WO2021238956A1

WO2021238956A1 - Identity verification method, apparatus and device based on privacy protection

Info

Publication number: WO2021238956A1
Application number: PCT/CN2021/095935
Authority: WO
Inventors: 曹佳炯; 李亮
Original assignee: 支付宝(杭州)信息技术有限公司
Priority date: 2020-05-27
Filing date: 2021-05-26
Publication date: 2021-12-02
Also published as: CN111538968A

Abstract

Provided are an identity verification method, apparatus and device based on privacy protection. The method comprises: acquiring a user image, in a space domain format, of a user to be verified, wherein the user image comprises the face of said user; performing format conversion processing on the user image according to a preset mode, so as to obtain a target image in a frequency domain format; and according to the target image and a pre-trained facial recognition model, verifying the identity of said user, so as to obtain identity verification result information.

Description

Identity verification method, device and equipment based on privacy protection

Technical field

This document relates to the field of identity authentication technology, in particular to an identity verification method, device and equipment based on privacy protection.

Background technique

Face recognition technology has developed tremendously in recent years and has been applied in many scenarios, such as payment, attendance, travel and other scenarios. In the current face recognition technology, each step of the operation is performed based on the collected original face image. Therefore, once the algorithm is compromised, the user's face image will be leaked. The leaked face image is likely to be processed by criminals and used to attack the face recognition system, or used to search in the database to obtain other user information (such as age, address, etc.), and this will It poses a threat to the personal and property safety of users.

Summary of the invention

One or more embodiments of this specification provide an identity verification method based on privacy protection. The method includes obtaining a user image in an airspace format of the user to be verified. Wherein, the user image includes the face of the user to be verified. Performing format conversion processing on the user image according to a preset manner to obtain a target image in a frequency domain format. Perform verification processing on the identity of the user to be verified according to the target image and the pre-trained face recognition model to obtain identity verification result information.

One or more embodiments of this specification provide an identity verification device based on privacy protection. The device includes an acquisition module to acquire the user image in the airspace format of the user to be verified. Wherein, the user image includes the face of the user to be verified. The device also includes a conversion module, which performs format conversion processing on the user image according to a preset manner to obtain a target image in a frequency domain format. The device also includes a verification module, which performs verification processing on the identity of the user to be verified based on the target image and a pre-trained face recognition model to obtain identity verification result information.

One or more embodiments of this specification provide an identity verification device based on privacy protection. The device includes a processor. The device also includes a memory arranged to store computer-executable instructions. When executed, the computer-executable instructions cause the processor to obtain a user image in an airspace format of the user to be verified. Wherein, the user image includes the face of the user to be verified. Performing format conversion processing on the user image according to a preset manner to obtain a target image in a frequency domain format. Perform verification processing on the identity of the user to be verified according to the target image and the pre-trained face recognition model to obtain identity verification result information.

One or more embodiments of this specification provide a storage medium. The storage medium is used to store computer-executable instructions. The computer-executable instructions, when executed, obtain a user image in an airspace format of the user to be verified. Wherein, the user image includes the face of the user to be verified. Performing format conversion processing on the user image according to a preset manner to obtain a target image in a frequency domain format. Perform verification processing on the identity of the user to be verified according to the target image and the pre-trained face recognition model to obtain identity verification result information.

Description of the drawings

In order to more clearly explain one or more embodiments of this specification or technical solutions in the prior art, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, in the following description The accompanying drawings are only some of the embodiments described in this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor.

FIG. 1 is a schematic diagram of a scenario of an identity verification method based on privacy protection provided by one or more embodiments of this specification;

2 is a schematic diagram of the first flow of a privacy protection-based identity verification method provided by one or more embodiments of this specification;

3 is a schematic diagram of the second flow of a privacy protection-based identity verification method provided by one or more embodiments of this specification;

4 is a schematic diagram of a third process of a privacy protection-based identity verification method provided by one or more embodiments of this specification;

FIG. 5 is a schematic diagram of the fourth process of a privacy protection-based identity verification method provided by one or more embodiments of this specification;

FIG. 6 is a schematic flowchart of a method for training a face recognition model provided by one or more embodiments of this specification;

FIG. 7 is a schematic diagram of the fifth flow of an identity verification method based on privacy protection provided by one or more embodiments of this specification;

FIG. 8 is a schematic diagram of the sixth process of a privacy protection-based identity verification method provided by one or more embodiments of this specification;

9 is a schematic diagram of the module composition of an identity verification device based on privacy protection provided by one or more embodiments of this specification;

FIG. 10 is a schematic structural diagram of an identity verification device based on privacy protection provided by one or more embodiments of this specification.

