Identity authentication method, device and module

Abstract

The embodiment of the invention provides an identity authentication method and device and a module, relates to the technical field of image processing, is applied to a processor in the identity authentication module, and comprises the following steps: identifying a first feature region in a first image acquired by an image acquisition component; if the first type of the biological features to be extracted in the first feature region is inconsistent with the second type corresponding to the loaded image processing parameters in the second memory, and the first type is a registered type, loading the image processing parameters corresponding to the first type from the first memory to the second memory, image processing parameters corresponding to the second type in the second memory are replaced; performing image processing on the first feature region based on the image processing parameters loaded in the second memory, and extracting a first biological feature of the processed first feature region; and performing identity authentication based on the first biological feature and the reference biological feature of the first type. By applying the scheme provided by the embodiment of the invention, the hardware cost of identity recognition can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of image processing, and particularly to an identity authentication method, apparatus and module. Background Art

[0002] Identity authentication technology based on biometrics is widely used in various scenarios such as access control management and financial payment due to its convenience and high efficiency. Currently, various biometrics such as face features and palm vein features can be used for identity authentication. Taking the access control management scenario as an example, the identity authentication module in an intelligent door lock can collect the face image of a visitor and authenticate the visitor's identity based on the face features, or can also collect the palm vein image of the visitor and authenticate the visitor's identity based on the palm vein features.

[0003] That is, in the related art, the identity authentication module usually supports authentication using different types of biometrics. In view of this, multiple independent image acquisition components are usually deployed in the identity authentication module. The multiple independent image acquisition components respectively extract the corresponding type of biometric features from the images they acquire, and then perform identity authentication based on the extracted biometric features. It can be seen that this increases the number of hardware components in the identity authentication module, resulting in a higher hardware cost. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide an identity authentication method, apparatus and module to reduce the hardware cost of identity recognition. The specific technical solutions are as follows:

[0005] In a first aspect, the embodiments of the present application provide an identity authentication method, which is applied to a processor in an identity authentication module. The identity authentication module further includes: an image acquisition component, a non-volatile first memory, and a volatile second memory. Multiple groups of image processing parameters are stored in the first memory, and each group of image processing parameters corresponds to a type of biometric feature. One group of image processing parameters among the multiple groups of image processing parameters is loaded in the second memory. The method includes:

[0006] Identifying a first feature area in a first image acquired by the image acquisition component;

[0007] If the first type of biometric feature to be extracted in the first feature area is inconsistent with the second type corresponding to the image processing parameters loaded in the second memory, and the first type is a registered type, then load the image processing parameters corresponding to the first type from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory, where the registered type is: the type of the benchmark biometric feature that has been entered;

[0008] Perform image processing on the first feature region based on the image processing parameters loaded in the second memory, and extract the first biometric feature of the processed first feature region;

[0009] Perform identity authentication based on the first biometric feature and the reference biometric feature of the first type.

[0010] In a second aspect, an embodiment of the present application provides an identity authentication device, which is applied to a processor in an identity authentication module. The identity authentication module further includes: an image acquisition component, a non-volatile first memory, and a volatile second memory. Multiple sets of image processing parameters are stored in the first memory, and each set of image processing parameters corresponds to a type of biometric feature. One set of image processing parameters among the multiple sets of image processing parameters is loaded in the second memory. The device includes:

[0011] A first recognition module, configured to recognize a first feature region in a first image acquired by the image acquisition component;

[0012] A first parameter loading module, configured to, if the first type of the biometric feature to be extracted in the first feature region is inconsistent with the second type corresponding to the image processing parameters already loaded in the second memory, and the first type is a registered type, load the image processing parameters corresponding to the first type from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory, where the registered type is: the type of the recorded reference biometric feature;

[0013] A first feature extraction module, configured to perform image processing on the first feature region based on the image processing parameters loaded in the second memory, and extract the first biometric feature of the processed first feature region;

[0014] A first identity authentication module, configured to perform identity authentication based on the first biometric feature and the reference biometric feature of the first type.

[0015] In a third aspect, an embodiment of the present application provides an identity authentication module, including:

[0016] An image acquisition component, configured to acquire an image and send the acquired image to a processor;

[0017] A non-volatile first memory, configured to store multiple sets of image processing parameters, and each set of image processing parameters corresponds to a type of biometric feature;

[0018] A volatile second memory, configured to load one set of image processing parameters among the multiple sets of image processing parameters;

[0019] The processor is configured to execute the method described in the first aspect.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0021] In a fifth aspect, an embodiment of the present application further provides a computer program product containing instructions, which when running on a computer, causes the computer to execute the method described in the first aspect.

[0022] As can be seen from the above, in the solution provided by the embodiment of the present application, before extracting the biometric feature from the first image, the relationship between the type of the biometric feature to be extracted and the currently loaded image processing parameters is considered. According to whether the first type of the biometric feature to be extracted matches the second type corresponding to the currently loaded image processing parameters, it is determined whether to switch the image processing parameters, so that the image processing parameters match the biometric feature to be extracted, so that an accurate and high-quality biometric feature can be extracted. Furthermore, the identity authentication module can smoothly perform subsequent identity authentication based on the extracted biometric feature. That is, by flexibly switching the image processing parameters, the image processing parameters can match the biometric feature to be extracted in various situations, so that identity authentication based on various biometric features can be realized based on the image collected by one image acquisition component, without setting multiple independent image acquisition components, reducing the number of hardware in the identity authentication module and reducing the hardware cost of identity recognition.

