Identity authentication method and device, storage device and electronic equipment

Abstract

The embodiment of the invention discloses an identity authentication method, which does not perform identity authentication on a user based on a fingerprint locally stored in a mobile terminal, but performs identity authentication on the user based on a standard fingerprint image acquired by a contact acquisition method in an authority after acquiring a to-be-authenticated image by a non-contact acquisition method. The gap of fingerprints collected by two different methods in application is broken, and the authentication credibility of the mobile terminal is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an identity authentication method, device, storage device and electronic device. Background Art

[0002] Currently, methods for identity authentication using biometric information such as fingerprints have been widely used in various fields, and fingerprints are used as an example for explanation below.

[0003] Many mobile terminals such as mobile phones and tablets have fingerprint recognition functions, which are usually used in application scenarios such as power on and unlocking, and payment. However, the principle of these fingerprint recognition functions is usually: the mobile terminal uses its own software and hardware to collect the user's fingerprint, and saves the collected fingerprint locally in the mobile terminal. When identifying the user, the fingerprint that has been saved locally is used to identify the user.

[0004] The user's fingerprints are also stored in authoritative institutions in other scenarios. The fingerprints stored by these authoritative institutions are often collected and stored through professional contact equipment. For example, when a user applies for an ID card or handles certain financial services at a bank, it may be necessary to collect fingerprints through professional contact fingerprint collection equipment and store them in an authoritative institution.

[0005] It can be seen from this that there is a natural gap between the non-contact fingerprint collection method based on mobile terminals and the contact fingerprint collection method based on authoritative institutions. When performing fingerprint recognition, the mobile terminal cannot use the fingerprint stored in the authoritative institution to identify the user, which makes the authentication credibility of the mobile terminal low. Summary of the invention

[0006] The embodiments of this specification provide a method, device, storage device and electronic device for identity authentication to partially solve the problems existing in the above-mentioned prior art.

[0007] The embodiments of this specification adopt the following technical solutions:

[0008] This specification provides a method for identity authentication, the method comprising:

[0009] Collecting the user's fingerprint image to be authenticated by a non-contact collection method;

[0010] Extracting fingerprint features to be authenticated from the fingerprint image to be authenticated;

[0011] The user is authenticated based on the fingerprint features to be authenticated and the standard fingerprint features extracted from a pre-stored standard fingerprint image, wherein the standard fingerprint image is a fingerprint image pre-stored in an authoritative institution and collected by a contact collection method.

[0012] Optionally, collecting the user's fingerprint image to be authenticated by a non-contact collection method specifically includes:

[0013] The user's fingerprint image to be authenticated is collected through the camera.

[0014] Optionally, extracting the fingerprint feature to be authenticated from the fingerprint image to be authenticated specifically includes:

[0015] Acquiring environmental features when the fingerprint image to be authenticated is collected, wherein the environmental features include at least one of light features and background noise features;

[0016] Determining, according to the environmental characteristics, an image quality representation value of the fingerprint image to be authenticated;

[0017] If the image quality representation value meets the preset condition, the fingerprint feature to be authenticated is extracted from the fingerprint image to be authenticated.

[0018] Optionally, determining the image quality representation value of the fingerprint image to be authenticated according to the environmental characteristics specifically includes:

[0019] The environmental features and the fingerprint image to be authenticated are input into a pre-trained image quality assessment model so that the image quality assessment model determines the texture clarity quality and the degree of deflection of the fingerprint image to be authenticated, and obtains the image quality characterization value of the fingerprint image to be authenticated based on the texture clarity quality and the degree of deflection.

[0020] Optionally, extracting the fingerprint feature to be authenticated from the fingerprint image to be authenticated specifically includes:

[0021] Performing liveness detection on the fingerprint image to be authenticated;

[0022] If the liveness detection is passed, the fingerprint feature to be authenticated is extracted from the fingerprint image to be authenticated.

