Authentication method and device, equipment, storage medium and program product

Abstract

The invention provides an authentication method which can be applied to the technical field of biological recognition. The authentication method comprises the following steps: in response to an authentication request for a target object, matching a target biological feature image carried by the authentication request with a first feature image in a first database to obtain a first matching result; under the condition that the first matching result represents that matching fails, the target biological feature image is matched with a second feature image in a second database, a second matching result is obtained, the second feature image is a biological feature image of the target object in the historical time period, and the second feature image is matched with the first feature image; and determining a target authentication result under the condition that the second matching result characterizes that the first matching result is matched with the second matching result. The invention further provides an authentication device, equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present application relates to the field of biometrics, and in particular to an authentication method, apparatus, device, storage medium, and program product. Background Art

[0002] Biometric recognition technology is a technology that uses a subject's biometric information to identify an individual. It is commonly used in financial services, such as mobile banking identity authentication, in-office transactions, and facial recognition payment. In real life, life events and accidents can cause short-term changes in a person's features (such as changes in facial features due to weight gain or weight loss, or illness). When these changes occur, it may not be possible to re-register the features in a timely manner.

[0003] In the process of implementing this application, the inventors discovered that in the related technology, when the user's biometric characteristics undergo short-term changes, the real-time image obtained by the terminal is compared with the standard image in the database through the image recognition system, resulting in a decrease in the recognition success rate. Summary of the Invention

[0004] In view of the above problems, the present application provides an authentication method, apparatus, device, storage medium and program product.

[0005] According to a first aspect of the present application, an authentication method is provided, comprising: in response to an authentication request for a target object, matching a target biometric image carried in the authentication request with a first feature image in a first database to obtain a first matching result; when the first matching result indicates a match failure, matching the target biometric image with a second feature image in a second database to obtain a second matching result, wherein the second feature image is a biometric image of the target object in a historical period, and the second feature image matches the first feature image; and when the second matching result indicates a match, determining a target authentication result.

[0006] According to an embodiment of the present application, the first database has a master database attribute; wherein, the authentication method further includes: when N target authentication results of N authentication requests in a specified time period are all determined based on the second matching result, converting the attribute of the second database into a master database attribute; wherein, when the second database has the master database attribute, in response to the N+1th authentication request for the target object, the target biometric image carried by the N+1th authentication request is matched with the second feature image in the second database to obtain the N+1th target authentication result.

[0007] According to an embodiment of the present application, in response to the N+1th authentication request for the target object, the target biometric image carried by the N+1th authentication request is matched with the second feature image in the second database, and the N+1th target authentication result is obtained, including: when the N+1th target authentication result indicates a matching failure, the attributes of the first database are converted into attributes of the main database.

[0008] According to an embodiment of the present application, the second database is determined based on the following operations: in response to the i-1th historical authentication request for the target object in the historical period, the i-1th historical biometric image carried by the i-1th historical authentication request is matched with the first feature image in the first database to obtain the i-1th first historical matching result, where i is an integer greater than 1; when the i-1th first historical matching result indicates a match, the i-1th historical biometric image is stored in the second database.

[0009] According to an embodiment of the present application, the i-1th historical biometric image carried by the i-1th historical authentication request is matched with the first feature image in the first database to obtain the i-1th first historical matching result, including: using the twin model to match the i-1th historical biometric image and at least one first feature image in the first database respectively to obtain at least one similarity; determining the maximum similarity among the at least one similarity as the first matching similarity between the i-1th historical biometric image and the first database; when the first matching similarity is greater than a preset similarity threshold, obtaining the i-1th first historical matching result representing the match.

[0010] According to an embodiment of the present application, the operation of determining the second database also includes: in response to the i-th historical authentication request for the target object in the historical period, matching the i-th historical biometric image carried by the i-th historical authentication request with the first feature image to obtain the i-th first historical matching result; when the i-th first historical matching result represents a match, determining the second matching similarity between the i-th historical biometric image and the first database; when the second matching similarity is greater than the first matching similarity, updating the i-1-th historical biometric image stored in the second database to the i-th historical biometric image.

[0011] According to an embodiment of the present application, the twin model includes a parallel first convolutional neural network layer and a second convolutional neural network layer; wherein, using the twin model to match the i-1th historical biometric image and the first feature image in the first database to obtain the similarity includes: using the first convolutional neural network layer to extract features from the i-1th historical biometric image to obtain a first convolutional feature; using the second convolutional neural network layer to extract features from the first feature image to obtain a second convolutional feature; matching the first convolutional feature and the second convolutional feature to obtain the similarity.