[0023] Of course, it is not necessary for any product or method implementing the present application to achieve all the above advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can also obtain other embodiments according to these drawings.

[0025] Figure 1 It is a schematic flowchart of an identity authentication method provided by an embodiment of the present application;

[0026] Figure 2 It is a schematic flowchart of a biometric feature entry method provided by an embodiment of the present application;

[0027] Figure 3 It is a schematic diagram of a face template registration process provided by an embodiment of the present application;

[0028] Figure 4A schematic diagram of a palm template registration process provided by an embodiment of the present application;

[0029] Figure 5 A schematic diagram of an identity authentication process provided by an embodiment of the present application;

[0030] Figure 6 A schematic structural diagram of an identity authentication device provided by an embodiment of the present application;

[0031] Figure 7 A schematic structural diagram of an identity authentication module provided by an embodiment of the present application. Detailed implementation manners

[0032] Next, the implementation subject of the solution provided by the embodiment of the present application will be described.

[0033] First, an explanation will be given for the implementation subject of the solution provided by the embodiment of the present application.

[0034] The implementation subject of the solution provided by the embodiment of the present application is the processor in the identity authentication module. The above identity authentication module includes an image acquisition component, a non-volatile first memory, a volatile second memory, and a processor.

[0035] Among them, the image acquisition component is used to acquire an image and send the acquired image to the processor; the non-volatile first memory is used to store multiple groups of image processing parameters, and each group of image processing parameters corresponds to a type of biometric feature; the volatile second memory is used to load a group of image processing parameters from the multiple groups of image processing parameters; the processor is used to execute the identity authentication solution provided by the embodiment of the present application based on the received image.

[0036] The above non-volatile first memory can be a memory of the read-only memory (ROM) type, a programmable read-only memory (PROM) type, an electrically alterable read-only memory (EAROM) type, etc. In one case, the first memory can be flash memory in the ROM type.

[0037] The above-mentioned volatile second memory refers to a memory of the Random Access Memory (RAM) type, specifically, it can be a memory of types such as Dynamic Random Access Memory (DRAM) or Static Random Access Memory (SRAM).

[0038] For the specific meanings of the above-mentioned concepts such as image processing parameters and biometrics, please refer to the specific embodiments described later, and will not be elaborated here for the time being.

[0039] Next, the application scenarios of the solution provided by the embodiments of the present application will be described.

[0040] The application scenarios of the solution provided by the embodiments of the present application can be: various scenarios of identity authentication based on biometrics, such as access control recognition, mobile payment, campus management, etc. For example, in the mobile payment scenario, a merchant can authenticate the identity of a customer based on the biometric of the customer and conduct payment when the authentication is passed; another example is that in the campus management scenario, a school can use biometric authentication technology for student attendance management, library borrowing management, etc.

[0041] Next, in combination with the accompanying drawings, the identity authentication solution provided by the embodiments of the present application will be introduced in detail.

[0042] See Figure 1 , which is a schematic flowchart of an identity authentication method provided by the embodiments of the present application. The above method is applied to a processor in an identity authentication module and includes the following steps S101 - step S104.

[0043] Step S101: Identify the first feature area in the first image collected by the image acquisition component.

[0044] The above-mentioned image acquisition component can be a component for collecting visible light images, a component for collecting infrared images, or a component that can collect both visible light images and infrared images.

[0045] In the solution of the embodiments of the present application, identity authentication can be performed by extracting the biometric in the above-mentioned first image.

[0046] Among them, the biometric for identity authentication can include multiple types, and the embodiments of the present application do not limit this.

[0047] In one case, the types of the above-mentioned biometric include at least two of the following types:

[0048] Palm, face, back of hand, eye, auricle, finger.

[0049] Among them, the biometric features of the palm type may include palmprint features, palm vein features, etc.; the biometric features of the back of the hand type may include dorsal vein features, etc.; the biometric features of the eye type may include iris features, etc.; the biometric features of the finger type may include fingerprint features, etc.

[0050] In this way, identity authentication can be performed based on a rich variety of biometric features, further improving the convenience of identity authentication.

[0051] The first feature region may be a region in the first image for extracting the above various biometric features. For example, it may be a palm region, a face region, a dorsal region, an eye region, etc. in the first image.

[0052] The specific method for identifying the first feature region from the first image will be introduced below.

[0053] In one implementation, a pattern matching algorithm can be used to identify the first feature region in the first image.

[0054] Specifically, each region can be divided in the first image. For each set biometric feature type, an image matching algorithm such as the normalized cross-correlation algorithm is used to calculate the similarity between the pre-collected template image of the biometric feature type and each region in the first image, and the region with the highest similarity is determined as the region for extracting the biometric feature of this type.

[0055] For example, for the biometric feature type of the face, multiple template images can be pre-collected, and then the similarity between the multiple template images and each region in the first image is calculated to obtain the average similarity between each region and the template image, and the region in the first image with the largest average similarity is determined as the region for extracting the face biometric feature.

