include steps S201 to S203.

[0037] In step S201, a first fragment image with the same resolution as the acquired face image is randomly generated and stored.

[0038] In response to user input, the recognition terminal initiates a face recognition service, which may include specific functions such as face image registration and face recognition. The user image security processing method in this embodiment can be applied to various scenarios of face recognition services. When initiating a face recognition service, the recognition terminal acquires the user's face image. The recognition terminal can also randomly generate a first fragment image with the same resolution as the acquired face image. For example, if the resolution of the acquired face image is 640*480*3, then the resolution of the randomly generated first fragment image is also 640*480*3, where 640 and 480 are the number of pixels in the horizontal and vertical directions, respectively, and 3 is the number of color channels per pixel. The pixel value of each pixel in the first fragment image can be independently and randomly generated, with a value range of 0 to 255. The first fragment image contains zero information about the acquired face image. For example... Figure 3 A schematic diagram illustrating an example of a first fragment image provided in an embodiment of this application, such as... Figure 3 As shown, the captured face image cannot be obtained from the first fragment image. It should be noted that... Figure 3 For ease of demonstration, grayscale processing is used; in reality, the first fragment image could be a color image.

[0039] In step S202, pixel calculations are performed based on the acquired face image and the first fragment image to obtain the second fragment image.

[0040] The pixel values ​​of the pixels in the acquired face image are compared with those in the first fragment image to obtain the pixel values ​​of the pixels in the second fragment image. The resolution of the second fragment image is the same as that of the acquired face image and the first fragment image. The pixel value of each pixel in the second fragment image is calculated based on the pixel values ​​of the pixels at the same position in the acquired face image and the pixels at the same position in the first fragment image. The pixel values ​​in the second fragment image range from 0 to 255.

[0041] Pixel operations can include one or more algorithms such as pixel value addition and subtraction. Pixel operations can also include other types of algorithms, which are not limited here. By selecting the appropriate pixel operation algorithm, the amount of information about the captured face image contained in the second fragment image can be reduced. In some examples, the amount of information about the captured face image contained in the second fragment image can be 0, that is, the probability distribution of pixel values ​​in the second fragment image within the range of 0 to 255 is completely unrelated to the captured face image. For example, Figure 4 A schematic diagram illustrating an example of a second fragment image provided in an embodiment of this application, such as... Figure 4 As shown, the captured face image cannot be obtained from the second fragment image. It should be noted that... Figure 4 For ease of demonstration, grayscale processing is used; in reality, the second fragment image could be a color image.

[0042] In step S203, the collected face image and the second fragment image are sent to the server so that the server can use the collected face image to perform face recognition. After the face recognition is completed, the collected face image is discarded and the second fragment image is stored.

[0043] The collected facial images are used by the server for facial recognition. It should be noted that the server does not retain the collected facial images after the facial recognition process is completed, to meet information security requirements. However, the server stores a second fragment image. This second fragment image does not contain information about the collected facial image; the collected facial image cannot be obtained solely from the second fragment image, thus improving the security of the facial image. However, if it is necessary to reconstruct the collected facial image and the user has authorized it, the collected facial image can be reconstructed from the first and second fragment images.

[0044] In this embodiment, the recognition terminal can randomly generate a first fragment image with the same resolution as the acquired face image. A second fragment image is obtained through pixel-wise operations between the face image and the first fragment image. The first fragment image is stored in the recognition terminal, and the second fragment image is stored in the server. Neither the recognition terminal nor the server stores the acquired face image. If the recognition terminal is attacked, the first fragment image is leaked. Since the first fragment image contains zero information about the acquired face image, the attacker cannot obtain the face image from the first fragment image. If the server is attacked, the second fragment image is leaked. Since the second fragment image does not contain any information about the acquired face image, the attacker cannot obtain the face image from the second fragment image. However, when user authorization is obtained to reconstruct the face image, the first and second fragment images can be legally obtained. The original acquired face image can then be reconstructed from the first and second fragment images, satisfying the face image acquisition requirements and improving the security of the acquired face image usage.

[0045] In some embodiments, pixel operations, including subtraction and addition of pixel values, can be used to make the information of the captured face image contained in the second fragment image zero, thereby further improving the security of face image use. Figure 5 A flowchart illustrating a method for securely processing user images according to another embodiment of the first aspect of this application. Figure 5 and Figure 2 The difference is that, Figure 2 Step S202 can be further refined as follows: Figure 5 Steps S2021 to S2023 in the process.

[0046] In step S2021, the first difference between the pixel value of the pixel in the acquired face image and the pixel value of the pixel in the first fragment image is calculated.

[0047] The difference between pixel values ​​calculated here refers to the difference between pixel values ​​at the same position in the face image and the first fragment image. For example, the difference between the pixel value of the first row and first column of the captured face image and the pixel value of the first row and first column of the first fragment image is a first difference. The first difference includes the difference between the pixel values ​​of the captured face image and the pixel values ​​of the first fragment image.