Detailed ways

In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will combine the drawings in one or more embodiments of this specification to compare The technical solution is described clearly and completely. Obviously, the described embodiments are only a part of the embodiments in this specification, rather than all the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by a person of ordinary skill in the art without creative work shall fall within the protection scope of this document.

Fig. 1 is a schematic diagram of an application scenario of an identity verification method based on privacy protection provided by one or more embodiments of this specification. As shown in Fig. 1, the scenario includes: an image acquisition device and an identity verification device; wherein, the image acquisition device For example, a camera, which can be installed in the identity verification device, and can also exist independently from the identity verification device (only the separated case is shown in FIG. 1).

Specifically, the image acquisition device collects a user image in an airspace format of the user to be verified, and the user image includes the face of the user to be verified. The identity verification device obtains the user image from the image acquisition device, performs format conversion processing on the user image according to a preset method, and obtains the target image in the frequency domain format; and, according to the target image and the pre-trained face recognition model, The identity is verified and processed, and the result information of the identity verification is obtained. Among them, the spatial domain is also called the spatial domain, that is, the pixel domain. The image content, such as people, plants, houses, etc., can be clearly seen from the image in the spatial domain format. The frequency domain is also called the frequency domain. Its independent variable is the frequency, that is, the horizontal axis is the frequency, and the vertical axis is the amplitude of the frequency signal, which is commonly referred to as the spectrogram; therefore, from the frequency domain format image Cannot see the content of the image. Therefore, by converting the user image in the airspace format into the target image in the frequency domain format, and performing the identity verification process based on the target image in the frequency domain format, even if the target image is stolen by the attacker during the identity verification process, the attacker will still Unable to know the content of the image, which effectively guarantees the security of the user's private information, and avoids the risk of user property loss caused by the leakage of the user's private information.

It should be pointed out that the above application scenarios are only for illustration and not for limitation. The image acquisition device can also be connected to the identity verification device through other business systems. Accordingly, the identity verification device can also obtain from the business system the information of the user to be verified. User image in airspace format.

Based on the foregoing application scenario architecture, one or more embodiments of this specification provide an identity verification method based on privacy protection. Figure 2 is a schematic flow chart of a privacy protection-based identity verification method provided by one or more embodiments of this specification. The method in Figure 2 can be executed by the identity verification device in Figure 1, as shown in Figure 2. It includes the following steps: step S102, obtaining a user image in the airspace format of the user to be verified; wherein the user image includes the face of the user to be verified; optionally, the identity verification device is connected to the image acquisition device and receives the image The user image in the airspace format of the user to be verified. Alternatively, the identity verification device is connected to the image acquisition device, and the image acquisition device saves the collected user image in the airspace format to a designated storage area, and the identity verification device acquires the user image in the airspace format of the user to be verified from the designated storage area. Or, the identity verification device is connected to the business system, and receives the user image in the airspace format of the user to be verified sent by the business system. The user image acquisition method is not specifically limited in this manual, and it can be set according to actual needs.

Further, the user image may be a full body image of the user to be verified, an upper body image of the user to be verified, or a head image of the user to be verified, which is not specifically limited in this specification.

Step S104: Perform format conversion processing on the acquired user image according to a preset method to obtain a target image in the frequency domain format; Step S106: Perform verification processing on the identity of the user to be verified based on the target image and the pre-trained face recognition model to obtain Identity verification result information.