[0056] In another implementation, the first image can be input into a pre-trained feature region recognition model to obtain the first feature region in the first image output by the feature region recognition model. The above-mentioned part recognition model can be a Convolutional Neural Networks (CNN) model, a Transformer network model, etc., and the embodiments of the present invention do not limit this.

[0057] Step S102: If the first type of the biometric feature to be extracted in the first feature region is inconsistent with the second type corresponding to the image processing parameters already loaded in the second memory, and the first type is a registered type, then load the image processing parameters corresponding to the first type from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory.

[0058] First, the first type, the second type, and the registered type will be introduced.

[0059] 1. First type

[0060] The first type is the type of biometric feature to be extracted in the first feature region. For example, if the first feature region is the face region, the first type is face; if the first feature region is the palm region, the first type is palm.

[0061] 2. Second type

[0062] As can be seen from the foregoing introduction, the first memory is used to store multiple groups of image processing parameters, and each group of image processing parameters corresponds to a type of biometric feature. For example, the face type corresponds to face image processing parameters, the palm type corresponds to palm image processing parameters, and so on.

[0063] One group of the multiple groups of image processing parameters is loaded into the second memory, and the type corresponding to the image processing parameter currently recorded in the second memory is the above-mentioned second type. For example, if the type corresponding to the image processing parameter currently loaded in the second memory is face, the second type is face type; if the type corresponding to the image processing parameter currently loaded in the second memory is palm, the second type is palm type.

[0064] 3. Registered type

[0065] The registered type is: the type of the recorded reference biometric feature.

[0066] The above-mentioned reference biometric feature is: the feature used for feature comparison and identity authentication based on the comparison result. The identity authentication module can pre-enter the above-mentioned reference biometric feature, and the type of the reference biometric feature is the registered type.

[0067] From this, it can be seen that for the registered type, identity authentication can be performed based on the reference biometric feature of the registered type.

[0068] In the case where the first type is inconsistent with the second type, that is, the type of the biometric feature to be extracted in the first feature region does not match the type of the currently loaded image processing parameter. Therefore, it can be preliminarily determined that image parameter switching is to be performed. Furthermore, if the first type is the registered type, it means that identity authentication can be performed based on the reference biometric feature of the registered type. Therefore, image parameter switching can be performed to make the type of the biometric feature consistent with the image processing parameter, and then the subsequent identity authentication operation can be executed.

[0069] When switching image parameters, the image processing parameters corresponding to the first type are loaded from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory. That is, the image processing parameters loaded in the second memory are replaced from the image processing parameters corresponding to the second type to the image processing parameters corresponding to the first type, and a set of image processing parameters is always loaded in the second memory.

[0070] Step S103: Perform image processing on the first feature region based on the image processing parameters loaded in the second memory, and extract the first biometric feature of the processed first feature region.

[0071] In this step, the image processing parameters loaded in the second memory, that is, the currently loaded image processing parameters, can be the replaced image processing parameters or the unreplaced image processing parameters.

[0072] The following provides a detailed introduction to the image processing parameters.

[0073] The image processing parameters can include parameters such as Automatic Exposure (AE), noise reduction, sharpening, and brightness (Gamma) correction. Moreover, the image processing parameters corresponding to different biometric feature types can be different.

[0074] Specifically, the staff can, based on experience and in combination with the characteristics of the biometric feature type, determine the image processing parameters corresponding to the biometric feature type, so that after processing the first feature region according to the image processing parameters, a more accurate and high-quality biometric feature can be extracted from the first feature region.

[0075] The following takes the face type and the palm type as examples for specific illustration.

[0076] For example, for the face type, the face in the image is generally at a long distance, and the facial biometric feature mainly relies on the overall features of the face region, with low requirements for local contrast. Therefore, the average target brightness in the automatic exposure parameters can be set to a relatively high value, such as 110 brightness units, etc.; noise reduction and sharpening can be turned off to retain facial details; the brightness parameters for brightening dark areas and darkening bright areas can be determined to make the face region clearly visible.

[0077] Another example is that for the palm type, the palm in the image is generally at a short distance, and the palm vein feature depends on the vein information inside the palm, with high requirements for contrast and low dependence on brightness. Therefore, the average target brightness in the automatic exposure parameters can be set to a relatively low value, such as 70 brightness units, etc.; noise reduction and sharpening can be turned on to highlight the vein information; the brightness parameters for darkening dark areas and slightly darkening bright areas can be determined to highlight the contrast between vein pixels and palm background pixels.

[0078] It should be noted that the above content is only an example for facilitating the understanding of image processing parameters. The image processing parameters corresponding to the biometric types can also be set based on other considerations, and the embodiments of the present application do not limit this.

[0079] After performing image processing on the first feature region according to the image processing parameters loaded in the second memory, the first biometric feature of the processed first feature region can be extracted according to the set image feature extraction strategy corresponding to the first type.

[0080] Among them, the image feature extraction strategy includes: setting corresponding image feature extraction algorithms for various biometric types, setting corresponding image processing models for various biometric types, etc., which will not be elaborated here.

[0081] Step S104: Perform identity authentication based on the first biometric feature and the reference biometric feature of the first type.