[0048] In step S2022, if the first difference is less than 0, the first sum of the first difference and 256 is calculated.

[0049] Since the pixel values ​​in the first fragment image are randomly generated, the first difference corresponding to a pixel may be greater than or equal to 0, or it may be less than 0. To ensure that the pixel values ​​in the second fragment image obtained through pixel processing fall within a certain range (e.g., 0 to 255), and to ensure that the probability distribution of pixel values ​​in the second fragment image within the range of 0 to 255 is completely independent of the acquired face image, the first difference less than 0 can be further processed to obtain values ​​that can be used as pixel values ​​in the second fragment image. The first sum can be calculated by adding the first difference less than 0 to 256, and this first sum is greater than or equal to 0. 256 represents the upper limit of the pixel value range plus one, i.e., the number of integer values ​​that a pixel value can take. Adding the first difference less than 0 to 256 yields the pixel values ​​falling within the range of 0 to 255.

[0050] In step S2023, a second fragment image is obtained based on the first sum and the first difference greater than or equal to 0.

[0051] In some cases, the first difference between the first sum and the first difference greater than or equal to 0 can be determined as the pixel value of the corresponding pixel in the second fragment image, thus obtaining the second fragment image. If the first difference corresponding to a pixel at a certain position is greater than or equal to 0, then the first difference greater than or equal to 0 is taken as the pixel value of the pixel at that position in the second fragment image; if the first difference corresponding to a pixel at a certain position is less than 0, then the first sum corresponding to the pixel at that position is taken as the pixel value of the pixel at that position in the second fragment image.

[0052] In some examples, different first fragment images correspond to different captured face images. This avoids the situation where multiple captured face images can be reconstructed from the same first fragment image and multiple second fragment images, further reducing the possibility of face image reconstruction due to leakage of the first fragment image. Generating different first fragment images for different captured face images is more suitable for scenarios where the number of face recognition operations within a cycle is relatively small.

[0053] In scenarios with a large number of facial recognition transactions within a given period, generating different first fragment images for different collected facial images increases the storage pressure on the recognition terminal. For example, if the facial image reconstruction requirement, such as a customer complaint, occurs over a period of one month, the recognition terminal needs to store the first fragment images corresponding to the facial images collected within that month. If the resolution of the first fragment image is 640*480*3, and 10,000 facial recognition transactions occur within a month, the storage space occupied by the first fragment images corresponding to these 10,000 facial recognition transactions can reach 9GB. For some recognition terminals, this storage pressure is unbearable.

[0054] To reduce the storage pressure on the recognition terminal, face images collected every N times can be divided into image groups. Face images within the same image group share the same first fragment image, while face images in different image groups correspond to different first fragment images, where N is an integer greater than 1. By dividing the image groups, the number of first fragment images that the recognition terminal needs to store can be reduced, thus lowering the storage pressure on the terminal. For example, if N=100, and 10,000 face recognition transactions occur in a month, without dividing the image groups, the recognition terminal would need to store 10,000 first fragment images. However, by dividing the image groups according to N=100, the recognition terminal only needs to store 100 first fragment images, occupying only one percent of the original required storage space, significantly reducing the storage pressure on the recognition terminal.

[0055] However, if the first fragment image corresponding to the facial images captured in the same image group is the same, obtaining the first fragment image and the corresponding second fragment image of the image group can reconstruct all facial images in that image group. For example, a user initiating a customer complaint can authorize the sending of their corresponding first fragment image to the server. Server-side maintenance personnel can use this first fragment image and the second fragment image stored on the server to reconstruct the facial images of an image group. To further improve the security of facial image usage and reduce the possibility of reconstructing other users' facial images while reconstructing one user's facial image, patch images can be introduced, allowing the patch images to participate in the generation process of the second fragment image.