[0012] A second aspect of the present application provides an authentication device, including: a response module, configured to, in response to an authentication request for a target object, match a target biometric image carried in the authentication request with a first feature image in a first database to obtain a first matching result; a matching module, configured to, if the first matching result indicates a match failure, match the target biometric image with a second feature image in a second database to obtain a second matching result, wherein the second feature image is a biometric image of the target object in a historical period, and the second feature image matches the first feature image; and an authentication module, configured to, if the second matching result indicates a match, determine a target authentication result.

[0013] The third aspect of the present application provides an electronic device, comprising: one or more processors; a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0014] The fourth aspect of the present application further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the computer program or instructions are executed by a processor.

[0015] The fifth aspect of the present application further provides a computer program product, comprising a computer program or instructions, which implement the steps of the above method when executed by a processor.

[0016] According to the authentication method, apparatus, device, medium, and product provided by the present application, a first matching result is obtained by matching the target biometric image carried in the authentication request with the first feature image in the first database; if the first matching result indicates a match failure, the target biometric image is matched with the second feature image in the second database to obtain a second matching result; if the second matching result indicates a match, the target authentication result is determined. Since the second feature image in the second database is dynamically updated based on the biometric image of the target object after matching with the first feature image in a historical period, the second database dynamically stores biometric images of the target object with high real-time performance and high reference value within a short historical period. After the target biometric image fails to match with the first database, it continues to match with the second feature image in the second database, which not only improves the target biometric image authentication success rate of the target object, but also reduces the additional operations caused by the failure to match with the standard first database due to temporary changes in the biometric characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above contents and other objects, features and advantages of the present application will become more apparent through the following description of the embodiments of the present application with reference to the accompanying drawings, in which:

[0018] Figure 1 An application scenario diagram of the authentication method, apparatus, device, medium, and program product according to an embodiment of the present application is shown;

[0019] Figure 2 A flowchart of an authentication method according to an embodiment of the present application is shown;

[0020] Figure 3 A schematic diagram showing a second database update according to an embodiment of the present application is shown;

[0021] Figure 4 shows a structural block diagram of an authentication device according to an embodiment of the present application; and

[0022] Figure 5 A block diagram of an electronic device suitable for implementing an authentication method according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present application. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present application. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present application.

[0024] The terms used herein are only for describing specific embodiments and are not intended to limit the present application. The terms "comprise," "include," etc. used herein indicate the presence of features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0025] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0026] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0027] During the implementation of this application, we discovered that in related technologies, due to life events and accidents, features can undergo short-term changes (e.g., changes in facial features due to weight gain or weight loss, illness, etc.). When these changes occur, it is not always possible to re-register features in a timely manner. In the event of a short-term change in a user's biometric features, the real-time image captured by the terminal is compared with the standard image in the database by the image recognition system, resulting in a decrease in the recognition success rate.

[0028] In view of this, an embodiment of the present application provides an authentication method, which, in response to an authentication request for a target object, matches a target biometric image carried in the authentication request with a first feature image in a first database to obtain a first matching result; when the first matching result indicates a match failure, matches the target biometric image with a second feature image in a second database to obtain a second matching result, wherein the second feature image is a biometric image of the target object in a historical period, and the second feature image matches the first feature image; and when the second matching result indicates a match, determines the target authentication result.

[0029] It should be noted that the authentication method and authentication device provided in this application can be used in the field of financial technology, such as banks and other financial institutions, and can also be used in any field other than the field of financial technology, such as e-commerce platforms such as shopping websites. Therefore, the application field of the authentication method and authentication device provided in this application is not limited.

[0030] In the technical solution of this application, the user information involved (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0031] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided in the embodiments of the present application all provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0032] Figure 1 The present invention provides an example of an application scenario of an authentication method, apparatus, device, medium, and program product according to an embodiment of the present application.

[0033] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0034] A user may use a first terminal device 101, a second terminal device 102, or a third terminal device 103 to interact with a server 105 via a network 104 to receive or send messages, etc. Various communication terminal applications may be installed on the first terminal device 101, the second terminal device 102, or the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email terminals, social platform software, etc. (for example only).

[0035] The first terminal device 101 , the second terminal device 102 , and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0036] The server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal devices.

[0037] It should be noted that the authentication method provided in the embodiment of the present application can generally be executed by the server 105. Accordingly, the authentication device provided in the embodiment of the present application can generally be set in the server 105. The authentication method provided in the embodiment of the present application can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the authentication device provided in the embodiment of the present application can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0038] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0039] The following will be based on Figure 1 The scene described by Figure 2~Figure 3 The authentication method according to the embodiment of the present application is described in detail.

