CN112734436A

CN112734436A - Terminal and method for supporting face recognition

Info

Publication number: CN112734436A
Application number: CN202110025115.6A
Authority: CN
Inventors: 吕瑞
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2021-01-08
Filing date: 2021-01-08
Publication date: 2021-04-30

Abstract

The embodiment of the specification discloses a terminal and a method for supporting face recognition. The terminal includes: the device comprises an image sensor, an identity recognition module, a data protection module and a data sharing module; the method comprises the steps that an image sensor collects a first face image of a user; the identity recognition module is used for recognizing the first face image so as to determine the identity of the user; the data protection module is used for processing the first face image to generate a second face image with an identity recognition error with the first face image; and the data sharing module is used for replacing the first face image with the second face image and providing the second face image for an external service provider to use.

Description

Terminal and method for supporting face recognition

Technical Field

The present disclosure relates to the field of image recognition technologies, and in particular, to a terminal and a method for supporting face recognition.

Background

The rapid development of internet technology has also promoted the development of a wide variety of payment means. The face-brushing payment is a payment mode which is started and gradually popularized in recent years, the payment is completed by recognizing the identity of a user through a face, and the face-brushing payment is widely applied to places such as markets, supermarkets and self-service vending machines.

In the shop of merchant, the payment of brushing face is realized through dedicated terminal, and a current payment terminal of brushing face commonly used is similar with vertical small-size sweep the ink recorder and uses on arranging the cashier's desk in usually, generally not mobile, when needing to brush face, merchant side input the amount of money of receivable, then, the user with the face make up the terminal in front scan can, at this in-process, brush face payment application can obtain user's facial image. In practical applications, the face-brushing payment application comprises sub-applications which are developed and provided with services by external service providers, and some sub-applications request the face-brushing payment application to acquire a face image of a user for legal purposes.

Based on this, for the face-brushing payment application, a more secure response scheme to the face image acquisition request of the external service provider is required.

Disclosure of Invention

One or more embodiments of the present specification provide a terminal, a method, a device and a storage medium for supporting face recognition, so as to solve the following technical problems: for the face-brushing payment application, a more secure response scheme to the face image acquisition request of the external service provider is needed.

To solve the above technical problem, one or more embodiments of the present specification are implemented as follows:

one or more embodiments of the present specification provide a terminal supporting face recognition, including: the device comprises an image sensor, an identity recognition module, a data protection module and a data sharing module;

the image sensor is used for acquiring a first face image of a user;

the identity recognition module is used for recognizing the first face image so as to determine the identity of the user;

the data protection module is used for processing the first face image to generate a second face image with an identity recognition error with the first face image;

and the data sharing module is used for replacing the first face image with the second face image and providing the first face image for an external service provider to use.

One or more embodiments of the present specification provide a method for supporting face recognition, including:

acquiring a first face image of a user;

identifying the first facial image to determine an identity of the user;

processing the first face image to generate a second face image with an identity recognition error with the first face image;

and replacing the first face image with the second face image, and providing the second face image for an external service provider to use.

One or more embodiments of the present specification provide an apparatus for supporting face recognition, including:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to:

acquiring a first face image of a user;

identifying the first facial image to determine an identity of the user;

One or more embodiments of the present specification provide a non-transitory computer storage medium storing computer-executable instructions configured to:

acquiring a first face image of a user;

identifying the first facial image to determine an identity of the user;

At least one technical scheme adopted by one or more embodiments of the specification can achieve the following beneficial effects: the terminal supporting face recognition is used as a face-brushing payment terminal, for example, by processing a face image to be shared by an external service provider, a person and/or a machine are/is difficult to correctly recognize the identity of an original user from the processed face image, or the machine is even difficult to correctly recognize a face area from the processed face image, so that the data security is improved, the privacy of the user is protected, the external service provider is responded to more safely, the external service provider can still be helped to realize legal use of the face image to a certain extent, and the user experience is further improved.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic structural diagram of a terminal supporting face recognition according to one or more embodiments of the present disclosure;

fig. 2 is a schematic flow chart of a method for supporting face recognition according to one or more embodiments of the present disclosure;

fig. 3 is a schematic application scenario of the terminal in fig. 1 according to one or more embodiments of the present disclosure;

FIG. 4 is a detailed flow diagram of the method of FIG. 2 provided in one or more embodiments of the present disclosure;

fig. 5 is a schematic structural diagram of an apparatus for supporting face recognition according to one or more embodiments of the present disclosure.