[0023] Optionally, extracting the fingerprint feature to be authenticated from the fingerprint image to be authenticated specifically includes:

[0024] Input the fingerprint image to be authenticated into a pre-trained fingerprint feature extraction model to extract the machine learning fingerprint feature to be authenticated from the fingerprint image to be authenticated through the fingerprint feature extraction model; and extract the MCC fingerprint feature to be authenticated from the fingerprint image to be authenticated;

[0025] Fusion of the machine learning fingerprint feature to be authenticated and the MCC fingerprint feature to be authenticated as the fingerprint feature to be authenticated;

[0026] Extract standard fingerprint features from pre-saved standard fingerprint images, including:

[0027] Inputting the standard fingerprint image into a pre-trained fingerprint feature extraction model to extract standard machine learning fingerprint features from the standard fingerprint image through the fingerprint feature extraction model; and extracting standard MCC fingerprint features from the standard fingerprint image;

[0028] The standard machine learning fingerprint feature and the standard MCC fingerprint feature are integrated as the standard fingerprint feature.

[0029] Optionally, a fingerprint feature extraction model is pre-trained, specifically including:

[0030] Acquire a sample fingerprint image of a sample user and a sample standard fingerprint image of the sample user, wherein the sample fingerprint image is collected by a non-contact collection method, and the sample standard fingerprint image is collected by a contact collection method;

[0031] Extracting sample machine learning fingerprint features from the sample fingerprint image and extracting sample standard machine learning fingerprint features from the sample standard fingerprint image through the fingerprint feature extraction model to be trained; and extracting sample MCC fingerprint features from the sample fingerprint image and extracting sample standard MCC fingerprint features from the sample standard fingerprint image;

[0032] The sample machine learning fingerprint feature and the sample MCC fingerprint feature are integrated to obtain the sample fingerprint feature; the sample standard machine learning fingerprint feature and the sample standard MCC fingerprint feature are integrated to obtain the sample standard fingerprint feature;

[0033] Calculating a loss value according to the sample fingerprint feature, the sample standard fingerprint feature and a preset similarity loss function;

[0034] The fingerprint feature extraction model to be trained is trained according to the loss value.

[0035] This specification provides an identity authentication system, the system comprising: a terminal, a remote server;

[0036] The terminal collects the user's fingerprint image to be authenticated by a non-contact collection method, and sends the fingerprint image to be authenticated to the remote server;

[0037] The remote server extracts the fingerprint features to be authenticated from the fingerprint image to be authenticated; and performs identity authentication on the user based on the fingerprint features to be authenticated and the standard fingerprint features extracted from the pre-saved standard fingerprint image, wherein the standard fingerprint image is a fingerprint image pre-saved in an authoritative institution and collected by a contact collection method.

[0038] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned identity authentication method is implemented.

[0039] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned identity authentication method when executing the program.

[0040] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:

[0041] The embodiments of this specification disclose a method for identity authentication, which no longer authenticates the user based on the fingerprint stored locally on the mobile terminal. Instead, after the image to be authenticated is collected by a non-contact collection method, the user is authenticated based on a standard fingerprint image collected by a contact collection method in an authoritative organization, thereby breaking the application barrier of fingerprints collected by two different methods and improving the authentication credibility of the mobile terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0043] Figure 1 A flowchart of an identity authentication method provided in an embodiment of this specification;

[0044] Figure 2 A schematic diagram of a mobile terminal displaying prompt information provided in an embodiment of this specification;

[0045] Figure 3 A schematic diagram of the system structure of an identity authentication provided in an embodiment of this specification;

[0046] Figure 4 A schematic diagram of the structure of an identity authentication device provided in an embodiment of this specification;

[0047] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0049] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0050] When applying for identity cards, large-value transfers, bank card opening and other services that require strict identity authentication, users are often required to go to designated institutions in person to handle offline. This is because although mobile terminals can realize fingerprint authentication, the principle is to use the fingerprint collected by the mobile terminal using its own non-professional collection equipment and non-professional collection methods as the standard fingerprint to realize the fingerprint authentication function, and the credibility of the authentication is low. Therefore, if the above-mentioned services with strict identity authentication requirements are migrated online, the mobile terminal will need to perform fingerprint authentication on the user. Even if the mobile terminal authenticates the user's identity through this fingerprint authentication function, it will bring great risks to these services due to the low credibility of its authentication.

[0051] To this end, an embodiment of this specification provides a method for identity authentication.

[0052] Figure 1 The following is a flowchart of an identity authentication method in this specification, which may include the following steps:

[0053] S100: Collecting the user's fingerprint image to be authenticated by a non-contact collection method.