[0082] The similarity between the first biometric feature and the reference biometric feature of the first type can be calculated, and then identity authentication can be performed based on the obtained similarity.

[0083] Specifically, it can be determined whether there is a target similarity greater than the set similarity threshold in the obtained similarities. If so, it means that there is a feature with a relatively high similarity between the reference biometric feature already entered and the first biometric feature, thereby indicating that the biometric features of the user who entered the reference biometric feature and the current authenticated user are relatively similar, and thus it can be determined that the identity authentication is passed.

[0084] As can be seen from the above, when applying the solution provided by the embodiments of the present application for identity authentication, the first feature region in the first image collected by the image acquisition component is recognized. If the first type of the biometric feature to be extracted in the first feature region is inconsistent with the second type corresponding to the image processing parameters already loaded in the second memory, and the first type is a registered type, then the image processing parameters corresponding to the first type are loaded from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory; then, image processing is performed on the first feature region according to the image processing parameters loaded in the second memory, and the first biometric feature of the processed first feature region is extracted; furthermore, identity authentication can be performed based on the first biometric feature and the reference biometric feature of the first type.

[0085] It can be seen that in the solution provided by the embodiments of the present application, before extracting the biometric feature from the first image, the type of the biometric feature to be extracted is considered. According to whether the first type of the biometric feature to be extracted matches the second type corresponding to the currently loaded image processing parameters, it is determined whether to switch the image processing parameters, so that the image processing parameters match the biometric feature to be extracted, so as to accurately and high-quality biometric features can be extracted. Furthermore, the identity authentication module can smoothly perform subsequent identity authentication based on the extracted biometric features. That is, by flexibly switching the image processing parameters, the image processing parameters can match the biometric features to be extracted in various situations, so that identity authentication based on various biometric features can be realized based on the images collected by one image acquisition component, without setting multiple independent image acquisition components, reducing the number of hardware in the identity authentication module and lowering the hardware cost of identity recognition.

[0086] The above step S102 introduces the situation where the first type is inconsistent with the second type and the first type is a registered type. Next, other situations will be introduced.

[0087] For the situation where the first type is inconsistent with the second type and the first type is not a registered type:

[0088] Since the first type is not a registered type, that is, there is no reference biometric feature of the first type, and thus identity authentication cannot be performed based on the reference biometric feature. Therefore, the image parameter switching operation can be not executed, and the authentication process can be directly ended.

[0089] For the situation where the first type is consistent with the second type and the first type is a registered type:

[0090] In this case, it means that the type of the biometric feature to be extracted in the first feature region matches the type of the currently loaded image processing parameters, and the reference biometric feature of the first type can be used. Therefore, the parameter switching operation is not executed, and the subsequent image processing operations are directly executed.

[0091] For the situation where the first type is consistent with the second type and the first type is not a registered type:

[0092] Similarly, since the first type is not a registered type, identity authentication cannot be performed based on the reference biometric feature. Therefore, the authentication process can be directly ended.

[0093] In an embodiment of the present application, when the image processing parameters corresponding to the first type are successfully loaded from the first memory to the second memory, after the above step S104, the following steps may further be included:

[0094] Load the image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory to replace the image processing parameters corresponding to the first type in the second memory.

[0095] Among them, the recognition priorities corresponding to the types of various biometric features can be preset in advance. The above recognition priorities can be set based on factors such as the extraction difficulty of biometric features and the accuracy of identity authentication based on biometric features. The embodiments of the present application do not limit this, and the following will be introduced by way of example.

[0096] Taking facial features and palm vein features as an example, assuming that the extraction difficulty of facial features is lower than that of palm vein features and the accuracy of identity authentication based on facial features is higher than that of palm vein features, the recognition priority of facial features can be set to a higher priority, and the recognition priority of palm vein features can be set to a lower priority.

[0097] In this way, after replacing the image processing parameters with the image processing parameters corresponding to the first type of biometric feature to be extracted, the currently loaded image processing parameters can be timely replaced with the image processing parameters corresponding to the registered type with the highest recognition priority, that is, the image processing parameters with the highest recognition priority are preferentially loaded, which is beneficial to extracting high-quality biometric features based on the image processing parameters corresponding to the type with the highest recognition priority, and reduces the probability of switching image processing parameters during subsequent identity authentication, improving the accuracy and efficiency of identity authentication.

[0098] In an embodiment of the present application, when identifying the feature region in the above step S101, it can also be implemented based on the following steps:

[0099] Step A: Identify the initial feature region in the first image collected by the image acquisition component.

[0100] The initial feature region refers to the region in the first image for extracting the above various biometric features. In this embodiment, before determining the first feature region, the region in the first image for extracting the above various biometric features is called the initial feature region.

[0101] Step B: If multiple initial feature regions are identified, then based on the selection factor, determine the initial feature region whose type of biometric feature to be extracted belongs to the registered type from the multiple initial feature regions as the first feature region.

[0102] The following will introduce the method for determining the first feature region according to different selection factors.

[0103] In one case, the selection factor includes the recognition priority of the type of biometric feature to be extracted in the initial feature region.

[0104] In this case, the initial feature region with the highest recognition priority among the types of biometric features to be extracted can be determined as the first feature region.

[0105] In another case, the selection factor includes the image quality characterization value of the initial feature region.