Detailed Description

The embodiment of the specification provides a terminal, a method, equipment and a storage medium for supporting face recognition.

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.

In one or more embodiments of the present specification, there is provided a face-brushing payment terminal having a data protection function for human face image data, compared with the existing face-brushing payment terminal, the method can execute image processing operations such as interference, deformation and the like on the face image on the terminal, effectively reduces the significance of user identity characteristics and the like contained in the face image on the premise of still representing the face image, the processed face image replaces the original face image and is sent to the server side to prevent the recognition of people and/or machines and even the machine retrains the recognition effect which is hard to realize, in order to provide an external service provider, such as an independent software developer, for legitimate purposes, and thus, help to cut off possible ways of revealing user privacy directly at the terminal, helping to prevent the external service provider from directly revealing user privacy maliciously or non-maliciously.

The following is a detailed description based on such a concept.

Fig. 1 is a schematic structural diagram of a terminal supporting face recognition according to one or more embodiments of the present disclosure. The application scenes of the terminal are various, for example, the terminal is used for merchants, vending machines and the like as a face-brushing payment terminal, and is used for schools, enterprises, station squares and the like as a face-brushing access control or large-range face-brushing identification camera. For convenience of description, some embodiments below are mainly specifically described as a face-brushing payment terminal.

The terminal in fig. 1 includes: the image sensor 102, the identification module 104, the data protection module 106, and the data sharing module 108. For the sake of brevity, only the names of these components will be referred to hereafter and reference numerals will be omitted. The image sensor comprises special hardware, such as a camera, and other components are realized in a software and hardware combined mode, or realized in a software mode based on a Central Processing Unit (CPU), so that the implementation cost of the latter scheme is low, the scheme can be realized on some existing terminals through software upgrading without adding extra hardware, and the scheme is beneficial to popularization and application.

In one or more embodiments of the present description, the above-described terminal is generally not required to be manually moved when in use. For example, it may be used on a checkout counter, or the terminal may be a robot with a road wheel, intelligently navigating automatically to use while moving, and so on.

In one or more embodiments of the present specification, the terminal has at least a face recognition function, and may further have a function of performing a subsequent specific service based on a recognition result, for example, a payment service, a vending service, a shopping guide service, a ticket checking service, a security check service, a garbage collection service, and the like.

The actions involved in the above-described several components of the terminal include the following:

the method comprises the steps that an image sensor collects a first face image of a user; the identity recognition module is used for recognizing the first face image so as to determine the identity of the user; the data protection module is used for processing the first face image to generate a second face image with an identity recognition error with the first face image; and the data sharing module is used for replacing the first face image with the second face image and providing the second face image for an external service provider to use.

The collected first face image can be temporarily stored in a memory, and can be timely cleared after subsequent necessary processing (such as user identity authentication, data protection processing and the like) is carried out, and the first face image is not stored in the power-off nonvolatile storage of the terminal, so that the user privacy can be prevented from being leaked from the terminal.

In one or more embodiments of the present specification, when a user wants to perform face brushing identity authentication, an image sensor collects a face image of the user in real time, which is called a first face image, so as to be distinguished from a face image obtained by subsequent processing. The image sensor may keep actively acquiring images near the terminal, rather than acquiring them in real time after being triggered, and then waiting for the next trigger. The latter scheme typically triggers image capture by the user or merchant instructing payment to begin (e.g., clicking on a "pay" button shown on the order page).

In one or more embodiments of the present specification, a face image is easily used illegally as privacy data that is intuitive for a user, resulting in a loss of the user. Based on this, in order to protect the user privacy, the data protection module processes the first face image with a view to preventing human and/or machine recognition. The specific target processing is determined by the use requirement of the subsequent external service provider, and at least the second face image generated after the processing can still meet the use requirement to a certain extent.

The target is different, and the adopted processing means and the processed image effect are different.

Assuming that the target is to prevent human recognition, it should be difficult for the naked eye to determine that the face in the second face image is the face of the user (referred to as the original user) in the first face image, and the two faces may be similar but difficult to judge to be the same person, and such second face image may certainly meet certain legal use requirements of the outside service provider. For example, an outside facilitator may simply serve it as an exemplary collateral for its own services; for another example, an external service provider may only need a user to have a more abstract face, and may lose many specific details, and in an application scenario, the more abstract face is used as a base layer to generate a face beautifying effect image layer; as another example, a real-world map for generating street views retains people who appear on the map, but does not reveal the identity of those people; and so on.