In one or more embodiments of this specification, the user image in the space domain format is converted into the target image in the frequency domain format, and the identity verification process is performed based on the target image in the frequency domain format; because the target image in the frequency domain format cannot reflect the spatial domain The image content of the user image in the format, therefore, even if the target image is stolen by the attacker during the identity verification process, the attacker cannot know the image content of the user image in the airspace format, thus effectively ensuring the security of the user’s private information , To avoid the risk of user property loss caused by the leakage of user privacy information.

Considering that the user's face in the user image may be tilted due to the acquisition angle or the user's posture, etc., which is not conducive to the subsequent identity verification process, in order to improve the accuracy of the identity verification process, one or more embodiments of this specification As shown in FIG. 3, step S104 includes: step S104-2, preprocessing the user image to obtain the image to be converted; specifically, as shown in FIG. 4, step S104-2 includes: step S104-22, according to the preset The detection algorithm is used to perform face detection processing on the user image to obtain the key position information of the face; among them, the key position information such as the position information of the eyes, eyebrows, nose, mouth and other parts; the key position and detection algorithm can be applied in practice Set it according to your needs.

In step S104-24, the user image is calibrated according to the obtained key position information to obtain the image to be converted.

Specifically, according to the obtained key position information and the preset calibration template, operations such as translation and flipping of the user image are performed to obtain the image to be converted.

Step S104-4: Perform format conversion processing on the image to be converted according to a preset method to obtain a target image in a frequency domain format.

Specifically, according to a preset method and preset conversion parameters, the format conversion processing of the image to be converted is performed to obtain the target image in the frequency domain format. Among them, the preset methods such as discrete Fourier transform, discrete cosine transform (Discrete Cosine Transform, DCT for short), etc., are not specifically limited in this specification, and can be set by themselves according to needs in actual applications. Since Fourier transform, discrete cosine transform, etc. are well-known technologies to those skilled in the art, the specific processing procedures of Fourier transform, discrete cosine transform, etc. will not be described in detail in this specification. It should be pointed out that the process of format conversion is reversible, that is, the target image is formatted according to the conversion parameters, and the image to be converted in the spatial format (ie the calibrated user image) can be obtained; however, the attacker cannot know Conversion parameters, so for the attacker, even if the target image is obtained, the user image cannot be restored; but for the identity verification device, the target image can be formatted based on the preset conversion parameters when needed to restore the user image.

Therefore, by preprocessing the user image to align it with the calibration template, it is ensured that the face in the obtained image to be converted is in a position that is conducive to recognition, thereby improving the accuracy of identity verification. By performing format conversion on the pre-processed image to be converted, the user's privacy protection is realized, and the target image can be formatted according to the conversion parameters corresponding to the preset mode when necessary in the future, and the spatial format is obtained. The user image has achieved the effect of saving the original image.

In order to avoid a live attack by criminals, in one or more embodiments of this specification, during the process of identity verification, the live body detection is first performed, and after the live body detection is passed, the face comparison process is performed. Specifically, as shown in FIG. 5, step S106 includes: step S106-2, according to the pre-trained life detection model, perform the life detection processing on the target image; step S106-4, if the result of the life detection processing is that the detection passed, then According to the pre-trained face comparison model, the target image is processed for face comparison.

Specifically, the target image is input to the pre-trained living body detection model, and the living body detection processing is performed to obtain the living body detection result information. If the living body detection result information is that the detection fails, the living body detection failure information is displayed; if the living body detection result information is detection If passed, the face image of the user to be verified is obtained from the designated database, and based on the pre-trained face comparison model, the obtained face image and the target image are compared with the target image, and the result information of the face comparison is obtained. The identity verification result information is determined according to the face comparison result information. Among them, the designated database can be a database of an authoritative organization, which is feasible, such as a database of a public security organization; the designated database can also be a local database of the identity verification device, including the data provided by each user when the user performs related business processing for the first time. Effective face image.

Therefore, before the face comparison processing, the living body detection processing is performed first, which effectively avoids the malicious impersonation behavior of others by illegal means, thereby avoiding the risk of the user's property loss.