[0056] Specifically, when every N captured face images are divided into an image group, and the first fragment image corresponding to the captured face images in the same image group is the same, the above step S2023 can be further refined as follows: Obtain a pre-generated patch image corresponding to the captured face image; determine the first difference (greater than or equal to 0) as the pixel value of the corresponding pixel in the intermediate image, thus obtaining the intermediate image; divide the intermediate image into multiple image blocks of the same size as the patch image; perform pixel operations based on the pixel values ​​of the pixels in the image blocks and the pixel values ​​of the pixels in the patch image to obtain the second fragment image. The pixel values ​​of the pixels in the patch image are randomly generated, and different captured face images correspond to different patch images. The patch image is stored in the recognition terminal. The size of the patch image is smaller than the size of the second fragment image. The shape of the patch image includes, but is not limited to, a rectangle. The size and shape of the patch image can be set according to the storage pressure requirements of the recognition terminal and the restoration requirements of the face images in the same image group that do not need to be restored, and are not limited here. For example, the patch image can be 1 / 16 × 1 / 16 of the face image. First, an intermediate image is generated using the first sum and first difference (greater than or equal to 0) of the pixels at each position in the above embodiments. If the first difference of a pixel at a certain position is greater than or equal to 0, then the first difference greater than or equal to 0 is used as the pixel value of that pixel at that position in the intermediate image; if the first difference of a pixel at a certain position is less than 0, then the first sum of the pixels at that position is used as the pixel value of that pixel at that position in the intermediate image. The intermediate image is divided into multiple image blocks, the size of which is the same as the size of the patch image. If the size of the intermediate image is insufficient to divide it into an integer number of image blocks, images can be added to the edges of the intermediate image so that the size of the supplemented intermediate image can be divided into an integer number of image blocks. The pixel values ​​of the supplemented images can be generated randomly or according to a certain rule, which is not limited here. The supplemented images have no practical meaning and are unrelated to the face image. The pixel operations between the pixel values ​​of the pixels in the image block and the pixel values ​​of the pixels in the patch image can include one or more of the following operations: subtraction, addition, etc., or other types of operations. For example, a second difference can be calculated between the pixel values ​​of a pixel in the image patch and the pixel values ​​of a pixel in the patch image. If the second difference is less than 0, a second sum of the second difference and 256 is calculated. Based on the second sum and the second difference greater than or equal to 0, the second fragment image is obtained. Specifically, if the second difference corresponding to a pixel at a certain position is greater than or equal to 0, then the second difference greater than or equal to 0 is taken as the pixel value of the pixel at that position in the second fragment image; if the second difference corresponding to a pixel at a certain position is less than 0, then the second sum corresponding to the pixel at that position is taken as the pixel value of the pixel at that position in the second fragment image, thus obtaining the second fragment image.The second fragment image obtained in this way contains zero information about the captured face image. Furthermore, even if the first and second fragment images are obtained, but no patch image corresponding to the first fragment image is obtained, the original captured face image cannot be reconstructed. For the same image group, based on the first fragment image corresponding to that image group, the patch image corresponding to a face image in that image group, and the second fragment image corresponding to that face image, only that face image can be reconstructed; other face images in that image group cannot be reconstructed. This significantly reduces the possibility of all face images in an image group being reconstructed during an attack.

[0057] The larger the patch image size, the greater the storage pressure on the recognition terminal, and the lower the degree of reconstruction of the face image B1 corresponding to patch image A1 in the same image group by the first fragment image and patch image A2. Similarly, the smaller the storage size of the patch image, the less the storage pressure on the recognition terminal, and the higher the degree of reconstruction of the face image B1 corresponding to patch image A1 in the same image group by the first fragment image and patch image A2. The size of the patch image can be determined based on the actual storage pressure requirements of the recognition terminal and the required degree of reconstruction of other face images in the same image group by the first fragment image and patch image corresponding to a single face image.

[0058] For example, Figure 6 This is a schematic diagram illustrating an example of a patch image provided in an embodiment of this application. Figure 7 This is a schematic diagram illustrating an example of a reconstructed image based on incomplete information, provided in an embodiment of this application. Figure 8 This is a schematic diagram illustrating another example of a patch image provided in an embodiment of this application. Figure 9 This is a schematic diagram of another example of a restored image based on incomplete information provided in an embodiment of this application. Figure 7 The restored image shown is based on the first fragment image, Figure 6 The patch image and the image group corresponding to the first fragment image in the image are not Figure 6 The patch image is obtained by reconstructing a second fragment image corresponding to the patch image. Figure 9 The restored image shown is based on the first fragment image, Figure 8 The patch image and the image group corresponding to the first fragment image in the image are not Figure 8 The patch image is reconstructed from a second fragment image corresponding to the patch image. Figure 7 and Figure 9 Therefore, the image reconstructed from a patch image that is not the face image itself is different from the face image and cannot obtain accurate information about the actual face image. Even if the attacker obtains the patch image of face image A1 in the image group, the first fragment image corresponding to the image group, and the second fragment image corresponding to another face image A2 in the image group, they cannot reconstruct face image A2.

[0059] in, Figure 6 The patch image shown is larger than Figure 8 The dimensions of the patch image shown are, i.e. Figure 6 The patch image shown contains more than [number of pixels]. Figure 8 The patch image shown contains the number of pixels; this is for ease of processing. Figure 6 and Figure 8 The patch image shown is a grayscale image; in reality, the patch image can be a color image. Figure 7 and Figure 9 It can be seen that the larger the size of the patch image, the lower the restoration degree of the N-1 face images corresponding to the patch images other than the patch image in the image group including N captured face images, and the higher the security of other face images in the image group. However, correspondingly, the storage space required for the recognition terminal to store the patch image is also larger.

[0060] To illustrate the security of face image usage in the embodiments of this application, Table 1 below describes the security of face image usage in various attack scenarios for the recognition terminal and server.

[0061] Table 1

[0062]

[0063]

[0064] As shown in Table 1, the security of using face images can be greatly improved by adopting the user image security processing method in the embodiments of this application.