Assuming that the aim is to prevent machine recognition, it should be difficult for the machine to determine that the face in the second face image is the face of the user (called the original user) in the first face image, or even to determine that the second face image is an image containing a face. For such a second face image, it is still possible, if desired, to achieve that although the machine is difficult to recognize, however, the user can be identified correctly with naked eyes, and the privacy of the user can be protected under some application scenes by the processing, for example, an external service provider obtains a large amount of second face images for splicing large photos for promotion and serving as game materials, or for protecting some other important data as obfuscated data, etc., such massive data is difficult to handle manually, must be able to be handled by the machine, while the user identity is not exposed to the machine, in this case, it is difficult for a person who wants to do a malicious job to rely on a machine, and if relying on a human power, although the corresponding user may be recognized from the single second face image by naked eyes, however, the user is not necessarily a malicious target user, and it is difficult to obtain a result that is truly valuable to the malicious user by manpower because of the large number of images.

Similarly, assuming that both the human recognition hindrance and the machine recognition hindrance are targeted, the generated second face image needs to meet the requirements corresponding to both types of targets.

In one or more embodiments of the present disclosure, the identification error includes an error of identification accuracy and an error of identification efficiency, both of which contribute to protecting user privacy and increasing difficulty of doing malicious activities.

In addition, the identification error may also include an error of the number of identification results, for example, assuming that the first face image only includes one face, more different faces are randomly added to the first face image through processing (for example, 8 other faces are added, and 9 faces are included in the generated second face image), so that the original face is not significant compared with the added face, and thus, it is possible to prevent a malicious party from identifying the user identity, and even if the malicious party can identify the user identity of some faces, it is still difficult to accurately associate the faces and the user identity with some other sensitive data (for example, transaction data, etc.), thereby helping to suppress some malicious actions.

In one or more embodiments of the present disclosure, unlike some solutions, the acquired face image is provided to an external service provider, and after the face image is processed as described above, the second face image is used to replace the first face image and provided to the external service provider. The terminal can directly provide the second face image or indirectly provide the second face image through a specified server, and the corresponding relation between the terminal and the second face image provided by the terminal and the corresponding relation between the terminal and an external provider legally obtaining the second face image are established for tracing.

Through the terminal in fig. 1, the face image shared by the external service provider is processed, so that it is difficult for people and/or machines to correctly recognize the identity of the original user from the processed face image, or even for machines to correctly recognize the face region from the processed face image, thereby contributing to improving data security, protecting user privacy, responding to the external service provider more safely, still being capable of helping the external service provider to realize legal use of the face image to a certain extent, and further contributing to improving user experience.

Based on the terminal of fig. 1, the present specification also provides some specific embodiments and extensions of the terminal, and the following description is continued.

In one or more embodiments of the present description, if the terminal is used as a face-brushing payment terminal, the terminal further includes a payment module. The identity recognition module is used for responding to the instruction of the user and recognizing the first face image collected by the image sensor so as to determine the identity of the user; and the payment module deducts money from the account of the user according to the identity of the user so as to complete payment.

In the mode, the user actively triggers the face recognition and money deduction process so as to prevent inconvenience caused by mistaken money deduction. More conveniently, the face recognition process can be performed automatically in advance without being triggered by the user, and the money deduction process is triggered automatically according to the actual consumption condition of the user.

In one or more embodiments of the present specification, in the current big data era, a large amount of even mass data are processed by a small amount of manual work, and the mass data are often processed through a machine learning model, so that the identity of a user is recognized through hindering the machine learning model, privacy protection is achieved, an effect is good, and practical value is also provided. Based on the thought, the data protection module generates a second human face image with an identity recognition error between the machine learning model and the first human face image by processing the first human face image.

More specifically, an interference mask may be used to add interference to the first face image, and the interference mask may include pixels that are helpful to hinder extraction of the face features, such as stripes, blurred shadows, color blocks, and cracks. For example, the data protection module includes an interference processing module, which obtains an interference mask containing irregular stripes, and generates the second face image by attaching the interference mask to the first face image. In order to improve efficiency, a plurality of interference masks are generated in advance, and when the interference masks are required to be used, the interference masks are selected and superposed on the first face image according to a certain strategy to realize interference adding. In order to achieve a better interference effect, for some first face images, by extracting features in the first face images, an interference mask special for the first face images is generated in real time according to the features.