Further, in order to realize the verification process of the identity of the user to be verified, in one or more embodiments of this specification, as shown in FIG. 6, before step S106, the method further includes: step S100-2, obtaining a sample set to be trained; where , The sample set includes multiple sample images in spatial format; step S100-4, format conversion processing is performed on each sample image in the sample set according to a preset method to obtain a sample image in frequency domain format; specifically, each sample image in the sample set is Preprocessing is performed on each sample image, and format conversion processing is performed on each sample image after preprocessing according to a preset method to obtain a sample image in a frequency domain format. Among them, the specific process of pre-processing can be referred to the aforementioned related description, and the repetitive points will not be repeated here.

In step S100-6, a model training process is performed based on the sample image in the frequency domain format to obtain a face recognition model.

Specifically, the sample image in the frequency domain is divided into a training set and a test set, and the training set is trained based on the convolutional neural network to obtain the initial model; the test set is used to test the obtained initial model to obtain the initial model Accuracy rate; determine whether the accuracy rate obtained is not less than the preset accuracy rate, if it is, the test process is determined to be passed, and the corresponding initial model is determined as the face recognition model; if not, the test process is determined to be failed, the training parameters are adjusted, and Continue training based on the training set until the face recognition model is obtained. Wherein, the face recognition model includes the aforementioned live body detection model and face comparison model, and the methods described in step S100-2 to step S100-6 are respectively used for training processing to obtain the corresponding live body detection model and face comparison model. Since the training process of the model is a well-known technique to those skilled in the art, it will not be described in further detail here.

Further, in order to use the user image in the airspace format of the user to be verified in the subsequent processing of related services or in the traceability process of related services, in one or more embodiments of this specification, as shown in Figure 7, After step S106, it also includes: step S108, if the identity verification result information is verified, then obtain an encrypted template image; optionally, preset a fixed encrypted template image, and obtain the preset encrypted template from a designated location image. Or, grab an image randomly from the network, and determine the grabbed image as an encrypted template image. Or, randomly select an image from the specified gallery, and determine the selected image as an encrypted template image. In this manual, there are no specific restrictions on the method of obtaining the encrypted template image and the style of the encrypted template image, and it can be set according to the needs in the actual application.

In step S110, the target image is encrypted using the encrypted template image; specifically, the encrypted template image and the target image are fused, and the fused image is determined as the encrypted image of the target image.

Step S112, save the encrypted target image.

Optionally, save the encrypted target image to a local designated storage area of the identity verification device, or save the encrypted target image to the cloud, etc. It should be pointed out that when the encrypted template image is an image randomly grabbed from the network, or an image randomly selected from a specified gallery, the method also includes associating and saving the encrypted template image with the relevant information of the target image, so as to When it is necessary to restore the user image in spatial format, obtain the encrypted template image according to the relevant information of the target image, and decrypt the encrypted target image according to the encrypted template image to obtain the target image; perform format conversion processing on the target image to obtain User image in airspace format. Among them, the relevant information of the target image, such as the image identification of the target image, and so on.

Therefore, by using the encrypted template image to encrypt the target image, and save the encrypted target image, even if the attacker intercepts the encrypted target image, because the attacker does not know the encrypted template image, he cannot The encrypted target image is decrypted. Therefore, the double protection of the user image in the airspace format is realized, and the security of the user's private information is greatly improved.

In one or more embodiments of this specification, a preset encryption algorithm may also be used to encrypt the target image. Specifically, as shown in FIG. 8, after step S106, it may further include: step S114, if the identity verification result information In order to pass the verification, the target image is encrypted according to the preset encryption algorithm; among them, the encryption algorithm, such as AES encryption algorithm, MD5 encryption algorithm, etc., can be set according to the needs in actual applications.

Step S116, save the encrypted target image.

Therefore, the target image is encrypted by using a preset encryption algorithm, and the encrypted target image is saved, so that even if the attacker intercepts the encrypted target image, because the attacker does not know the specific encryption algorithm, It is not possible to decrypt the encrypted target image. Therefore, the double protection of the user image in the airspace format is realized, and the security of the user's private information is greatly improved.