[0106] The above image quality characterization value can be obtained according to parameters such as the clarity and brightness of the initial image region. Specifically, according to the set conversion relationship, the above parameters can be converted into the image quality characterization value.

[0107] In this case, the initial feature region with the largest image quality characterization value can be determined as the first feature region.

[0108] In yet another case, the selection factor includes the above recognition priority and the image quality characterization value.

[0109] In this case, the weighted scores of each initial feature region can be calculated according to the weight coefficients set for the recognition priority and the image quality characterization value, and the initial feature region with the highest weighted score can be determined as the first feature region. The specific calculation method is not elaborated here.

[0110] In this way, based on the selection factor, the initial feature region with the highest recognition priority or the best image quality can be determined as the first feature region, which is conducive to extracting high-quality biometric features from the determined first feature region and improving the accuracy of subsequent identity authentication based on biometric features.

[0111] In an embodiment of the present application, in the case of recognizing multiple initial feature regions, if the identity authentication fails based on the first biometric feature and the reference biometric feature of the first type, the following step C can also be executed:

[0112] Step C: Based on the selection factor, determine the initial feature region whose type of biometric feature to be extracted belongs to the registered type from the initial feature regions that have not participated in the identity authentication as the new first feature region, and perform identity authentication based on the new first feature region.

[0113] In this step, the method of determining the new first feature region based on the selection factor is similar to the method of determining the first feature region in the above step B, and the difference is only that in this step, the first feature region is selected from the initial feature regions that have participated in the identity authentication.

[0114] In the case of recognizing multiple initial feature regions, if the identity authentication fails based on the first feature region determined last time, new first feature regions can continue to be selected from the initial feature regions that have not participated, and identity authentication can be performed again based on the new first feature regions, which improves the success rate of identity authentication.

[0115] In one embodiment of the present application, after determining that the identity authentication is successful, it is also possible to determine the target reference biometric feature corresponding to the maximum target similarity, determine the object identifier corresponding to the target reference biometric feature, and determine the object indicated by the object identifier as the object in the first image.

[0116] Next, in combination with Figure 2 , the method of inputting the reference biometric feature will be introduced.

[0117] Refer to Figure 2 , which is a schematic flowchart of a biometric feature input method provided by an embodiment of the present application. The above method includes the following steps S201 - step S204.

[0118] Step S201: If the second type is inconsistent with the third type, then load the image processing parameters corresponding to the third type from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory.

[0119] The above third type is: the registration type selected by the user, which can be the face, palm, eye, etc. mentioned above.

[0120] The second type is inconsistent with the third type, that is, the currently loaded image processing parameters are inconsistent with the registration type selected by the user. Therefore, an image parameter switching operation can be performed to switch the currently loaded image processing parameters to the image processing parameters corresponding to the registration type selected by the user.

[0121] Step S202: Identify the second feature area of the registration type in the second image collected by the image acquisition component.

[0122] The method of identifying the second feature area from the second image can be obtained based on the implementation method of identifying the first feature area from the first image introduced above, with the difference being the specific image and feature area.

[0123] Step S203: Perform image processing on the second feature area based on the image processing parameters loaded in the second memory.

[0124] For the meaning of the image processing parameters, refer to the introduction in the embodiment of the identity authentication method above, and details will not be elaborated here.

[0125] Step S204: Extract the second biometric feature of the processed second feature area as the reference biometric feature of the registration type, and store the reference biometric feature.

[0126] The method of extracting the second biometric feature can be obtained based on the implementation method of extracting the first biological area introduced above, with the difference being only the specific feature area and biometric feature.

[0127] In this way, after storing the reference biometric features of the registered type, the feature entry is completed, and subsequent identity authentication can be performed based on the reference biometric features of the registered type.

[0128] It can be seen that in this embodiment, before feature entry, the relationship between the registered type selected by the user and the currently loaded image processing parameters is considered. Whether to switch the image processing parameters is determined according to whether the second type corresponding to the registered type and the currently loaded image processing parameters matches, so that the image processing parameters match the biometric features to be extracted, so as to accurately and high-quality biometric features can be extracted. Furthermore, the identity authentication module can extract and store the biometric features, and successfully complete the entry of the basic biometric features. That is, by flexibly switching the image processing parameters, the image processing parameters can match the biometric features to be extracted in various situations, so that the reference biometric features of various biometric features can be entered based on the images collected by one image acquisition component, without setting multiple independent image acquisition components, reducing the number of hardware in the identity authentication module, and reducing the hardware cost of identity recognition.

[0129] In an embodiment of the present application, in the case of successfully loading the image processing parameters corresponding to the third type from the first memory to the second memory, after storing the reference biometric features, the following steps may also be performed:

[0130] Load the image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory to replace the image processing parameters corresponding to the third type in the second memory.

[0131] In this way, after replacing the image processing parameters with the image processing parameters corresponding to the registered type, the currently loaded image processing parameters can be timely replaced with the image processing parameters corresponding to the registered type with the highest recognition priority, that is, the image processing parameters with the highest recognition priority are preferentially loaded, which is beneficial to extracting and entering high-quality biometric features based on the image processing parameters with the highest recognition priority, and reducing the probability of switching the image processing parameters during subsequent feature entry, improving the quality of the entered features and the efficiency of feature entry.