[0054] In the embodiments of this specification, the system for implementing the identity authentication method may include a mobile terminal (such as a mobile phone, a tablet computer, etc.), or may include a mobile terminal and a remote server at the same time. Figure 1 The identity authentication method shown is used as an example for explanation.

[0055] The mobile terminal can collect the user's fingerprint image through a non-contact collection method as the fingerprint image to be authenticated. Among them, the non-contact collection method described in the embodiments of this specification refers to a method for collecting fingerprint images without contacting the user's finger. The non-contact collection method does not use any fingerprint collector and can directly collect the user's fingerprint image to be authenticated through the mobile terminal's own camera.

[0056] After the mobile terminal collects the fingerprint image to be authenticated, it sends the fingerprint image to be authenticated to the remote server.

[0057] S102: Extracting fingerprint features to be authenticated from the fingerprint image to be authenticated.

[0058] After the remote server receives the fingerprint image to be authenticated sent by the mobile terminal, it can extract fingerprint features from the fingerprint image to be authenticated as the fingerprint features to be authenticated.

[0059] It should be noted that the remote server in this specification can extract fingerprint features (hereinafter referred to as machine learning fingerprint features to be authenticated) from the fingerprint image to be authenticated through a pre-trained fingerprint feature extraction model. In order to further improve the credibility of identity authentication, the fingerprint features to be authenticated described in this specification can be a fusion feature that combines the machine learning fingerprint features to be authenticated and the Minutia Cylinder-Code (MCC) fingerprint features to be authenticated.

[0060] Specifically, the remote server may input the fingerprint image to be authenticated into a pre-trained fingerprint feature extraction model, so as to extract the machine learning fingerprint feature to be authenticated from the fingerprint image to be authenticated through the fingerprint feature extraction model, and extract the MCC fingerprint feature to be authenticated from the fingerprint image to be authenticated, and fuse the machine learning fingerprint feature to be authenticated and the MCC fingerprint feature to be authenticated as the fingerprint feature to be authenticated. The time sequence of extracting the machine learning fingerprint feature to be authenticated and extracting the MCC fingerprint feature to be authenticated is not particular.

[0061] When fusing the machine learning fingerprint feature to be authenticated with the MCC fingerprint feature to be authenticated, the dimensions of the machine learning fingerprint feature to be authenticated and the MCC fingerprint feature to be authenticated can be adjusted to the same dimension first, and then the two can be fused by the maximum pooling, minimum pooling or average pooling method. Of course, the machine learning fingerprint feature to be authenticated and the MCC fingerprint feature to be authenticated can also be directly connected (concat) as the fused fingerprint feature to be authenticated. Those skilled in the art should understand that the identity authentication method of this specification can be implemented by using any method to fuse the machine learning fingerprint feature to be authenticated and the MCC fingerprint feature to be authenticated.

[0062] The reason why this manual does not use machine learning fingerprint features or MCC fingerprint features alone, but needs to integrate the two, is that when extracting MCC fingerprint features, it is necessary to extract them from fingerprint images collected by professional contact fingerprint collectors. The reliability of extracting MCC fingerprint features from fingerprint images collected by non-contact collection methods is not high, and the interpretability of machine learning fingerprint features is not very strong. Therefore, in order to maximize the credibility of identity authentication, this manual integrates the two features as the basis for identity authentication.

[0063] S104: Authenticate the user according to the fingerprint feature to be authenticated and the standard fingerprint feature extracted from the pre-stored standard fingerprint image.

[0064] The standard fingerprint image is a fingerprint image collected by a contact collection method and stored in an authoritative institution in advance. That is, the standard fingerprint image is a fingerprint image collected by a contact fingerprint collector and stored in an authoritative institution.

[0065] In the embodiment of the present specification, the remote server also needs to extract standard fingerprint features from the pre-saved standard fingerprint image. Similar to the above step S102, the extracted standard fingerprint features are also fusion features of standard machine learning fingerprint features and standard MCC fingerprint features. The remote server needs to use the same fingerprint feature extraction model to extract standard machine learning fingerprint features.