Corresponding to the privacy protection-based identity verification method described in Figs. 2 to 8, based on the same technical concept, one or more embodiments of this specification also provide an identity verification device based on privacy protection. Figure 9 is a schematic diagram of the module composition of a privacy protection-based identity verification device provided by one or more embodiments of this specification. The device is used to execute the privacy protection-based identity verification method described in Figs. 2 to 8, as shown in Fig. 9 As shown, the device includes: an acquisition module 201, which acquires a user image in an airspace format of the user to be verified; wherein the user image includes the face of the user to be verified; The image undergoes format conversion processing to obtain a target image in a frequency domain format; the verification module 203 performs verification processing on the identity of the user to be verified based on the target image and a pre-trained face recognition model to obtain identity verification result information.

The privacy protection-based identity verification device provided by one or more embodiments of this specification converts a user image in the space domain format into a target image in the frequency domain format, and performs identity verification processing based on the target image in the frequency domain format; The target image in the format cannot reflect the image content of the user image in the airspace format. Therefore, even if the target image is stolen by the attacker during the identity verification process, the attacker cannot know the image content of the user image in the airspace format, which is effective This guarantees the security of users’ private information and avoids risks such as user property losses caused by the leakage of user’s private information.

Optionally, the conversion module 202 preprocesses the user image to obtain an image to be converted; and performs format conversion processing on the image to be converted according to a preset manner to obtain a target image in a frequency domain format.

Optionally, the conversion module 202 performs face detection processing on the user image according to a preset detection algorithm to obtain key position information of the face; and, according to the key position information, The user image is calibrated to obtain the image to be converted.

Optionally, the verification module 203 performs a live body detection process on the target image according to a pre-trained live body detection model; if the result of the live body detection process is that the detection is passed, it compares the model according to the pre-trained face , Perform face comparison processing on the target image.

Optionally, the device further includes: a first saving module; the saving module, if the identity verification result information is verified, obtain an encrypted template image; use the encrypted template image to encrypt the target image Processing; save the encrypted target image.

Optionally, the device further includes: a second storage module; the second storage module, if the identity verification result information is verified, encrypt the target image according to a preset encryption algorithm; and ,

Save the encrypted target image.

Optionally, the device further includes: a training module; the training module, before the verification module performs verification processing on the identity of the user to be verified based on the target image and a pre-trained face recognition model, Acquire a sample set to be trained; wherein, the sample set includes a plurality of sample images in spatial domain format; and, according to the preset manner, perform format conversion processing on each of the sample images in the sample set to obtain the frequency domain Format sample image; based on the frequency domain format sample image for model training processing to obtain the face recognition model.

It should be noted that the embodiment of the identity verification device based on privacy protection in this specification and the embodiment of the identity verification method based on privacy protection in this specification are based on the same inventive concept, so the specific implementation of this embodiment can refer to the aforementioned corresponding The implementation of the identity verification method based on privacy protection will not be repeated here.

Further, corresponding to the aforementioned privacy protection-based identity verification method, based on the same technical concept, one or more embodiments of this specification also provide an identity verification device based on privacy protection, which is used to perform the aforementioned identity verification Method, FIG. 10 is a schematic structural diagram of an identity verification device based on privacy protection provided by one or more embodiments of this specification.

As shown in FIG. 10, the identity verification device based on privacy protection may have relatively large differences due to different configurations or performances, and may include one or more processors 301 and a memory 302, and the memory 302 may store one or more Store applications or data. Among them, the memory 302 may be short-term storage or persistent storage. The application program stored in the memory 302 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in an identity verification device based on privacy protection. Furthermore, the processor 301 may be configured to communicate with the memory 302, and execute a series of computer-executable instructions in the memory 302 on an identity verification device based on privacy protection. The identity verification device based on privacy protection may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input and output interfaces 305, one or more keyboards 306, and so on.