[0065] In some embodiments, when it is necessary to restore a face image, such as when a face recognition service misidentifies a face and a customer files a complaint, the recognition terminal may, with the user's authorization, send the information required to restore the face image to the server, so that the server can restore the face image and perform relevant analysis. Figure 10 A flowchart illustrating a user image security processing method provided in another embodiment of the first aspect of this application. Figure 10 and Figure 2 The difference is that, Figure 9 The method for securely processing user images may further include step S204.

[0066] In step S204, in response to the user's authentication and authorization input, image reconstruction information is sent to the server so that the server can reconstruct the acquired face image based on the image reconstruction information and the second fragment image.

[0067] The server can receive image reconstruction requests from users, which may include customer complaints or other requests. Based on the image reconstruction request, the server can locate the corresponding facial recognition service, such as payment, access control, or attendance tracking, and push an authorization request to the user. The user can then input authentication authorization information into the recognition terminal, authorizing the terminal to provide image reconstruction information to the server.

[0068] The image reconstruction information includes a first fragment image. The server can perform the inverse operation of the pixel operations described in the above embodiments based on the image reconstruction information and the second fragment image, thereby reconstructing the acquired face image.

[0069] The server can calculate the third sum of the pixel values ​​of the pixels in the second fragment image and the pixel values ​​of the pixels in the first fragment image. If the third sum is greater than or equal to 256, the server can calculate the third difference between the third sum and 256. Based on the third difference and the third sum which is less than 256, the server can reconstruct the face image.

[0070] In some examples, if the pixel values ​​of the pixels in the second fragment image include the first sum and a first difference greater than or equal to 0 as described in the above embodiments, correspondingly, the pixel values ​​of the pixels in the reconstructed face image include a third difference and a third sum less than 256. Specifically, if the third sum corresponding to a pixel at a certain position is less than 256, then the third sum less than 256 is used as the pixel value of the pixel at that position in the reconstructed face image; if the third sum corresponding to a pixel at a certain position is greater than or equal to 256, then the third difference corresponding to the pixel at that position is used as the pixel value of the pixel at that position in the reconstructed face image, thereby reconstructing the face image.

[0071] In some examples, the image reconstruction information also includes the patch image. The server can calculate the third sum of the pixel values ​​and the fourth sum of the pixel values ​​in the patch image. If the fourth sum is greater than or equal to 256, the server calculates the fourth difference between the fourth sum and 256. Based on the fourth difference and the fourth sum which is less than 256, the face image is reconstructed.

[0072] If the pixel values ​​of the pixels in the second fragment image include the second sum and the second difference greater than or equal to 0 as described in the above embodiment, then the pixel values ​​of the pixels in the reconstructed face image include the fourth difference and the fourth sum less than 256. Specifically, if the fourth sum corresponding to a pixel at a certain position is less than 256, then the fourth sum less than 256 is used as the pixel value of the pixel at that position in the reconstructed face image; if the fourth sum corresponding to a pixel at a certain position is greater than or equal to 256, then the fourth difference corresponding to the pixel at that position is used as the pixel value of the pixel at that position in the reconstructed face image, thereby reconstructing the face image.

[0073] The user image security processing method in the above embodiments can restore only the facial images of customers who require image restoration, and supports a delay of one cycle between the image restoration request and the facial recognition service. This cycle can be set according to the scenario, requirements, experience, etc., and is not limited here. Facial images cannot be obtained without user authorization and authorization from server-side maintenance or management personnel. Even if all data on the recognition terminal side or the server side is completely extracted, the collected facial images will not be leaked. Moreover, compared with traditional cryptographic schemes, i.e., facial image encryption schemes, the user image security processing method in this application embodiment does not pose a security risk to the use of facial images even if the algorithm details are disclosed, even if both the data on the recognition terminal side and the data on the server side are leaked simultaneously.

[0074] The second aspect of this application provides a method for securely processing user images, applied to a server, meaning that the method for securely processing user images can be executed by the server. Figure 11 A flowchart of a user image security processing method provided in an embodiment of the second aspect of this application is shown below. Figure 11 As shown, the secure processing method for user images may include steps S301 and S302.

[0075] In step S301, the collected face image and second fragment image are received from the recognition terminal.

[0076] The second fragment image is obtained by performing pixel calculations based on the acquired face image and the first fragment image. The first fragment image is randomly generated and stored in the recognition terminal; in some examples, the first fragment image is randomly generated when a face recognition service is initiated. The resolution of the first fragment image is the same as the resolution of the acquired face image.

[0077] In step S302, the collected face image is used for face recognition. After the face recognition is completed, the collected face image is discarded and the second fragment image is stored.

[0078] The specific details of steps S301 to S302 can be found in the relevant descriptions in the above embodiments, and will not be repeated here.