[0066] Specifically, the remote server may first obtain the standard fingerprint image of the user stored in the authority, and input the standard fingerprint image into a pre-trained fingerprint feature extraction model to extract the standard machine learning fingerprint feature from the standard fingerprint image through the fingerprint feature extraction model, and extract the standard MCC fingerprint feature from the standard fingerprint image, and fuse the standard machine learning fingerprint feature and the standard MCC fingerprint feature as the standard fingerprint feature. Among them, the time sequence of extracting the standard machine learning fingerprint feature and extracting the standard MCC fingerprint feature is not particular. The method of fusing the standard machine learning fingerprint feature and extracting the standard MCC fingerprint feature is the same as the method of fusing the machine learning fingerprint feature to be authenticated and the MCC fingerprint feature to be authenticated in step S102, and will not be repeated here.

[0067] It should be noted that the remote server extracts the fingerprint features to be authenticated from the fingerprint image to be authenticated (ie step S102) and extracts the standard fingerprint features from the standard fingerprint image in no particular order.

[0068] After the remote server extracts the fingerprint features to be authenticated and the standard fingerprint features respectively, it can authenticate the user based on the fingerprint features to be authenticated and the standard fingerprint features. Specifically, the similarity between the fingerprint features to be authenticated and the standard fingerprint features can be calculated. If the similarity is higher than the set threshold, the authentication is passed, otherwise the authentication fails. The similarity can be represented by Euclidean distance or cosine distance.

[0069] In addition, the above-mentioned fingerprint feature extraction model can be pre-trained by a comparative learning method. Specifically, a sample fingerprint image of a sample user and a sample standard fingerprint image of the sample user can be obtained, wherein the sample fingerprint image is collected by a non-contact collection method, and the sample standard fingerprint image is collected by a contact collection method; through the fingerprint feature extraction model to be trained, a sample machine learning fingerprint feature is extracted from the sample fingerprint image, and a sample standard machine learning fingerprint feature is extracted from the sample standard fingerprint image; and, a sample MCC fingerprint feature is extracted from the sample fingerprint image, and a sample standard MCC fingerprint feature is extracted from the sample standard fingerprint image; the sample machine learning fingerprint feature and the sample MCC fingerprint feature are fused to obtain a sample fingerprint feature; the sample standard machine learning fingerprint feature and the sample standard MCC fingerprint feature are fused to obtain a sample standard fingerprint feature; a loss value is calculated based on the sample fingerprint feature, the sample standard fingerprint feature and a preset similarity loss function; and the fingerprint feature extraction model to be trained is trained based on the loss value. Among them, the similarity between the sample fingerprint feature and the sample standard fingerprint feature is negatively correlated with the loss value of the loss function, that is, the higher the similarity between the sample fingerprint feature and the sample standard fingerprint feature, the lower the loss value, and vice versa.

[0070] The device for training the fingerprint feature extraction model can be the remote server itself or other devices. After the fingerprint feature extraction model is trained using the above training method, the fingerprint feature extraction model can be deployed in the remote server.

[0071] Through the above method, the mobile terminal no longer authenticates the user based on the fingerprint collected by the contactless collection method and stored locally, but after collecting the image to be authenticated by the contactless collection method, authenticates the user based on the standard fingerprint image collected by the contact collection method in the authority, breaking the application barriers between the fingerprints collected by the two different methods and improving the authentication credibility of the mobile terminal. When the business with strict identity authentication requirements is migrated to the online, the mobile terminal can collect the user's fingerprint image to be authenticated by the contactless collection method and send it to the remote server. The remote server extracts the fingerprint features to be authenticated from the fingerprint image to be authenticated, obtains the standard fingerprint image of the user collected by the contact collection method from the authority, extracts the standard fingerprint features from the standard fingerprint image, and finally authenticates the user based on the fingerprint features to be authenticated and the standard fingerprint features, and then transmits the authentication results to the business party that executes these businesses with strict identity authentication requirements, so that the business party continues to execute subsequent businesses based on the authentication results.

[0072] In the embodiments of this specification, when the mobile terminal collects the user's fingerprint image to be authenticated by a non-contact collection method, it can first display prompt information to the user, and the prompt information is used to prompt the user to collect the finger and collection method to be collected, such as Figure 2 As shown. Figure 2 In the example, "Please place your right index finger in the circle and take a photo" is a prompt message, which is used to prompt the user that the finger to be collected is the right index finger, and the collection method is to place the front of the right index finger in the circle and take a photo. Of course, those skilled in the art should understand that which finger to be collected needs to be determined based on the finger corresponding to the standard fingerprint image pre-stored in the authority.