In a specific embodiment, the identity verification device based on privacy protection includes a memory and one or more programs, wherein one or more programs are stored in the memory, and the one or more programs may include one or more programs. Modules, and each module may include a series of computer-executable instructions for a privacy-protected identity verification device, and is configured to be executed by one or more processors. Execution instruction: Obtain the user image in the spatial format of the user to be verified; wherein the user image includes the face of the user to be verified; perform format conversion processing on the user image according to a preset method to obtain the target in the frequency domain format Image; According to the target image and a pre-trained face recognition model, the identity of the user to be verified is verified to obtain identity verification result information.

Optionally, when the computer-executable instructions are executed, the format conversion processing on the user image according to a preset manner to obtain the target image in the frequency domain format includes: preprocessing the user image to obtain the Converting an image; performing format conversion processing on the image to be converted according to a preset manner to obtain a target image in a frequency domain format.

Optionally, when the computer-executable instructions are executed, the preprocessing the user image to obtain the image to be converted includes: performing face detection processing on the user image according to a preset detection algorithm to obtain The key position information of the face; according to the key position information, the user image is calibrated to obtain the image to be converted.

Optionally, when the computer-executable instructions are executed, the verification processing of the identity of the user to be verified according to the target image and a pre-trained face recognition model includes: according to a pre-trained live detection model , Performing a living body detection processing on the target image; if the result of the living body detection processing is that the detection is passed, then performing a face comparison processing on the target image according to a pre-trained face comparison model.

Optionally, when the computer-executable instructions are executed, after the obtaining of the identity verification result information, the method further includes: if the identity verification result information is verified, obtaining an encrypted template image; The target image is encrypted; the encrypted target image is saved.

Optionally, when the computer-executable instructions are executed, after obtaining the identity verification result information, the method further includes: if the identity verification result information is verified, encrypting the target image according to a preset encryption algorithm Processing; save the encrypted target image.

Optionally, when the computer-executable instructions are executed, before performing the verification process on the identity of the user to be verified based on the target image and a pre-trained face recognition model, the method further includes: obtaining a sample to be trained Wherein, the sample set includes a plurality of sample images in spatial format; according to the preset manner, format conversion processing is performed on each of the sample images in the sample set to obtain sample images in frequency domain format; Model training is performed on the sample image in the frequency domain format to obtain the face recognition model.

The privacy protection-based identity verification device provided in one or more embodiments of this specification converts a user image in the space domain format into a target image in the frequency domain format, and performs identity verification processing based on the target image in the frequency domain format; The target image in the format cannot reflect the image content of the user image in the airspace format. Therefore, even if the target image is stolen by the attacker during the identity verification process, the attacker cannot know the image content of the user image in the airspace format, which is effective This guarantees the security of users’ private information and avoids risks such as user property losses caused by the leakage of user’s private information.

Further, corresponding to the aforementioned privacy protection-based identity verification method, based on the same technical concept, one or more embodiments of this specification also provide a storage medium for storing computer-executable instructions. A specific embodiment Wherein, the storage medium may be a U disk, an optical disk, a hard disk, etc., when the computer executable instructions stored in the storage medium are executed by the processor, the following process can be realized: Obtain the user image in the airspace format of the user to be verified; The user image includes the face of the user to be verified; the user image is formatted according to a preset method to obtain a target image in a frequency domain format; according to the target image and a pre-trained face recognition model, The identity of the to-be-verified user undergoes verification processing to obtain identity verification result information.

When the computer executable instructions stored in the storage medium provided by one or more embodiments of this specification are executed by the processor, they convert the user image in the space domain format into the target image in the frequency domain format, and perform processing based on the target image in the frequency domain format. Identity verification processing; since the target image in the frequency domain format cannot reflect the image content of the user image in the airspace format, even if the target image is stolen by the attacker during the identity verification process, the attacker cannot know the user in the airspace format The image content of the image effectively guarantees the security of the user's private information and avoids the risk of user property loss caused by the leakage of the user's private information.

Optionally, when the computer-executable instructions stored in the storage medium are executed by the processor, the format conversion processing on the user image according to a preset manner to obtain the target image in the frequency domain format includes: The image is preprocessed to obtain the image to be converted; the format conversion process is performed on the image to be converted according to a preset method to obtain the target image in the frequency domain format.