In one or more embodiments of the present description, the data protection module includes an interference generation module for generating interference data (e.g., interference masks, random noise, etc.). Taking the generation of the interference mask as an example, the interference mask for the machine learning model is generated through countermeasure training, for example, countermeasure training is implemented by using a countermeasure generation network, a target set for the determiner is to successfully recognize the user identity of the input face image, a target set for the generator is to generate the interference mask capable of successfully hindering the recognition of the determiner, or to generate the face image on which the interference mask has been superimposed.

In one or more embodiments of the present specification, in order to verify the interference effect and ensure reliability, before replacing the first face image with the second face image and providing the second face image to an external service provider for use, the identity recognition module attempts to recognize the second face image in an attempt to obtain a recognition result inconsistent with the identity of the original user, and if a desire is met (for example, the probability of recognizing the identity of the original user in the second face image is lower than a set threshold), the interference effect is proved to be good, otherwise, the first face image may be reprocessed, or more interference may be added to the second face image. More reliably, the second face image is verified by adopting a machine learning model except the terminal to determine that the identity recognition error reaches the expectation, and then the second face image is shared to the outside.

In one or more embodiments of the present description, more effective interference data is utilized, so that even after the machine model is retrained from the second face image, it is still difficult to correctly identify the original user identity from the second face image or other subsequent second face images. For example, the machine learning model may be trained by performing trial adjustment on the interference data for a plurality of times and using a large number of correspondingly generated second face images as training data, so that the training process is difficult to converge finally, and interference data with better effect and more universality for the machine learning model is obtained.

In one or more embodiments of the present disclosure, the face region in the first face image may be directly processed to change the appearance of the face itself to prevent visual recognition, but of course, such processing may also help to prevent machine recognition.

For example, the data protection module may include an image transformation module; and the image transformation module generates a second face image by carrying out perspective transformation on the first face image. More specifically, the second face image is generated by adjusting the shape of and the distance between the five sense organs on the face in a perspective transformation (e.g., lengthening the mouth, changing the face shape, distorting the nose, adjusting the eye distance, etc.) in a face image.

For another example, the data protection module may include an image replacement module; and the image replacement module is used for identifying the characteristics of one or more local areas in the face area and then replacing the local areas with corresponding areas in other face images so as to generate a second face image. In order to obtain a more natural effect, the face local area of other users with similar growth to a certain extent can be used for replacement. Similarly, in addition to the long-term similarity, the similarity of the behavior features is also considered, after the identity of the original user is recognized, the behavior features are extracted according to the acquired behavior data (such as transactions, trips and the like) of the original user, then other users with similar behavior features are matched, the corresponding region in the first facial image is replaced by the image of the local region such as a certain five-officer in the facial image of other users, so as to generate a second facial image, the scheme has the advantage of more targeted defense for the following possible malicious behaviors, because the malicious behaviors are often performed according to the behaviors of the original user, for example, the user account is stolen according to the transaction behaviors of the original user, or a false transaction cheating bureau and the like are constructed, so that the second facial image is processed based on the similar behavior features, so that the malicious parties are easy to confuse the user, thereby effectively preventing execution of a malicious act.

Some processing means of the first face image are exemplarily described above, and these means can be used together with each other to achieve better privacy protection effect.

In one or more embodiments of the present specification, a family image set pre-registered by a user is received, wherein the family image set comprises facial images of a plurality of members in the family of the user. Based on this, the first face image of the user is processed, the face images of other members can be acquired in the family image set as the second face image, or the second face image is obtained by fusing or replacing the features in the face images of other members with the first face image. Therefore, the privacy of the user is protected, and the use value of the second face image is improved. The user can construct other image sets similar to the family image set according to the requirement of the user, and the members of the image sets have more extensive pre-negotiation selections, such as selecting the close friends of the user, the boss of the user and the like. The above steps are performed by, for example, a data protection module or other modules added separately.

In one or more embodiments of the present disclosure, after determining an external service provider needing to share data, a facial image registered by the external service provider may be obtained (which reflects privacy of people in the external service provider and may be specified by a platform of a sharing party), and the first facial image is processed according to the facial image registered by the external service provider to obtain a second facial image, where the processing manner may refer to some manners listed above and is not described again. In this case, the second face image also contains some information of the external service provider, even partial privacy information, so that the second face image is prevented from being actively revealed by the external service provider, and the defense enthusiasm and responsibility of the external service provider are improved.