[0073] In addition, after the mobile terminal collects the fingerprint image to be authenticated, it can also first perform quality detection and liveness detection on the fingerprint image to be authenticated. After both the quality detection and liveness detection are passed, it is sent to the remote server to extract the fingerprint features to be authenticated. The mobile terminal can also directly send the fingerprint image to be authenticated to the remote server after collecting the fingerprint image to be authenticated, and the remote server performs quality detection and liveness detection on the fingerprint image to be authenticated. After both the quality detection and liveness detection are passed, the fingerprint features to be authenticated are extracted. Regardless of which device performs the quality detection and liveness detection, the quality detection and liveness detection methods can be implemented by the following methods:

[0074] Quality detection. Obtain the environmental characteristics when collecting the fingerprint image to be authenticated, wherein the environmental characteristics include at least one of light characteristics and background noise characteristics; determine the image quality characterization value of the fingerprint image to be authenticated according to the environmental characteristics; if the image quality characterization value meets the preset conditions, it is determined that the quality detection is passed and the fingerprint features to be authenticated can be extracted from the fingerprint image to be authenticated. Among them, satisfying the preset conditions may mean that the image quality characterization value is higher than the preset image quality threshold.

[0075] The quality detection described in this specification may include the texture clarity and finger deflection degree of the fingerprint image to be authenticated, and the quality detection may be achieved through a machine learning model. Specifically, the environmental features and the fingerprint image to be authenticated may be input into a pre-trained image quality evaluation model so that the image quality evaluation model determines the texture clarity quality and deflection degree of the fingerprint image to be authenticated, and obtains the image quality characterization value of the fingerprint image to be authenticated based on the texture clarity quality and the deflection degree.

[0076] Liveness detection: Perform liveness detection on the fingerprint image to be authenticated; if the liveness detection passes, extract the fingerprint features to be authenticated from the fingerprint image to be authenticated.

[0077] Liveness detection can also be achieved through machine learning models. Specifically, the fingerprint image to be authenticated and environmental features can be input into a pre-trained liveness detection model to perform liveness detection on the fingerprint image to be authenticated. This is to prevent illegal users from using mobile terminals to collect photos of legal users' fingers to obtain fingerprint images to be authenticated, so as to prevent them from impersonating legal users to pass identity authentication.

[0078] When training a liveness detection model, the liveness detection model can be used to learn the difference between light reflected by human skin and light reflected by photo printouts, and can also learn the texture characteristics of human skin, and train the liveness detection model by self-creating positive and negative samples. Specifically, a fingerprint image of a sample user can be collected as a positive sample, and a photo image and a printout of the fingerprint image of the sample user can be generated as negative samples, and the liveness detection model can be trained based on the positive and negative samples.

[0079] Those skilled in the art should understand that the above method is only used to illustrate the example of implementing the identity authentication method through a system composed of a mobile terminal and a remote server. It is also feasible to implement the above identity authentication method by a mobile terminal or a remote server alone, which is an equivalent replacement method and is also within the scope of the present application.

[0080] The above is an identity authentication method provided in an embodiment of this specification. Based on the same idea, this specification also provides corresponding systems, devices, storage media and electronic devices.

[0081] Figure 3 A schematic diagram of the structure of an identity authentication system provided in an embodiment of this specification, the system includes: a terminal 301, a remote server 302;

[0082] The terminal 301 collects the user's fingerprint image to be authenticated by a non-contact collection method, and sends the fingerprint image to be authenticated to the remote server 302;

[0083] The remote server 302 extracts the fingerprint features to be authenticated from the fingerprint image to be authenticated; and performs identity authentication on the user based on the fingerprint features to be authenticated and the standard fingerprint features extracted from the pre-saved standard fingerprint image, wherein the standard fingerprint image is a fingerprint image pre-saved in an authoritative institution and collected by a contact collection method.