[0040] Figure 2 A flow chart of an authentication method according to an embodiment of the present application is shown.

[0041] like Figure 2 As shown, the authentication method 200 of this embodiment includes operations S210 to S230.

[0042] In operation S210 , in response to an authentication request for a target object, a target biometric feature image carried in the authentication request is matched with a first feature image in a first database to obtain a first matching result.

[0043] According to an embodiment of the present application, the target object is an object undergoing authentication in a business scenario, for example, an object undergoing facial image authentication in a terminal login scenario.

[0044] According to an embodiment of the present application, the server obtains a target biometric image of the target object in response to receiving an authentication request for the target object sent by the terminal.

[0045] In an embodiment of the present application, before obtaining the target object's information, the target object's consent or authorization may be obtained. For example, before operation S210, a request to obtain information may be issued to the target object. If the target object agrees or authorizes the acquisition of information, operation S210 is performed.

[0046] According to an embodiment of the present application, the target biometric image is a biometric image acquired in real time. For example, the biometric feature may be a fingerprint, iris, face, palm print, or other feature.

[0047] According to an embodiment of the present application, the first database is the system's initial default main database, and the first database stores comprehensive, standard, and rich first feature images. The first feature images can be biometric images of objects under different lighting conditions, expressions, and postures entered during information registration.

[0048] According to an embodiment of the present application, a similarity function may be used to match the target biometric image with the first feature image in the first database to obtain a first matching result.

[0049] In operation S220 , if the first matching result indicates a matching failure, the target biometric image is matched with a second biometric image in the second database to obtain a second matching result.

[0050] According to an embodiment of the present application, the second database is a dynamic database, and the second feature image in the second database can be updated in real time based on the first matching result.

[0051] According to an embodiment of the present application, the second feature image is a biometric feature image of the target object in a historical period, which is a biometric feature image of the target object that is dynamically updated in real time and matches the first feature image in a short historical period.

[0052] According to an embodiment of the present application, in a historical period, when the first matching result indicates a match, the second feature image in the second database is dynamically updated based on the target biometric feature image, so that the second feature image in the second database matches the first feature image.

[0053] According to an embodiment of the present application, the first matching result represents a matching failure, indicating that the target biometric image fails to match the first feature image, and then the similarity function is used to match the target biometric image with the second feature image in the second database to obtain a second matching result.

[0054] In operation S230 , if the second matching result indicates a match, a target authentication result is determined.

[0055] According to an embodiment of the present application, when the second matching result indicates a match, the target authentication result is determined to be authentication success, and when the second matching result indicates a match failure, the target authentication result is determined to be authentication failure.

[0056] According to the embodiments of the present application, since the second characteristic image in the second database is dynamically updated based on the target object's biometric image after matching the first characteristic image in a historical period, the second database dynamically stores the target object's biometric image within a short historical period, which is highly real-time and has high reference value. If the target biometric image fails to match with the first database, the second characteristic image in the second database is continued to match, which not only improves the target object's target biometric image authentication success rate, but also reduces the additional operations caused by the failure to match with the standard first database due to temporary changes in the biometric characteristics.

[0057] According to an embodiment of the present application, the first database has a master database attribute; wherein, the authentication method further includes: when N target authentication results of N authentication requests in a specified time period are all determined based on the second matching result, converting the attribute of the second database into a master database attribute; wherein, when the second database has the master database attribute, in response to the N+1th authentication request for the target object, the target biometric image carried by the N+1th authentication request is matched with the second feature image in the second database to obtain the N+1th target authentication result.

[0058] According to an embodiment of the present application, in response to N consecutive authentication requests for a target object within a certain period of time, N target authentication results corresponding to the N authentication requests are obtained.

[0059] According to an embodiment of the present application, the system initially defaults to setting the first database to be the main database attribute. Each time in response to an authentication request, it first matches the first database with the main database attribute. When a first matching result with a matching representation is obtained, the target authentication result of successful authentication is determined. When a first matching result with a matching representation failure is obtained, it matches the second database again. When a second matching result with a matching representation is obtained, the target authentication result of successful authentication is determined.

[0060] According to an embodiment of the present application, N target authentication results are all determined based on the second matching result to represent N consecutive failures in matching with the first database and N consecutive matches with the second database.

[0061] According to an embodiment of the present application, when N target authentication results are all determined based on the second matching result, the attributes of the second database are converted into attributes of the main database.