[0132] In an embodiment of the present application, in the case of successfully loading the image processing parameters corresponding to the third type from the first memory to the second memory, after storing the reference biometric features, the following step D1 may be performed:

[0133] Step D1: In the case where the second feature area is not recognized and there is a registered type, load the image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory to replace the image processing parameters corresponding to the third type in the second memory.

[0134] In this case, it indicates that the feature entry fails and there are registered types. The image processing parameters can be replaced with the image processing parameters corresponding to the registered type with the highest recognition priority, which is beneficial to extracting and entering high-quality biometric features based on the image processing parameters corresponding to the type with the highest recognition priority subsequently, and reduces the probability of switching the image processing parameters during subsequent feature entry.

[0135] In another embodiment of the present application, in the case of successfully loading the image processing parameters corresponding to the third type from the first memory to the second memory, after storing the reference biometric feature, the following step D2 can be executed:

[0136] Step D2: In the case of not recognizing the second feature area and there being no registered types, load the image processing parameters corresponding to the type with the highest priority from the first memory to the second memory to replace the image processing parameters corresponding to the third type in the second memory.

[0137] Compared with step D1, the difference in this step is that the loaded feature is replaced from the image processing parameters corresponding to the registered type with the highest recognition priority with: the image processing parameters corresponding to the type with the highest recognition priority among all types.

[0138] In this case, it indicates that the feature entry fails and there are no registered types. Therefore, the image processing parameters can be replaced with the image processing parameters corresponding to the type with the highest recognition priority among all types, which is beneficial to extracting and entering high-quality biometric features based on the image processing parameters corresponding to the type with the highest recognition priority subsequently, and reduces the probability of switching the image processing parameters during subsequent feature entry.

[0139] As can be seen from the foregoing introduction, in specific cases, the solution provided by the embodiments of the present application will trigger an image processing parameter switching operation to switch the image processing parameters. Among them, the switching of the image processing parameters can be executed by an Image Signal Processor (ISP) module in the identity authentication, specifically including the ISP module actively switching parameters and the ISP module passively switching parameters upon receiving an instruction from the processor.

[0140] Taking the types of biometric features including face type and palm type as an example below, various cases of active switching and passive switching of the image processing parameters are described in detail. Among them, the recognition priority of the face type is higher than that of the palm type.

[0141] Cases of active switching:

[0142] Active switching case 1: The user registration template contains both a face template and a palm template. After the user completes a palm vein recognition and the currently loaded ISP parameters are the palm ISP parameters, regardless of the recognition result, the ISP module will actively trigger parameter switching and switch the palm ISP parameters to the default face ISP parameters after the recognition ends.

[0143] Among them, the registration template refers to the aforementioned input reference features. The face template is also the input face reference biometric feature, and the palm template is also the input palm vein reference biometric feature. The palm ISP parameters refer to the image processing parameters corresponding to the palm vein, and the face ISP parameters refer to the image processing parameters corresponding to the face.

[0144] The recognition priority of the face type is higher than that of the palm type. Therefore, the face ISP parameters can also be called the default ISP parameters.

[0145] Active switching case 2: The user registration template only contains a face template. When the user completes a palm template registration and the currently loaded ISP parameters are the palm ISP parameters, regardless of the registration result, the ISP module will actively trigger parameter switching and switch the palm ISP parameters to the default face ISP parameters after the registration ends.

[0146] Active switching case 3: The user registration template only contains a palm template. When the user completes a face template registration and the registration fails, since the ISP parameters are the face ISP parameters at this time but the registration template only has a palm template, the ISP module will actively trigger parameter switching and switch the face ISP parameters to the palm ISP parameters.

[0147] Active switching case 4: The user has no registered template. When the user completes a palm template registration and the registration fails, since there is no registered template at this time and the current ISP parameters are the palm ISP parameters rather than the default face ISP parameters, the ISP module will actively trigger parameter switching and switch the palm ISP parameters to the face ISP parameters.

[0148] Active switching case 5: The user registration template contains both a face template and a palm template. After the user completes a palm vein registration and the currently loaded ISP parameters are the palm ISP parameters, regardless of the registration result, the ISP module will actively trigger parameter switching and switch the palm ISP parameters to the default face ISP parameters after the registration ends.

[0149] Passive switching cases:

[0150] Passive switching case 1: In the template registration stage, if the template type registered by the user is inconsistent with the current ISP parameter type, the processor will notify the ISP module to perform parameter switching, so that the ISP module will passively switch the current ISP parameter to another ISP parameter.

[0151] For example, if the user registers a face template, but the current ISP parameter is the palm ISP parameter, the ISP module will receive an instruction from the processor and passively switch the current ISP parameter to the face ISP parameter; another example is that if the user registers a palm template, but the current ISP parameter is the face ISP parameter, the ISP module will receive an instruction from the processor and passively switch the current ISP parameter to the palm ISP parameter.

[0152] Passive switching case 2: In the identity authentication stage, the feature type corresponding to the recognized feature area is inconsistent with the current ISP parameter type. For example, if the detected feature area is the face and the corresponding feature type is the face type, but the current ISP parameter is the palm ISP parameter, the ISP module will receive an instruction from the processor and passively switch the current ISP parameter to the face ISP parameter.