In one or more embodiments of the present specification, based on the second face image, if the second face image is generated in the processing, and the processing such as feature replacement or fusion is performed, the second face image includes features of multiple users. The payment authentication is performed by using the second face image, specifically, for example, after a payment authentication process of a certain transaction is triggered, the face images of the multiple users need to be collected in real time (instead of collecting the face image of a certain user), then the collected face images are respectively compared with the second face image instead of the face images registered in advance by the users (even the face images are not registered in advance, or only the images in the face part area are registered), and then all comparison results are comprehensively considered, for example, if the comprehensive similarity exceeds a set threshold, the authentication is considered to be passed, and payment is deducted from a designated account (for example, the account of one of the multiple users), so that a single-account deduction function based on the collective fuzzy authentication is realized. In this case, the privacy of the multiple users can be further protected, and the conditions required to reach payment may be higher, contributing to increased user asset security.

Some of the above flow descriptions omit the execution main body and can be executed by existing or expanded modules.

The composition and the working principle of the terminal are exemplarily described above, in practical application, the division schemes of the components are various and are not limited to the above examples, as long as corresponding steps can be executed, for example, the data protection module and the data sharing module may be fused into the same module, the data protection module may include a confrontation training module, and the data protection module may also be disposed at a server instead of the terminal, and the like. Based on the same idea, one or more embodiments of the present specification further provide a flowchart of a method for supporting face recognition, as shown in fig. 2.

The flow in fig. 2 may include the following steps:

s202: a first face image of a user is acquired.

S204: and identifying the first face image to determine the identity of the user.

S206: and processing the first face image to generate a second face image with an identity recognition error with the first face image.

S208: and replacing the first face image with the second face image, and providing the second face image for an external service provider to use.

Optionally, the recognizing the first face image to determine the identity of the user specifically includes:

identifying the first facial image to determine an identity of the user in response to the user's instruction;

the method further comprises the following steps:

and deducting money from the account of the user according to the identity of the user to complete payment.

Optionally, the processing the first face image to generate a second face image having an identification error with the first face image specifically includes:

and processing the first face image to generate a second face image with an identity recognition error between the machine learning model and the first face image.

Optionally, before replacing the first facial image with the second facial image and providing the second facial image to an external service provider for use, the method further includes:

and identifying the second face image to obtain an identification result inconsistent with the identity of the user.

and acquiring an interference mask, and attaching the interference mask to the first face image to generate the second face image.

Optionally, the obtaining the interference mask specifically includes:

the interference mask is generated by countermeasure training.

and generating a second face image with an identity recognition error with the first face image by carrying out perspective transformation on the first face image.

Optionally, the generating a second face image with an identification error with the first face image by performing perspective transformation on the first face image specifically includes:

and generating a second face image with identity recognition error with the first face image by adjusting the shape of five sense organs on the face and the distance between the five sense organs in the first face image through the perspective transformation.

Optionally, the method is used for a specified application on the terminal, the specified application containing a sub-application provided by an external independent software developer;

the replacing of the first face image by the second face image is provided for an external service provider, and the replacing specifically comprises:

and replacing the first face image with the second face image, and sending the second face image to the server of the specified application so that the server can provide the second face image for the external independent software developer to use.

In light of the foregoing description, one or more embodiments of the present specification provide a schematic view of an application scenario of the terminal in fig. 1, as shown in fig. 3.

In fig. 3, the terminal belongs to a shop of a merchant side, and a face privacy protection function is supported by a specific application (for example, a face-brushing payment application) installed. The terminal collects a first face image of a certain user, then carries out privacy protection processing, uploads the first face image to the server side, and then the first face image is legally shared to the outside through the server side according to a certain strategy. In fig. 3, compared with the first face image, the interference mask containing irregular stripes is superimposed on the second face image, and the eye distance is increased and the mouth is lengthened through perspective transformation, so that the machine learning model is not easy to correctly recognize.

Fig. 4 is a detailed flow diagram of the method in fig. 2 according to one or more embodiments of the present disclosure. In the scenario of fig. 4, the terminal is placed at a store door or a cash register of a merchant and is used as a face-brushing payment terminal, and the specific application includes a sub-application (e.g., "applet" embedded in the specific application) provided by an external independent software developer.

The flow in fig. 4 includes the following steps:

s402: the interference mask is generated in advance by countermeasure training.