[0062] According to an embodiment of the present application, N can be determined based on a preset reliability threshold. N consecutive matches with the second database can indicate a short-term stable change in the target subject's biometric characteristics, such as changes in facial features after weight gain over a month. In this case, the stability and efficiency of recognition based on the second database are demonstrated.

[0063] According to an embodiment of the present application, the attributes of the second database are converted into attributes of the primary database, which means that in response to the subsequent N+1th authentication request, matching is first performed with the second database.

[0064] According to an embodiment of the present application, the target biometric feature image carried in the N+1th authentication request is matched with the second feature image in the second database to obtain the N+1th target authentication result.

[0065] According to an embodiment of the present application, when the second matching results of continuous matching with the second database are all matched and the number of continuous matching is greater than a preset reliability threshold, the attributes of the second database are converted into the attributes of the main database. Therefore, after a brief change in the biometric characteristics, when the continuous matching with the first database fails, the reliability of switching the second database to the attributes of the main database is guaranteed, overcoming the additional operations caused by changes in the subjectivity of the object, unexpected changes, etc. over time, and improving the recognition efficiency and readiness for authentication after the change.

[0066] According to an embodiment of the present application, in response to the N+1th authentication request for the target object, the target biometric image carried by the N+1th authentication request is matched with the second feature image in the second database, and the N+1th target authentication result is obtained, including: when the N+1th target authentication result indicates a matching failure, the attributes of the first database are converted into attributes of the main database.

[0067] According to an embodiment of the present application, the N+1th target authentication result indicates a matching failure, which means that the target biometric image carried in the N+1th authentication request fails to match the second feature image in the second database.

[0068] According to an embodiment of the present application, when the N+1th target authentication result represents a match failure, it can be reflected that the biometric characteristics of the target object are fully or partially restored to the initial state. Since the first database is a database that stores standard source data, the attributes of the first database are reconverted into the main database attributes.

[0069] According to an embodiment of the present application, the attributes of the first database are converted into attributes of the main database, which means that in response to the subsequent N+2 authentication request, a match is first performed with the first database.

[0070] According to an embodiment of the present application, the second database is determined based on the following operations: in response to the i-1th historical authentication request for the target object in the historical period, the i-1th historical biometric image carried by the i-1th historical authentication request is matched with the first feature image in the first database to obtain the i-1th first historical matching result, where i is an integer greater than 1; when the i-1th first historical matching result indicates a match, the i-1th historical biometric image is stored in the second database.

[0071] According to an embodiment of the present application, the historical period is a period before responding to an authentication request for the target object.

[0072] According to an embodiment of the present application, the (i-1)th historical biometric image is a biometric image carried in the (i-1)th historical authentication request of the target object.

[0073] According to an embodiment of the present application, in response to the i-1th historical authentication request for the target object in the historical period, a similarity function can be used to match the i-1th historical biometric image with the first feature image in the first database to obtain the i-1th first historical matching result.

[0074] According to an embodiment of the present application, the (i-1)th first historical matching result may be a matching failure or a matching result.

[0075] According to an embodiment of the present application, when the i-1th first historical matching result indicating a matching failure is obtained, the i-1th target authentication result indicating an authentication failure is obtained.

[0076] According to an embodiment of the present application, when the i-1th first historical matching result represents a match, the i-1th historical biometric image is a real-time biometric image that matches the first feature image in response to the i-1th historical authentication request, and the i-1th historical biometric image is dynamically stored in the second database.

[0077] According to an embodiment of the present application, the second database is dynamically updated through the first historical matching results of the real-time historical biometric image obtained each time in the historical period and the first feature image in the first database, so as to be used when the recognition with the first database fails in the subsequent response period, thereby improving the recognition rate.

[0078] According to an embodiment of the present application, the i-1th historical biometric image carried by the i-1th historical authentication request is matched with the first feature image in the first database to obtain the i-1th first historical matching result, including: using the twin model to match the i-1th historical biometric image and at least one first feature image in the first database respectively to obtain at least one similarity; determining the maximum similarity among the at least one similarity as the first matching similarity between the i-1th historical biometric image and the first database; when the first matching similarity is greater than a preset similarity threshold, obtaining the i-1th first historical matching result representing the match.

[0079] According to an embodiment of the present application, the twin model can be composed of two parallel convolutional neural networks. For example, the convolutional neural network can be a Visual Geometry Group Network (VGG), a Residual Neural Network (NetworkResNet), etc.