Optionally, when the computer-executable instructions stored in the storage medium are executed by the processor, the preprocessing of the user image to obtain the image to be converted includes: comparing the user image to the user image according to a preset detection algorithm Perform face detection processing to obtain key position information of the face; perform calibration processing on the user image according to the key position information to obtain an image to be converted.

Optionally, when the computer-executable instructions stored in the storage medium are executed by the processor, the verification process on the identity of the user to be verified based on the target image and a pre-trained face recognition model includes: According to the pre-trained living body detection model, the target image is subjected to the living body detection processing; if the result of the living body detection processing is that the detection is passed, the face comparison is performed on the target image according to the pre-trained face comparison model To deal with.

Optionally, when the computer-executable instructions stored in the storage medium are executed by the processor, after obtaining the identity verification result information, the method further includes: if the identity verification result information is verified, obtaining an encrypted template image; The encrypted template image performs encryption processing on the target image; and saves the encrypted target image.

Optionally, when the computer-executable instructions stored in the storage medium are executed by the processor, after obtaining the identity verification result information, the method further includes: if the identity verification result information is verified, then according to a preset encryption algorithm Encryption processing is performed on the target image; and the target image after the encryption processing is saved.

Optionally, when the computer-executable instructions stored in the storage medium are executed by the processor, before the verification process is performed on the identity of the user to be verified according to the target image and a pre-trained face recognition model, The method includes: obtaining a sample set to be trained; wherein the sample set includes a plurality of sample images in spatial format; and performing format conversion processing on each of the sample images in the sample set according to the preset manner to obtain the frequency domain Format sample image; based on the frequency domain format sample image for model training processing to obtain the face recognition model.

It should be noted that the embodiment of the storage medium in this specification and the embodiment of the identity verification method based on privacy protection in this specification are based on the same inventive concept, so the specific implementation of this embodiment can refer to the aforementioned corresponding privacy protection-based embodiment. The implementation of the identity verification method will not be repeated here.

The foregoing describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than in the embodiments and still achieve desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown in order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In the 1990s, the improvement of a technology can be clearly distinguished between hardware improvements (for example, improvements in circuit structures such as diodes, transistors, switches, etc.) and software improvements (improvements in method flow). However, with the development of technology, the improvement of many methods and processes of today can be regarded as a direct improvement of the hardware circuit structure. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by the hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user's programming of the device. It is programmed by the designer to "integrate" a digital system on a piece of PLD, without having to ask the chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly realized by using "logic compiler" software, which is similar to the software compiler used in program development and writing, but before compilation The original code must also be written in a specific programming language, which is called Hardware Description Language (HDL), and there is not only one type of HDL, but many types, such as ABEL (Advanced Boolean Expression Language) , AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description), etc., currently most commonly used It is VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should also be clear to those skilled in the art that just a little bit of logic programming of the method flow in the above-mentioned hardware description languages and programming into an integrated circuit can easily obtain the hardware circuit that implements the logic method flow.

The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor. , Logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers. Examples of controllers include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as part of the memory control logic. Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code manner, it is entirely possible to program the method steps to make the controller use logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded logic. The same function can be realized in the form of a microcontroller or the like. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for realizing various functions can also be regarded as a structure within the hardware component. Or even, the device for realizing various functions can be regarded as both a software module for realizing the method and a structure within a hardware component.

The systems, devices, modules, or units explained in the foregoing embodiments may be specifically implemented by computer chips or entities, or implemented by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cell phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or Any combination of these devices.

For the convenience of description, when describing the above device, the functions are divided into various units and described separately. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same one or more software and/or hardware.

Those skilled in the art should understand that one or more embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

This specification is described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are used to generate It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.

In a typical configuration, the computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.

The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.

Computer-readable media includes permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

It should also be noted that the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or equipment including a series of elements includes not only those elements, but also Other elements that are not explicitly listed, or include elements inherent to such processes, methods, commodities, or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, commodity or equipment that includes the element.

One or more embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of this specification can also be practiced in distributed computing environments. In these distributed computing environments, tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

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 each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.