[0153] The following combines Figure 3 and Figure 4 , taking the biometric types including face and palm as an example, to introduce the complete process of the user registering face templates and palm templates.

[0154] First, refer to Figure 3 , to introduce the process of registering a face template during template registration.

[0155] The process of the user registering a face template is further divided into the following two cases:

[0156] 1. For the cases where the user registers for the first time, has only registered the face, or has registered both the face and the palm:

[0157] Since the recognition priority of the face is higher than that of the palm, in these cases, the default ISP parameter is the face ISP parameter, and the currently registered biometric category is the face, that is, the current ISP parameter matches the registered biometric category.

[0158] Therefore, face detection can be directly performed to determine whether a face is detected. If so, face feature extraction is performed, and the extracted face features are stored, so that the face template registration is successful. After successful registration, the registered templates include the face template, so no parameter switching is performed, and the face ISP parameter is still maintained; if not, it means that the face template registration fails. At this time, the registered templates include the face template or there is no registered module, so the face ISP parameter is still maintained.

[0159] 2. For the case where the user has only registered the palm:

[0160] When the user has only registered the palm, the currently loaded default ISP parameters in the memory are the palm ISP parameters, and the currently registered biometric category is the face, that is, the current ISP parameters do not match the registered biometric category. Therefore, the palm ISP parameters can be switched to the face ISP parameters (corresponding to passive switching case 1).

[0161] Then, perform face detection to determine whether a face is detected. If so, extract the face features and store the extracted face features, so that the face template registration is successful. At this time, the face has been registered, so keep the face ISP parameters; if not, it means that the face template registration fails. At this time, the only registered biometric type is still the palm. Therefore, the face ISP parameters need to be switched to the palm ISP parameters (corresponding to active switching case 3).

[0162] See also Figure 4 for the introduction of the palm template registration process during template registration.

[0163] The process of the user registering the palm template can be divided into the following three cases:

[0164] 1. For the case where the user registers for the first time:

[0165] Since the recognition priority of the face is higher than that of the palm, in the case of no registered type, the default ISP parameters are the face ISP parameters, and the currently registered biometric category is the palm, that is, the current ISP parameters do not match the registered biometric category. Therefore, the face ISP parameters can be switched to the palm ISP parameters (corresponding to passive switching case 1).

[0166] Then, perform palm detection to determine whether a palm is detected. If so, extract the palm vein features and store the extracted palm vein features, so that the palm template registration is successful. At this time, only the palm template has been registered, so no parameter switching is performed and the palm ISP parameters are kept; if not, it means that the palm template registration fails. At this time, there is no registered biometric type. Therefore, the palm ISP parameters are switched back to the default face ISP parameters (corresponding to active switching case 4).

[0167] 2. For the case where the user has only registered the face, or has registered both the face and the palm:

[0168] Since the recognition priority of the face is higher than that of the palm, as long as the face has been registered, the default ISP parameters are the face ISP parameters. Currently, the registered biometric category is the palm, that is, the current ISP parameters do not match the registered biometric category. Therefore, the face ISP parameters can be switched to the palm ISP parameters (corresponding to passive switching case 1).

[0169] Then, perform palm detection to determine whether a palm is detected. If so, extract the palm vein features and store the extracted palm vein features, so that the palm template registration is successful. However, since the face template has been registered, the palm ISP parameters need to be switched to the default face ISP parameters (corresponding to active switching cases 2 and 5); if not, it means that the palm template registration fails. Also, because the face template has been registered, the palm ISP parameters need to be switched to the default face ISP parameters (corresponding to active switching cases 2 and 5).

[0170] 3. For the case where the user has only registered the palm:

[0171] In this case, since only the palm has been registered, the currently loaded ISP parameters are the palm ISP parameters, and the currently registered biometric category is the palm, that is, the current ISP parameters match the registered biometric category.

[0172] Therefore, palm detection can be directly performed to determine whether a palm is detected. If so, extract the palm vein features and store the extracted palm vein features, so that the palm template registration is successful. And since only the palm has been registered, no switching is performed and the palm ISP parameters are still maintained; if no palm is detected, it means that the palm template registration fails. Since only the palm has been registered, no switching is performed and the face ISP parameters are still maintained.

[0173] Combined with Figure 5 , the process of user authentication is introduced. This process can be divided into the following three cases:

[0174] 1. The case where only the face has been registered

[0175] Directly perform face detection to determine whether a face is detected. If a face is detected, extract the face features and determine whether the feature comparison passes. If so, determine that the authentication is successful; if not, determine that the authentication fails; if no face is detected, directly determine that the authentication fails.

[0176] Among them, determining whether the feature comparison passes, that is, the similarity between the extracted face features and the registered face template features, and then performing identity authentication based on the obtained similarity.

[0177] Specifically, it can be determined whether there is a target similarity greater than the set similarity threshold in the obtained similarities. If so, it indicates that the identity authentication is successful; otherwise, the identity authentication is determined to be failed.

[0178] 2. The case of only registering the palm

[0179] Directly perform palm detection to determine whether a palm is detected. If a palm is detected, perform palm vein feature extraction and determine whether the feature comparison passes. If so, determine that the authentication is successful; if not, determine that the authentication is failed. If no palm is detected, directly determine that the authentication is failed.