[0079] In this embodiment, the recognition terminal can randomly generate a first fragment image with the same resolution as the acquired face image. A second fragment image is obtained through pixel-wise operations between the face image and the first fragment image. The second fragment image and the face image are then sent to the server. The first fragment image is stored in the recognition terminal, and the second fragment image is stored on the server. Neither the recognition terminal nor the server stores the acquired face image. If the recognition terminal is attacked, the first fragment image is leaked. Since the first fragment image contains zero information about the acquired face image, the attacker cannot obtain the face image from the first fragment image. If the server is attacked, the second fragment image is leaked. Since the second fragment image does not contain any information about the acquired face image, the attacker cannot obtain the face image from the second fragment image. However, when user authorization is obtained to reconstruct the face image, the first and second fragment images can be legally obtained. The original acquired face image can then be reconstructed from the first and second fragment images, satisfying the face image acquisition requirements and improving the security of the acquired face image usage.

[0080] In some embodiments, the second fragment image is obtained based on a first sum and a first difference greater than or equal to 0, wherein the first difference is the difference between the pixel value of a pixel in the acquired face image and the pixel value of a pixel in the first fragment image, and the first sum is the sum of the first difference less than 0 and 256.

[0081] In some examples, the pixel values ​​of pixels in the second fragment image include a first summation and a first difference greater than or equal to 0 corresponding to the pixel.

[0082] In some embodiments, different first fragment images correspond to different acquired face images. Alternatively, face images acquired every N times are divided into an image group, with the first fragment images corresponding to the face images acquired in the same image group being the same, and the first fragment images corresponding to the face images acquired in different image groups being different, where N is an integer greater than 1.

[0083] In some examples, every N captured face images are divided into an image group, and the first fragment image corresponding to the face images captured in the same image group is the same.

[0084] The pixel values ​​of the second fragment image are obtained by performing pixel operations on the pixel values ​​of the pixels in the image block and the pixel values ​​of the pixels in the patch image. The image block is obtained by dividing the intermediate image, and the size of the image block is the same as the size of the patch image. The pixel values ​​of the pixels in the intermediate image include the first sum and the first difference greater than or equal to 0 corresponding to the pixel. The patch image is randomly generated in advance and its size is smaller than the size of the second fragment image.

[0085] Figure 12A flowchart illustrating a user image security processing method provided in another embodiment of the second aspect of this application. Figure 12 and Figure 11 The difference is that, Figure 12 The method for securely processing user images also includes steps S303 and S304.

[0086] In step S303, the image reconstruction information sent by the identification terminal in response to the user's identity authentication authorization input is received.

[0087] The image reconstruction information includes the first fragment image.

[0088] In some examples, the image restoration information also includes patch images.

[0089] In step S304, the inverse operation of pixel operation is performed based on the image restoration information and the second fragment image to restore the acquired face image.

[0090] The specific details of steps S303 and S304 can be found in the relevant descriptions in the above embodiments, and will not be repeated here.

[0091] A third aspect of this application provides an identification terminal. Figure 13 This is a schematic diagram of the structure of an identification terminal provided in an embodiment of the third aspect of this application, as shown below. Figure 13 As shown, the identification terminal 400 may include a first image generation module 401, a second image generation module 402, and a transmission module 403.

[0092] The first image generation module 401 can be used to randomly generate and store a first fragment image with the same resolution as the acquired face image.

[0093] The second image generation module 402 can be used to perform pixel calculations based on the acquired face image and the first fragment image to obtain the second fragment image.

[0094] The sending module 403 can be used to send the collected face image and the second fragment image to the server so that the server can use the collected face image to perform face recognition service. After the face recognition service is completed, the collected face image is discarded and the second fragment image is stored.

[0095] In this embodiment, the recognition terminal can randomly generate a first fragment image with the same resolution as the acquired face image. A second fragment image is obtained through pixel-wise operations between the face image and the first fragment image. The first fragment image is stored in the recognition terminal, and the second fragment image is stored in the server. Neither the recognition terminal nor the server stores the acquired face image. If the recognition terminal is attacked, the first fragment image is leaked. Since the first fragment image contains zero information about the acquired face image, the attacker cannot obtain the face image from the first fragment image. If the server is attacked, the second fragment image is leaked. Since the second fragment image does not contain any information about the acquired face image, the attacker cannot obtain the face image from the second fragment image. However, when user authorization is obtained to reconstruct the face image, the first and second fragment images can be legally obtained. The original acquired face image can then be reconstructed from the first and second fragment images, satisfying the face image acquisition requirements and improving the security of the acquired face image usage.

[0096] In some embodiments, the second image generation module 402 may be specifically used to: calculate a first difference between the pixel value of a pixel in the acquired face image and the pixel value of a pixel in the first fragment image; if the first difference is less than 0, calculate a first sum of the first difference and 256; and obtain the second fragment image based on the first sum and the first difference which is greater than or equal to 0.

[0097] In some examples, the second image generation module 402 may be specifically used to: determine the first difference between the first sum and the first difference greater than or equal to 0 as the pixel value of the corresponding pixel in the second fragment image, thereby obtaining the second fragment image.