The above descriptions are only examples of this document, and are not intended to limit this document. For those skilled in the art, this document can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document shall be included in the scope of the claims of this document.

Claims

An identity verification method based on privacy protection, including:

Acquiring a user image in an airspace format of the user to be verified; wherein the user image includes the face of the user to be verified;

Performing format conversion processing on the user image according to a preset manner to obtain a target image in a frequency domain format;

Perform verification processing on the identity of the user to be verified according to the target image and the pre-trained face recognition model to obtain identity verification result information.
The method according to claim 1, wherein said performing format conversion processing on said user image according to a preset manner to obtain a target image in a frequency domain format comprises:

Preprocessing the user image to obtain an image to be converted;

Perform format conversion processing on the image to be converted according to a preset manner to obtain a target image in a frequency domain format.
The method according to claim 2, wherein the preprocessing the user image to obtain the image to be converted comprises:

Performing face detection processing on the user image according to a preset detection algorithm to obtain key position information of the face;

According to the key position information, the user image is calibrated to obtain the image to be converted.
The method according to claim 1, wherein the verification process on the identity of the user to be verified according to the target image and a pre-trained face recognition model includes:

Performing a living detection processing on the target image according to a pre-trained living detection model;

If the result of the living body detection processing is that the detection is passed, a face comparison process is performed on the target image according to a pre-trained face comparison model.
The method according to claim 1, after obtaining the identity verification result information, further comprising:

If the identity verification result information is that the verification is passed, obtain an encrypted template image;

Encrypting the target image by using the encrypted template image;

Save the encrypted target image.
The method according to claim 1, after obtaining the identity verification result information, further comprising:

If the identity verification result information is verified, the target image is encrypted according to a preset encryption algorithm;

Save the encrypted target image.
The method according to any one of claims 1-6, before the verification process is performed on the identity of the user to be verified according to the target image and a pre-trained face recognition model, the method further comprises:

Acquiring a sample set to be trained; wherein the sample set includes a plurality of sample images in spatial format;

Performing format conversion processing on each of the sample images in the sample set according to the preset manner to obtain a sample image in a frequency domain format;

Model training processing is performed based on the sample image in the frequency domain format to obtain the face recognition model.
An identity verification device based on privacy protection, including:

An obtaining module, which obtains a user image in an airspace format of the user to be verified; wherein the user image includes the face of the user to be verified;

A conversion module, which performs format conversion processing on the user image according to a preset method to obtain a target image in a frequency domain format;

The verification module performs verification processing on the identity of the user to be verified based on the target image and the pre-trained face recognition model, and obtains identity verification result information.
The device according to claim 8,

The conversion module preprocesses the user image to obtain an image to be converted;

Perform format conversion processing on the image to be converted according to a preset manner to obtain a target image in a frequency domain format.
The device according to claim 8,

The verification module performs a living detection processing on the target image according to a pre-trained living detection model;

If the result of the living body detection processing is that the detection is passed, a face comparison process is performed on the target image according to a pre-trained face comparison model.
The device according to claim 8, further comprising: a first storage module;

The first storage module acquires an encrypted template image when the identity verification result information is passed verification;

Encrypting the target image by using the encrypted template image;

Save the encrypted target image.
An identity verification device based on privacy protection, including:

Processor; and,

A memory arranged to store computer-executable instructions which, when executed, cause the processor to:

Acquiring a user image in an airspace format of the user to be verified; wherein the user image includes the face of the user to be verified;

Performing format conversion processing on the user image according to a preset manner to obtain a target image in a frequency domain format;

Perform verification processing on the identity of the user to be verified according to the target image and the pre-trained face recognition model to obtain identity verification result information.
A storage medium for storing computer-executable instructions, which, when executed, implement the following processes:

Acquiring a user image in an airspace format of the user to be verified; wherein the user image includes the face of the user to be verified;

Performing format conversion processing on the user image according to a preset manner to obtain a target image in a frequency domain format;

Perform verification processing on the identity of the user to be verified according to the target image and the pre-trained face recognition model to obtain identity verification result information.