[0080] According to an embodiment of the present application, one or more first feature images are stored in the first database. The twin model is used to match the i-1th historical biometric feature image with the one or more first feature images to obtain one or more similarities.

[0081] According to an embodiment of the present application, the similarity represents the distance between the (i-1)th historical biometric feature image and the first feature image, and the greater the similarity, the smaller the distance.

[0082] According to an embodiment of the present application, a maximum similarity is determined from at least one similarity, and the maximum similarity is determined as the first matching similarity between the (i-1)th historical biometric image and the first database.

[0083] According to an embodiment of the present application, when the first matching similarity is greater than a preset similarity threshold, a first historical matching result representing the i-1th match is obtained, indicating that the i-1th historical biometric image matches the first database, the i-1th historical biometric image is stored in the second database, and the first matching similarity is recorded in the log.

[0084] According to an embodiment of the present application, the operation of determining the second database also includes: in response to the i-th historical authentication request for the target object in the historical period, matching the i-th historical biometric image carried by the i-th historical authentication request with the first feature image to obtain the i-th first historical matching result; when the i-th first historical matching result represents a match, determining the second matching similarity between the i-th historical biometric image and the first database; when the second matching similarity is greater than the first matching similarity, updating the i-1-th historical biometric image stored in the second database to the i-th historical biometric image.

[0085] According to an embodiment of the present application, the i-th historical biometric image is a biometric image carried in the i-th historical authentication request of the target object.

[0086] According to an embodiment of the present application, in response to the i-th historical authentication request for the target object in the historical period, the i-th historical biometric image can be matched with the first feature image in the first database using a similarity function to obtain the i-th first historical matching result.

[0087] According to an embodiment of the present application, an i-th historical biometric image is matched with at least one first feature image in a first database to obtain at least one similarity; the maximum similarity among the at least one similarity is determined as a second matching similarity between the i-th historical biometric image and the first database; when the second matching similarity is greater than a preset similarity threshold, an i-th first historical matching result representing a match is obtained.

[0088] According to an embodiment of the present application, when the second matching similarity is less than or equal to a preset similarity threshold, the i-th first historical matching result representing a matching failure is obtained, thereby obtaining the i-th target authentication result representing an authentication failure.

[0089] According to an embodiment of the present application, when the i-th first historical matching result indicates a match, the i-th historical biometric image is a real-time biometric image that matches the first feature image in response to the i-th historical authentication request.

[0090] According to an embodiment of the present application, when the second matching similarity is greater than the first matching similarity, the (i-1)th historical biometric image stored in the second database is replaced with the (i)th historical biometric image.

[0091] According to an embodiment of the present application, when the second matching similarity is less than or equal to the first matching similarity, the second database is not updated.

[0092] According to the embodiments of the present application, in multiple consecutive historical authentication requests, the historical biometric images are matched with the first database. By comparing the second matching similarity with the first matching similarity, it is ensured that the historical biometric image with the highest similarity to the first feature image in the first database is dynamically updated in the second database each time. The positive feedback mechanism is used to superimpose the previous first historical matching result on the next authentication operation, and the second database is dynamically updated in real time, thereby improving the accuracy of the second database. This not only improves the recognition rate, but also reduces the extra operations caused by recognition failures.

[0093] According to an embodiment of the present application, the twin model includes a parallel first convolutional neural network layer and a second convolutional neural network layer; wherein, using the twin model to match the i-1th historical biometric image and the first feature image in the first database to obtain the similarity includes: using the first convolutional neural network layer to extract features from the i-1th historical biometric image to obtain a first convolutional feature; using the second convolutional neural network layer to extract features from the first feature image to obtain a second convolutional feature; matching the first convolutional feature and the second convolutional feature to obtain the similarity.

[0094] According to an embodiment of the present application, the i-1th historical biometric image and the first feature image are preprocessed, and the image sizes are normalized using a mean-variance function to reduce the impact of differences in image grayscale distribution.

[0095] In one embodiment, the first feature image is normalized as shown in formula (1):

[0096] (1);

[0097] Among them, X represents the first feature image, Characterize the pixel grayscale mean of the first feature image, Characterizes the pixel grayscale variance of the first feature image, Characterize the first eigenimage after normalization.

[0098] According to an embodiment of the present application, the first convolutional neural network layer and the second convolutional neural network layer share the same convolution weights, so that the convolutional neural network layer can learn the common features or similar features between the preprocessed i-1th historical biometric image and the first feature image, and can better perform matching and comparison.