[0098] In some embodiments, different first fragment images correspond to different acquired face images; or, every N acquired face images are divided into an image group, the first fragment images corresponding to the face images acquired in the same image group are the same, and the first fragment images corresponding to the face images acquired in different image groups are different, where N is an integer greater than 1.

[0099] In some examples, every N captured face images are divided into an image group, and the first fragment image corresponding to the face images captured in the same image group is the same, where N is an integer greater than 1. The second image generation module 402 can be specifically used to: obtain a pre-generated patch image corresponding to the captured face image, the size of the patch image being smaller than the size of the second fragment image; determine the first difference between the first sum and the first difference greater than or equal to 0 as the pixel value of the corresponding pixel in the intermediate image, thereby obtaining an intermediate image; divide the intermediate image into multiple image blocks of the same size as the patch image; and perform pixel operations based on the pixel values ​​of the pixels in the image blocks and the pixel values ​​of the pixels in the patch image to obtain the second fragment image.

[0100] In some embodiments, the sending module 403 can also be used to: send image reconstruction information to the server in response to user authentication and authorization input, so that the server can reconstruct the acquired face image based on the image reconstruction information and the second fragment image. The image reconstruction information includes the first fragment image.

[0101] In some examples, the image restoration information also includes patch images.

[0102] The fourth aspect of this application provides a server. Figure 14 This is a schematic diagram of the structure of a server provided in an embodiment of the fourth aspect of this application, as shown below. Figure 14 As shown, the server 500 may include a receiving module 501, a processing module 502, and a storage module 503.

[0103] The receiving module 501 can be used to receive the collected face image and second fragment image sent by the recognition terminal.

[0104] The second fragment image is obtained by pixel-wise calculation based on the acquired face image and the first fragment image. The first fragment image is randomly generated and stored in the recognition terminal. The resolution of the first fragment image is the same as the resolution of the acquired face image.

[0105] The processing module 502 can be used to perform face recognition services using the collected face images, and discard the collected face images after the face recognition service is completed.

[0106] Storage module 503 can be used to store the second fragment image.

[0107] In this embodiment, the recognition terminal can randomly generate a first fragment image with the same resolution as the acquired face image. A second fragment image is obtained through pixel-wise operations between the face image and the first fragment image. The second fragment image and the face image are then sent to the server. The first fragment image is stored in the recognition terminal, and the second fragment image is stored on the server. Neither the recognition terminal nor the server stores the acquired face image. If the recognition terminal is attacked, the first fragment image is leaked. Since the first fragment image contains zero information about the acquired face image, the attacker cannot obtain the face image from the first fragment image. If the server is attacked, the second fragment image is leaked. Since the second fragment image does not contain any information about the acquired face image, the attacker cannot obtain the face image from the second fragment image. However, when user authorization is obtained to reconstruct the face image, the first and second fragment images can be legally obtained. The original acquired face image can then be reconstructed from the first and second fragment images, satisfying the face image acquisition requirements and improving the security of the acquired face image usage.

[0108] In some embodiments, the second fragment image is obtained based on a first sum and a first difference greater than or equal to 0, wherein the first difference is the difference between the pixel value of a pixel in the acquired face image and the pixel value of a pixel in the first fragment image, and the first sum is the sum of the first difference less than 0 and 256.

[0109] In some examples, the pixel values ​​of pixels in the second fragment image include a first summation and a first difference greater than or equal to 0 corresponding to the pixel.

[0110] In some embodiments, different first fragment images correspond to different acquired face images; or, every N acquired face images are divided into an image group, the first fragment images corresponding to the face images acquired in the same image group are the same, and the first fragment images corresponding to the face images acquired in different image groups are different, where N is an integer greater than 1.

[0111] In some examples, every N captured face images are divided into an image group, and the first fragment image corresponding to the face images captured in the same image group is the same. The pixel values ​​of the second fragment image are obtained by performing pixel operations on the pixel values ​​of the image block and the pixel values ​​of the patch image. The image block is obtained by dividing the intermediate image, and the size of the image block is the same as the size of the patch image. The pixel values ​​of the intermediate image include the first sum and the first difference greater than or equal to 0 for the corresponding pixels. The patch image is pre-generated randomly and its size is smaller than the size of the second fragment image.

[0112] In some embodiments, the receiving module 501 can also be used to: receive image restoration information sent by the identification terminal in response to the user's identity authentication authorization input, the image restoration information including a first fragment image.

[0113] The aforementioned processing module 502 can also be used to: perform inverse pixel operations based on the image reconstruction information and the second fragment image to reconstruct the acquired face image.

[0114] In some examples, the image restoration information also includes patch images.

[0115] The fifth aspect of this application provides an identification terminal. Figure 15 This is a schematic diagram of the structure of an identification terminal provided in an embodiment of the fifth aspect of this application. Figure 15 As shown, the identification terminal 600 includes a memory 601, a processor 602, and a computer program stored in the memory 601 and capable of running on the processor 602.