[0084] Figure 4 A schematic diagram of the structure of an identity authentication device provided in an embodiment of this specification, the device comprising:

[0085] The acquisition module 401 acquires the user's fingerprint image to be authenticated by a non-contact acquisition method;

[0086] Extraction module 402, extracting fingerprint features to be authenticated from the fingerprint image to be authenticated;

[0087] The authentication module 403 performs identity authentication on the user according to the fingerprint feature to be authenticated and the standard fingerprint feature extracted from the pre-stored standard fingerprint image, wherein the standard fingerprint image is a fingerprint image pre-stored in an authoritative institution and collected by a contact collection method.

[0088] Optionally, the acquisition module 401 is specifically configured to acquire a fingerprint image of the user to be authenticated through a camera.

[0089] Optionally, the extraction module 402 is specifically used to obtain environmental characteristics when the fingerprint image to be authenticated is collected, and the environmental characteristics include at least one of light characteristics and background noise characteristics; determine the image quality characterization value of the fingerprint image to be authenticated according to the environmental characteristics; if the image quality characterization value meets a preset condition, extract the fingerprint characteristics to be authenticated from the fingerprint image to be authenticated.

[0090] Optionally, the extraction module 402 is specifically used to input the environmental features and the fingerprint image to be authenticated into a pre-trained image quality evaluation model, so that the image quality evaluation model determines the texture clarity quality and the deflection degree of the fingerprint image to be authenticated, and obtains the image quality characterization value of the fingerprint image to be authenticated based on the texture clarity quality and the deflection degree.

[0091] Optionally, the extraction module 402 is specifically configured to perform liveness detection on the fingerprint image to be authenticated; if the liveness detection passes, extracting features of the fingerprint to be authenticated from the fingerprint image to be authenticated.

[0092] Optionally, the extraction module 402 is specifically used to input the fingerprint image to be authenticated into a pre-trained fingerprint feature extraction model to extract the machine learning fingerprint feature to be authenticated from the fingerprint image to be authenticated through the fingerprint feature extraction model; and extract the MCC fingerprint feature to be authenticated from the fingerprint image to be authenticated; and fuse the machine learning fingerprint feature to be authenticated and the MCC fingerprint feature to be authenticated as the fingerprint feature to be authenticated;

[0093] The authentication module 403 is specifically used to input the standard fingerprint image into a pre-trained fingerprint feature extraction model to extract standard machine learning fingerprint features from the standard fingerprint image through the fingerprint feature extraction model; and extract standard MCC fingerprint features from the standard fingerprint image; and fuse the standard machine learning fingerprint features and the standard MCC fingerprint features as standard fingerprint features.

[0094] Optionally, the device further comprises:

[0095] The training module 404 is used to obtain a sample fingerprint image of a sample user and a sample standard fingerprint image of the sample user, wherein the sample fingerprint image is collected by a non-contact collection method, and the sample standard fingerprint image is collected by a contact collection method; extract a sample machine learning fingerprint feature from the sample fingerprint image, and extract a sample standard machine learning fingerprint feature from the sample standard fingerprint image through a fingerprint feature extraction model to be trained; and extract a sample MCC fingerprint feature from the sample fingerprint image, and extract a sample standard MCC fingerprint feature from the sample standard fingerprint image; fuse the sample machine learning fingerprint feature and the sample MCC fingerprint feature to obtain a sample fingerprint feature; fuse the sample standard machine learning fingerprint feature and the sample standard MCC fingerprint feature to obtain a sample standard fingerprint feature; calculate a loss value based on the sample fingerprint feature, the sample standard fingerprint feature and a preset similarity loss function; and train the fingerprint feature extraction model to be trained based on the loss value.

[0096] This specification also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, it can be used to perform the above Figure 1 The authentication method provided.

[0097] based on Figure 1 Based on the Figure 1 The wind control method shown in the specification also provides Figure 5 The structural diagram of the electronic device shown in FIG. Figure 5 At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The method of identity authentication.

[0098] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0099] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a 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 implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, 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 Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0100] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0101] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or 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 cellular 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 a combination of any of these devices.

[0102] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0103] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take 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.) that contain computer-usable program code.

[0104] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0107] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0108] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0109] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. 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, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0110] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0111] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take 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 code.

[0112] 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. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0113] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0114] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A method for identity authentication, the method comprising: Collecting the user's fingerprint image to be authenticated by a non-contact collection method; Extracting fingerprint features to be authenticated from the fingerprint image to be authenticated; The user is authenticated based on the fingerprint features to be authenticated and the standard fingerprint features extracted from a pre-stored standard fingerprint image, wherein the standard fingerprint image is a fingerprint image pre-stored in an authoritative institution and collected by a contact collection method.