[0099] According to an embodiment of the present application, a first convolutional neural network layer is used to extract features from the (i-1)th historical biometric image to obtain a first convolutional feature. The first convolutional feature is a depth feature of the (i-1)th historical biometric image.

[0100] According to an embodiment of the present application, a second convolutional neural network layer is used to extract features from the first feature image to obtain a second convolutional feature, which is a depth feature of the first feature image.

[0101] According to an embodiment of the present application, in order to enhance the distinction between faces, the weights of the fully connected layer, the first convolutional features and the second convolutional features are normalized based on the activation function, the feature space is compressed into a hyperplane of a specified radius, and the cosine interval m is introduced for constraint.

[0102] According to an embodiment of the present application, the twin model also includes a classifier. The normalized first and second convolutional features are input into the classifier. The similarity is measured based on the distance between the first and second convolutional features. To reduce the recognition error rate between biometric features of similar objects, the Mahalanobis distance, a modified version of the Euclidean distance, is used to calculate the similarity. The classification result is finally input. The classification result is either a match or a match failure.

[0103] In one embodiment, the Mahalanobis distance As shown in formula (2):

[0104] (2);

[0105] in, Characterize the first convolution feature, Characterize the first convolution feature, M= , is the linear transformation matrix of the sample points of the i-1th historical biometric image, is the linear transformation matrix of the sample points of the first eigenimage.

[0106] According to an embodiment of the present application, the parallel first convolutional neural network layer and the second convolutional neural network layer in the twin model are used to perform similarity matching on the i-1th historical biometric image and the first feature image, so as to obtain common features or similar features between the two images, better perform feature comparison, and enhance the distinction between features.

[0107] Figure 3 A schematic diagram showing the update of the second database according to an embodiment of the present application is shown.

[0108] like Figure 3As shown, in response to receiving the i-1th historical authentication request for the target object sent from the terminal in the historical period, the first convolutional neural network layer is used to extract features of the i-1th historical biometric image 310 to obtain a first convolutional feature 320; the second convolutional neural network layer is used to extract features of the first feature image 330 in the first database to obtain a second convolutional feature 340; the first convolutional feature 320 and the second convolutional feature 340 are matched to obtain a similarity; the maximum similarity among at least one similarity is determined as the first matching similarity 350 between the i-1th historical biometric image and the first database; when the first matching similarity is greater than a preset similarity threshold, the i-1th first historical matching result 360 representing the match is obtained, the i-1th historical biometric image 310 is stored in the second database 370 and the first matching similarity is recorded in the log; when the first matching similarity is less than or equal to the preset similarity threshold, the i-1th first historical matching result 380 representing the match failure is obtained, and the second feature image in the second database is not updated.

[0109] Based on the above authentication method, this application also provides an authentication device. Figure 4 The device is described in detail.

[0110] Figure 4 The figure shows a structural block diagram of an authentication device according to an embodiment of the present application.

[0111] like Figure 4 As shown, the authentication device 400 of this embodiment includes a response module 410 , a matching module 420 and an authentication module 430 .

[0112] Response module 410 is configured to respond to an authentication request for a target object by matching the target biometric image carried in the authentication request with a first biometric image in the first database to obtain a first matching result. In one embodiment, response module 410 may be configured to perform operation S210 described above, which will not be further described herein.

[0113] Matching module 420 is configured to, if the first matching result indicates a match failure, match the target biometric image with a second feature image in a second database to obtain a second matching result, where the second feature image is a biometric image of the target subject during a historical period, and the second feature image matches the first feature image. In one embodiment, matching module 420 may be configured to perform operation S220 described above, and will not be further described here.

[0114] The authentication module 430 is configured to determine a target authentication result when the second matching result indicates a match. In one embodiment, the authentication module 430 may be configured to execute the operation S230 described above, which will not be described in detail herein.

[0115] According to the authentication method, apparatus, device, medium, and product provided by the present application, a first matching result is obtained by matching the target biometric image carried in the authentication request with the first feature image in the first database; if the first matching result indicates a match failure, the target biometric image is matched with the second feature image in the second database to obtain a second matching result; if the second matching result indicates a match, the target authentication result is determined. Since the second feature image in the second database is dynamically updated based on the biometric image of the target object after matching with the first feature image in a historical period, the second database dynamically stores biometric images of the target object with high real-time performance and high reference value within a short historical period. After the target biometric image fails to match with the first database, it continues to match with the second feature image in the second database, which not only improves the target biometric image authentication success rate of the target object, but also reduces the additional operations caused by the failure to match with the standard first database due to temporary changes in the biometric characteristics.