[0116] In some examples, the processor 602 described above may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits that may be configured to implement the embodiments of this application.

[0117] Memory 601 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory 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 secure processing method for user images according to the first aspect embodiment of this application.

[0118] The processor 602 runs a computer program corresponding to the executable program code by reading the executable program code stored in the memory 601, so as to implement the user image security processing method in the first aspect embodiment described above.

[0119] In some examples, the identification terminal 600 may also include a communication interface 603 and a bus 604. For example, Figure 15 As shown, the memory 601, processor 602, and communication interface 603 are connected through bus 604 and complete communication with each other.

[0120] The communication interface 603 is mainly used to enable communication between various modules, devices, units, and / or equipment in the embodiments of this application. Input devices and / or output devices can also be connected through the communication interface 603.

[0121] Bus 604 includes hardware, software, or both, that couples the components of identification terminal 600 together. For example, and not limitingly, bus 604 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-E) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 604 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0122] A sixth aspect of this application provides a server. The server includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The memory 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 operations described with reference to the secure processing method for user images according to an embodiment of a second aspect of this application. The processor runs a computer program corresponding to the executable program code stored in the memory to implement the secure processing method for user images described in the second aspect embodiment above.

[0123] In some examples, the server may also include a communication interface and a bus. The memory, processor, and communication interface are connected via the bus and communicate with each other.

[0124] The connection relationships and specific hardware implementations of the aforementioned memory, processor, communication interface, bus, etc., can be found in [reference needed]. Figure 15 The memory 601, processor 602, communication interface 603, and bus 604 in the identification terminal, along with their corresponding descriptions, will not be repeated here.

[0125] The seventh aspect of this application also provides a computer-readable storage medium storing computer program instructions. When executed by a processor, these computer program instructions can implement the user image security processing method described in the first aspect embodiment or the user image security processing method described in the second aspect embodiment, and achieve the same technical effect. To avoid repetition, further details are omitted here. The aforementioned computer-readable storage medium may include non-transitory computer-readable storage media, such as read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc., and is not limited thereto.

[0126] This application provides a computer program product. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device can execute the user image security processing method in the first aspect embodiment or the user image security processing method in the second aspect embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0127] It should be clarified that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. For the device embodiments, equipment embodiments, and computer-readable storage medium embodiments, the relevant parts can be referred to the description section of the method embodiments. This application is not limited to the specific steps and structures described above and shown in the figures. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application. Furthermore, for the sake of brevity, detailed descriptions of known methods and techniques are omitted here.

[0128] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0129] Those skilled in the art will understand that the above embodiments are exemplary and not restrictive. Different technical features appearing in different embodiments can be combined to achieve beneficial effects. Based on a study of the drawings, specification, and claims, those skilled in the art should be able to understand and implement other variations of the disclosed embodiments. In the claims, the term "comprising" does not exclude other means or steps; the quantifier "a" does not exclude a plurality; the terms "first" and "second" are used to identify names and not to indicate any particular order. No reference numerals in the claims should be construed as limiting the scope of protection. The functionality of multiple parts appearing in the claims can be implemented by a single hardware or software module. The appearance of certain technical features in different dependent claims does not mean that these technical features cannot be combined to achieve beneficial effects.

Claims

1. A method for securely processing user images, characterized in that, Applied to an identification terminal, the method includes: A first fragment image with the same resolution as the acquired face image is randomly generated and stored; The second fragment image is obtained by performing pixel calculations based on the collected face image and the first fragment image; The system sends the collected face image and the second fragment image to the server so that the server can use the collected face image to perform face recognition. After the face recognition is completed, the collected face image is discarded and the second fragment image is stored. The step of performing pixel calculations based on the acquired face image and the first fragment image to obtain the second fragment image includes: Calculate the first difference between the pixel value of a pixel in the acquired face image and the pixel value of a pixel in the first fragment image; If the first difference is less than 0, calculate the first sum of the first difference and 256; The second fragment image is obtained based on the first difference value that is greater than or equal to 0 in the first summation; Every N captured face images are divided into an image group. Face images captured in the same image group correspond to the same first fragment image. N is an integer greater than 1. The step of obtaining the second fragment image based on the first difference value that is greater than or equal to 0 by the first summation includes: Obtain a pre-generated patch image corresponding to the acquired face image, wherein the size of the patch image is smaller than the size of the second fragment image; The first difference, where the first sum is greater than or equal to 0, is determined as the pixel value of the corresponding pixel in the intermediate image, thus obtaining the intermediate image; The intermediate image is divided into multiple image blocks of the same size as the patch image; The second fragment image is obtained by performing pixel operations based on the pixel values ​​of the pixels in the image block and the pixel values ​​of the pixels in the patch image.

2. The method according to claim 1, characterized in that, Also includes: In response to the user's authentication and authorization input, image reconstruction information is sent to the server so that the server can reconstruct the acquired face image based on the image reconstruction information and the second fragment image, wherein the image reconstruction information includes the first fragment image.