S404: a first face image of a user is acquired.

S406: in response to an instruction by the user, the first face image is recognized to determine the identity of the user.

S408: and deducting money from the account of the user according to the identity of the user to complete the payment.

S410: by subjecting the first face image to perspective transformation and attaching an interference mask, a second face image from which it is difficult to correctly recognize the user is generated.

S412: and sending the second face image to a server, and sending the second face image to an external independent software developer for use by the server.

Based on the same idea, one or more embodiments of the present specification further provide an apparatus corresponding to the above method, as shown in fig. 5.

Fig. 5 is a schematic structural diagram of an apparatus for supporting face recognition according to one or more embodiments of the present specification, where the apparatus includes:

at least one processor; and the number of the first and second groups,

acquiring a first face image of a user;

identifying the first facial image to determine an identity of the user;

The processor and the memory may communicate via a bus, and the device may further include an input/output interface for communicating with other devices.

Based on the same idea, one or more embodiments of the present specification provide a non-volatile computer storage medium storing computer-executable instructions configured to:

acquiring a first face image of a user;

identifying the first facial image to determine an identity of the user;

and replacing the first face image with the second face image, and providing the second face image for an external service provider to use so as to realize privacy protection of the user.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, the present specification embodiments may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

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

The memory may include forms of volatile 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 a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, 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, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and for the relevant points, reference may be made to the partial description of the embodiments of the method.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The above description is merely one or more embodiments of the present disclosure and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments of the present description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A terminal supporting face recognition, comprising: the device comprises an image sensor, an identity recognition module, a data protection module and a data sharing module;

the image sensor is used for acquiring a first face image of a user;

2. The terminal of claim 1, further comprising: a payment module;

the identity recognition module is used for responding to the instruction of the user and recognizing the first face image so as to determine the identity of the user;

and the payment module deducts money from the account of the user according to the identity of the user so as to complete payment.

3. The terminal of claim 1, wherein the data protection module generates a second facial image having an identification error with respect to the first facial image for a machine learning model by processing the first facial image.

4. The terminal of claim 3, wherein the identity recognition module is configured to recognize the second facial image to obtain a recognition result inconsistent with the identity of the user before the second facial image is used to replace the first facial image for an external service provider.

5. The terminal of claim 3, the data protection module comprising an interference processing module;

the interference processing module acquires an interference mask, and generates the second face image by attaching the interference mask to the first face image.

6. The terminal of claim 5, the data protection module comprising an interference generation module;

the interference generating module generates the interference mask through countermeasure training.

7. The terminal of claim 1, the data protection module comprising an image transformation module;

the image transformation module generates the second face image by performing perspective transformation on the first face image.

8. The terminal of claim 7, wherein the image transformation module generates the second facial image by adjusting the shape of five sense organs and the distance between five sense organs on the face in the first facial image with the perspective transformation.

9. The terminal of claim 1, wherein the data sharing module belongs to a designated application on the terminal, and the designated application comprises a sub-application provided by an external independent software developer;

the data sharing module sends the second face image to the server side of the specified application, so that the server side can provide the second face image for an external independent software developer to use, and privacy protection of the user is achieved.

10. A method of supporting face recognition, comprising:

acquiring a first face image of a user;

identifying the first facial image to determine an identity of the user;

11. The method according to claim 10, wherein the recognizing the first face image to determine the identity of the user comprises:

the method further comprises the following steps:

12. The method according to claim 10, wherein the generating a second face image having an identification error with the first face image by processing the first face image specifically includes:

13. The method of claim 12, wherein said replacing said first facial image with said second facial image further comprises, prior to providing said second facial image to an external service provider for use:

14. The method according to claim 12, wherein the generating a second face image having an identification error with the first face image by processing the first face image specifically includes:

15. The method according to claim 14, wherein the obtaining the interference mask specifically comprises:

the interference mask is generated by countermeasure training.

16. The method according to claim 10, wherein the generating a second face image having an identification error with the first face image by processing the first face image specifically includes:

17. The method according to claim 16, wherein generating a second face image having an identification error with the first face image by performing perspective transformation on the first face image includes:

18. The method of claim 10, the method being used for a specified application on the terminal, the specified application containing sub-applications provided by an external independent software developer;

and replacing the first face image with the second face image, and sending the second face image to the server of the specified application, so that the server can provide the second face image for an external independent software developer to use, and privacy protection of the user is realized.