2. The method according to claim 1, wherein the fingerprint image of the user to be authenticated is collected by a non-contact collection method, specifically comprising: The user's fingerprint image to be authenticated is collected through the camera.

3. The method according to claim 1, wherein extracting the fingerprint feature to be authenticated from the fingerprint image to be authenticated comprises: Acquiring environmental features when the fingerprint image to be authenticated is collected, wherein the environmental features include at least one of light features and background noise features; Determining, according to the environmental characteristics, an image quality representation value of the fingerprint image to be authenticated; If the image quality representation value meets the preset condition, the fingerprint feature to be authenticated is extracted from the fingerprint image to be authenticated.

4. The method according to claim 3, determining the image quality representation value of the fingerprint image to be authenticated according to the environmental characteristics, specifically comprising: The environmental features and the fingerprint image to be authenticated are input into a pre-trained image quality assessment model so that the image quality assessment model determines the texture clarity quality and the degree of deflection of the fingerprint image to be authenticated, and obtains the image quality characterization value of the fingerprint image to be authenticated based on the texture clarity quality and the degree of deflection.

5. The method according to claim 1, wherein extracting the fingerprint feature to be authenticated from the fingerprint image to be authenticated comprises: Performing liveness detection on the fingerprint image to be authenticated; If the liveness detection is passed, the fingerprint feature to be authenticated is extracted from the fingerprint image to be authenticated.

6. The method according to claim 1, wherein extracting the fingerprint feature to be authenticated from the fingerprint image to be authenticated comprises: Inputting the fingerprint image to be authenticated into a pre-trained fingerprint feature extraction model to extract the machine learning fingerprint features to be authenticated from the fingerprint image to be authenticated through the fingerprint feature extraction model; And, extracting the MCC fingerprint feature to be authenticated from the fingerprint image to be authenticated; Fusion of the machine learning fingerprint feature to be authenticated and the MCC fingerprint feature to be authenticated as the fingerprint feature to be authenticated; Extract standard fingerprint features from pre-saved standard fingerprint images, including: Inputting the standard fingerprint image into a pre-trained fingerprint feature extraction model to extract standard machine learning fingerprint features from the standard fingerprint image through the fingerprint feature extraction model; and extracting standard MCC fingerprint features from the standard fingerprint image; The standard machine learning fingerprint feature and the standard MCC fingerprint feature are integrated as the standard fingerprint feature.

7. The method according to claim 6, wherein the fingerprint feature extraction model is pre-trained, specifically comprising: Acquire a sample fingerprint image of a sample user and a sample standard fingerprint image of the sample user, wherein the sample fingerprint image is collected by a non-contact collection method, and the sample standard fingerprint image is collected by a contact collection method; Extracting sample machine learning fingerprint features from the sample fingerprint image and extracting sample standard machine learning fingerprint features from the sample standard fingerprint image by using the fingerprint feature extraction model to be trained; And, extracting a sample MCC fingerprint feature from the sample fingerprint image, and extracting a sample standard MCC fingerprint feature from the sample standard fingerprint image; The sample machine learning fingerprint feature and the sample MCC fingerprint feature are integrated to obtain the sample fingerprint feature; Fusion of the sample standard machine learning fingerprint feature and the sample standard MCC fingerprint feature to obtain a sample standard fingerprint feature; Calculating a loss value according to the sample fingerprint feature, the sample standard fingerprint feature and a preset similarity loss function; The fingerprint feature extraction model to be trained is trained according to the loss value.

8. A system for identity authentication, the system comprising: Terminal, remote server; The terminal collects the user's fingerprint image to be authenticated by a non-contact collection method, and sends the fingerprint image to be authenticated to the remote server; The remote server extracts the fingerprint feature to be authenticated from the fingerprint image to be authenticated; The user is authenticated based on the fingerprint features to be authenticated and the standard fingerprint features extracted from a pre-stored standard fingerprint image, wherein the standard fingerprint image is a fingerprint image pre-stored in an authoritative institution and collected by a contact collection method.

9. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.

Images