3. The method according to claim 2, characterized in that, The image restoration information also includes patch images.

4. A method for securely processing user images, characterized in that, Applied to a server, the method includes: The system receives a collected face image and a second fragment image sent by the recognition terminal. The second fragment image is obtained by pixel calculation based on the collected face image and the first fragment image. The first fragment image is randomly generated and stored in the recognition terminal. The resolution of the first fragment image is the same as the resolution of the collected face image. The collected face images are used for face recognition services. After the face recognition service is completed, the collected face images are discarded and the second fragment image is stored. The second fragment image is obtained based on a first difference greater than or equal to a first sum, where the first difference is the difference between the pixel value of a pixel in the acquired face image and the pixel value of a pixel in the first fragment image, and the first sum is the sum of the first difference less than 0 and 256. Every N collected face images are divided into an image group. The first fragment image corresponding to the face images collected in the same image group is the same, and N is an integer greater than 1. The pixel values ​​of the second fragment image are obtained by performing pixel operations on the pixel values ​​of the pixels in the image block and the pixel values ​​of the pixels in the patch image. The image block is obtained by dividing the intermediate image. The size of the image block is the same as the size of the patch image. The pixel values ​​of the pixels in the intermediate image include the first sum and the first difference greater than or equal to 0 corresponding to the pixels. The patch image is randomly generated in advance and its size is smaller than the size of the second fragment image.

5. The method according to claim 4, characterized in that, Also includes: The system receives image restoration information sent by the recognition terminal in response to the user's authentication and authorization input, the image restoration information including the first fragment image; Based on the image reconstruction information and the second fragment image, the inverse operation of pixel calculation is performed to reconstruct the acquired face image.

6. The method according to claim 5, characterized in that, The image restoration information also includes patch images.

7. An identification terminal, characterized in that, include: The first image generation module is used to randomly generate and store a first fragment image with the same resolution as the acquired face image; The second image generation module is used to perform pixel calculations based on the acquired face image and the first fragment image to obtain the second fragment image; The sending module is used to send the collected face image and the second fragment image to the server so that the server can use the collected face image to perform face recognition service. After the face recognition service is completed, the collected face image is discarded and the second fragment image is stored. The second image generation module is specifically used for: Calculate the first difference between the pixel value of a pixel in the acquired face image and the pixel value of a pixel in the first fragment image; If the first difference is less than 0, calculate the first sum of the first difference and 256; The second fragment image is obtained based on the first difference value that is greater than or equal to 0 in the first summation; In this method, every N captured face images are divided into an image group. The first fragment image corresponding to the face images captured in the same image group is the same, where N is an integer greater than 1. The second image generation module is specifically used for: Obtain a pre-generated patch image corresponding to the acquired face image, wherein the size of the patch image is smaller than the size of the second fragment image; The first difference, where the first sum is greater than or equal to 0, is determined as the pixel value of the corresponding pixel in the intermediate image, thus obtaining the intermediate image; The intermediate image is divided into multiple image blocks of the same size as the patch image; The second fragment image is obtained by performing pixel operations based on the pixel values ​​of the pixels in the image block and the pixel values ​​of the pixels in the patch image.

8. A server, characterized in that, include: The receiving module is used to receive the collected face image and the second fragment image sent by the recognition terminal. The second fragment image is obtained by pixel calculation based on the collected face image and the first fragment image. The first fragment image is randomly generated and stored in the recognition terminal. The resolution of the first fragment image is the same as the resolution of the collected face image. The processing module is used to perform face recognition using the collected face images and discard the collected face images after the face recognition process is completed. Storage module for storing the second fragment image; The second fragment image is obtained based on a first difference greater than or equal to a first sum, where the first difference is the difference between the pixel value of a pixel in the acquired face image and the pixel value of a pixel in the first fragment image, and the first sum is the sum of the first difference less than 0 and 256. Every N collected face images are divided into an image group. The first fragment image corresponding to the face images collected in the same image group is the same, and N is an integer greater than 1. The pixel values ​​of the second fragment image are obtained by performing pixel operations on the pixel values ​​of the pixels in the image block and the pixel values ​​of the pixels in the patch image. The image block is obtained by dividing the intermediate image. The size of the image block is the same as the size of the patch image. The pixel values ​​of the pixels in the intermediate image include the first sum and the first difference greater than or equal to 0 corresponding to the pixels. The patch image is randomly generated in advance and its size is smaller than the size of the second fragment image.

9. An identification terminal, characterized in that, include: Processor and memory storing computer program instructions; When the processor executes the computer program instructions, it implements the user image security processing method as described in any one of claims 1 to 3.

10. A server, characterized in that, include: Processor and memory storing computer program instructions; When the processor executes the computer program instructions, it implements the user image security processing method as described in any one of claims 4 to 6.

11. A user image security processing system, characterized in that, include: The identification terminal as described in claim 9; The server as described in claim 10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the secure processing method for user images as described in any one of claims 1 to 6.

Images