[0116] According to an embodiment of the present application, the authentication device 400 further includes a conversion module.

[0117] A conversion module is configured to convert the attributes of the second database into attributes of the primary database when N target authentication results of N authentication requests in a specified time period are all determined based on the second matching result; wherein, when the second database has the attributes of the primary database, in response to an N+1th authentication request for the target object, match the target biometric image carried in the N+1th authentication request with the second feature image in the second database to obtain an N+1th target authentication result.

[0118] According to an embodiment of the present application, the conversion module includes a conversion sub-module.

[0119] The conversion submodule is configured to convert the attributes of the first database into attributes of the main database when the N+1th target authentication result indicates a match failure.

[0120] According to an embodiment of the present application, the matching module 420 includes a matching submodule and a storage submodule.

[0121] The matching submodule is used to respond to the i-1th historical authentication request for the target object in the historical period, match the i-1th historical biometric image carried by the i-1th historical authentication request with the first feature image in the first database, and obtain the i-1th first historical matching result, where i is an integer greater than 1.

[0122] The storage submodule is configured to store the (i-1)th historical biometric feature image in the second database when the (i-1)th first historical matching result indicates a match.

[0123] According to an embodiment of the present application, the matching submodule includes a first matching unit, a second matching unit, and a third matching unit.

[0124] The first matching unit is used to use the twin model to match the i-1th historical biometric image with at least one first feature image in the first database to obtain at least one similarity.

[0125] The second matching unit is configured to determine a maximum similarity among the at least one similarity as a first matching similarity between the (i-1)th historical biometric feature image and the first database.

[0126] The third matching unit is configured to obtain an i-1th first historical matching result representing a match when the first matching similarity is greater than a preset similarity threshold.

[0127] According to an embodiment of the present application, the matching module 420 further includes a response submodule, a determination submodule, and an update submodule.

[0128] The response submodule is used to respond to the i-th historical authentication request for the target object in the historical period, match the i-th historical biometric image carried by the i-th historical authentication request with the first feature image, and obtain the i-th first historical matching result.

[0129] The determination submodule is configured to determine a second matching similarity between the i-th historical biometric image and the first database when the i-th first historical matching result indicates a match.

[0130] The updating submodule is configured to update the (i-1)th historical biometric feature image stored in the second database to the (i)th historical biometric feature image when the second matching similarity is greater than the first matching similarity.

[0131] According to an embodiment of the present application, the first matching unit includes a first matching sub-unit, a second matching sub-unit, and a third matching sub-unit.

[0132] The first matching subunit is used to extract features from the i-1th historical biometric image using the first convolutional neural network layer to obtain a first convolutional feature.

[0133] The second matching subunit is used to use the second convolutional neural network layer to extract features from the first feature image to obtain second convolution features.

[0134] The third matching subunit is used to match the first convolution feature and the second convolution feature to obtain similarity.

[0135] According to embodiments of the present application, any multiple modules among response module 410, matching module 420, and authentication module 430 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present application, at least one of response module 410, matching module 420, and authentication module 430 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or may be implemented in any one of the three implementation methods of software, hardware, and firmware, or any appropriate combination of these. Alternatively, at least one of response module 410, matching module 420, and authentication module 430 may be at least partially implemented as a computer program module that, when executed, performs the corresponding functionality.

[0136] Figure 5 A block diagram of an electronic device suitable for implementing an authentication method according to an embodiment of the present application is shown.

[0137] like Figure 5 As shown, an electronic device 500 according to an embodiment of the present application includes a processor 501, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 502 or a program loaded from a storage unit 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present application.

[0138] Various programs and data required for the operation of the electronic device 500 are stored in the RAM 503. The processor 501, ROM 502, and RAM 503 are connected to each other via a bus 504. The processor 501 performs various operations of the method flow according to the embodiment of the present application by executing the programs in the ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 may also perform various operations of the method flow according to the embodiment of the present application by executing the programs stored in one or more memories.

[0139] According to an embodiment of the present application, electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to bus 504. Electronic device 500 may also include one or more of the following components connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 508 including a hard disk; and a communication section 509 including a network interface card such as a LAN card or modem. Communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. Removable media 511, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 510 as needed, so that computer programs read from the removable media can be installed into storage section 508 as needed.

[0140] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the authentication method according to the embodiments of this application.

[0141] According to an embodiment of the present application, a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as, but not limited to, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present application, a computer-readable storage medium may include the ROM 502 and / or RAM 503 described above and / or one or more memories other than ROM 502 and RAM 503.

[0142] The embodiments of the present application also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the authentication method provided in the embodiments of the present application.

[0143] The computer program executes the above functions defined in the system / device of the embodiment of the present application when the computer program is executed by the processor 501. According to the embodiment of the present application, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0144] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 509, and / or installed from a removable medium 511. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0145] In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 509, and / or installed from the removable medium 511. When the computer program is executed by the processor 501, the above-mentioned functions defined in the system of the embodiment of the present application are performed. According to the embodiment of the present application, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0146] According to an embodiment of the present application, the program code for executing the computer program provided by the embodiment of the present application can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0147] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0148] It will be understood by those skilled in the art that the features described in the various embodiments of this application may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in this application. In particular, the features described in the various embodiments of this application may be combined and / or coupled in various ways without departing from the spirit and teachings of this application. All such combinations and / or couplings fall within the scope of this application.

Claims

1. An authentication method, characterized in that: The method comprises: In response to an authentication request for a target object, matching a target biometric image carried in the authentication request with a first feature image in a first database to obtain a first matching result; If the first matching result indicates a match failure, matching the target biometric image with a second feature image in a second database to obtain a second matching result, wherein the second feature image is a biometric image of the target object in a historical period, and the second feature image matches the first feature image; and If the second matching result indicates a match, a target authentication result is determined.

2. The method according to claim 1, characterized in that The first database has a master database attribute; wherein the method further comprises: When N target authentication results of N authentication requests in a specified time period are all determined based on the second matching result, converting the attributes of the second database into the attributes of the main database; In which, when the second database has the attributes of the main database, in response to the N+1th authentication request for the target object, the target biometric image carried by the N+1th authentication request is matched with the second feature image in the second database to obtain the N+1th target authentication result.

3. The method according to claim 2, characterized in that In response to the N+1th authentication request for the target object, matching the target biometric image carried in the N+1th authentication request with the second feature image in the second database to obtain the N+1th target authentication result includes: In a case where the (N+1)th target authentication result indicates a matching failure, the attributes of the first database are converted into the attributes of the main database.

4. The method according to claim 1, wherein The second database is determined based on the following operations: In response to an i-1th historical authentication request for the target object in a historical period, matching an i-1th historical biometric image carried in the i-1th historical authentication request with a first feature image in a first database to obtain an i-1th first historical matching result, where i is an integer greater than 1; When the (i-1)th first historical matching result indicates a match, the (i-1)th historical biometric feature image is stored in the second database.

5. The method according to claim 4, characterized in that The matching of the i-1th historical biometric image carried in the i-1th historical authentication request with the first feature image in the first database to obtain the i-1th first historical matching result includes: Using the twin model, respectively matching the (i-1)th historical biometric image with at least one first feature image in the first database to obtain at least one similarity; determining a maximum similarity among at least one of the similarities as a first matching similarity between the (i-1)th historical biometric image and the first database; When the first matching similarity is greater than a preset similarity threshold, a first historical matching result representing the (i-1)th matching is obtained.

6. The method according to claim 5, characterized in that The operation of determining the second database further includes: In response to an i-th historical authentication request for the target object in a historical period, matching an i-th historical biometric image carried in the i-th historical authentication request with the first biometric image to obtain an i-th first historical matching result; In a case where the i-th first historical matching result indicates a match, determining a second matching similarity between the i-th historical biometric image and the first database; In a case where the second matching similarity is greater than the first matching similarity, the (i-1)th historical biometric image stored in the second database is updated to the (i)th historical biometric image.

7. The method according to claim 5, characterized in that The twin model includes a first convolutional neural network layer and a second convolutional neural network layer in parallel; The similarity obtained by matching the i-1th historical biometric image with the first feature image in the first database using the twin model includes: Performing feature extraction on the (i-1)th historical biometric image using the first convolutional neural network layer to obtain a first convolutional feature; Performing feature extraction on the first feature image using the second convolutional neural network layer to obtain second convolution features; The first convolution feature and the second convolution feature are matched to obtain a similarity.

8. An authentication device, characterized in that: The device comprises: a response module, configured to respond to an authentication request for a target object by matching a target biometric image carried in the authentication request with a first feature image in a first database to obtain a first matching result; a matching module, configured to, if the first matching result indicates a match failure, match the target biometric image with a second feature image in a second database to obtain a second matching result, wherein the second feature image is a biometric image of the target object in a historical period, and the second feature image matches the first feature image; The authentication module is configured to determine a target authentication result when the second matching result representation is a match.

9. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images