[0180] 3. The case of registering the face and the palm

[0181] First, perform face detection to determine whether a face is detected. If a face is detected, perform face feature extraction and determine whether the feature comparison passes. If so, determine that the authentication is successful; if not, determine that the authentication is failed.

[0182] If no face is detected, perform palm detection to determine whether a palm is detected. In the case of detecting a palm, switch the currently default face ISP parameter to the palm ISP parameter (corresponding to the passive switching case 2), then perform palm vein feature extraction and perform feature comparison to determine whether the feature comparison passes. If it passes, determine that the authentication is successful; otherwise, determine that the authentication is failed. Regardless of whether the feature comparison passes, switch the palm ISP parameter to the default face ISP parameter (corresponding to the active switching case 1); in the case of not detecting a palm, determine that the authentication is failed.

[0183] As can be seen from the above, the solution provided by the embodiment of the present application can implement identity authentication based on multiple biometric features such as the face and palm vein only through one image acquisition component (lens), without the need for multiple image acquisition components or additional hardware such as a distance sensor, significantly reducing the consumption of hardware resources and saving hardware costs. While minimizing costs as much as possible, multiple biometric authentication functions are implemented on the same identity authentication module, and different image effects are obtained for different targets. Specifically, a common infrared lens (IR lens) can be used to achieve palm vein recognition at 15 - 35 cm and face recognition at 40 - 120 cm, without the need for other hardware assistance.

[0184] Moreover, by using face detection and palm detection algorithms to accurately determine the object target in front of the lens, the ISP parameter can be reasonably switched, making the adjustment of the ISP parameter more accurate, and the image processed based on the ISP parameter is more likely to extract high-quality features.

[0185] Furthermore, according to different situations of the user registration template, the present invention precisely sets ISP parameter settings and switching processes in various situations, making the parameter switching process design in the registration and identity authentication stages of the identity authentication module more reasonable and having less switching loss.

[0186] In the solution provided by the embodiments of the present application, for the processing of collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved, etc., it is all executed on the premise that the user is aware and authorizes, and complies with the provisions of relevant laws and regulations, and does not violate public order and good customs.

[0187] It should be noted that the two-dimensional face images in this embodiment are from a public dataset.

[0188] Corresponding to the above identity authentication method, the embodiments of the present application further provide an identity authentication device.

[0189] See Figure 6 , which is a schematic structural diagram of an identity authentication device provided by the embodiments of the present application, applied to a processor in an identity authentication module. The identity authentication module further includes: an image acquisition component, a non-volatile first memory, and a volatile second memory. Multiple groups of image processing parameters are stored in the first memory, and each group of image processing parameters corresponds to a type of biometric feature. One group of image processing parameters among the multiple groups of image processing parameters is loaded in the second memory. The above device includes the following modules:

[0190] A first recognition module 601, configured to recognize a first feature area in a first image acquired by the image acquisition component;

[0191] A first parameter loading module 602, configured to, if the first type of biometric feature to be extracted in the first feature area is inconsistent with the second type corresponding to the image processing parameters already loaded in the second memory, and the first type is a registered type, load the image processing parameters corresponding to the first type from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory, where the registered type is: the type of the benchmark biometric feature that has been entered;

[0192] A first feature extraction module 603, configured to perform image processing on the first feature area based on the image processing parameters loaded in the second memory, and extract the first biometric feature of the processed first feature area;

[0193] A first identity authentication module 604, configured to perform identity authentication based on the first biometric feature and the benchmark biometric feature of the first type.

[0194] As can be seen from the above, when performing identity authentication using the solution provided in the embodiments of the present application, the first feature area in the first image collected by the recognition image acquisition component is recognized. If the first type of the biometric feature to be extracted in the first feature area is inconsistent with the second type corresponding to the image processing parameters already loaded in the second memory, and the first type is a registered type, the image processing parameters corresponding to the first type are loaded from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory; then, image processing is performed on the first feature area based on the image processing parameters loaded in the second memory, and the first biometric feature of the processed first feature area is extracted; furthermore, identity authentication can be performed based on the first biometric feature and the reference biometric feature of the first type.

[0195] It can be seen that in the solution provided in the embodiments of the present application, before extracting the biometric feature from the first image, the type of the biometric feature to be extracted is considered. According to whether the first type of the biometric feature to be extracted matches the second type corresponding to the currently loaded image processing parameters, it is determined whether to switch the image processing parameters, so that the image processing parameters match the biometric feature to be extracted, so as to be able to extract accurate and high-quality biometric features. Furthermore, the identity authentication module can smoothly perform subsequent identity authentication based on the extracted biometric features. That is, by flexibly switching the image processing parameters, the image processing parameters can match the biometric features to be extracted in various situations, so that identity authentication based on various biometric features can be realized based on the image collected by one image acquisition component, without setting multiple independent image acquisition components, reducing the number of hardware in the identity authentication module and lowering the hardware cost of identity recognition.

[0196] In an embodiment of the present application, if the image processing parameters corresponding to the first type are successfully loaded from the first memory to the second memory, the device further includes:

[0197] A second parameter loading module, configured to, after completing identity authentication based on the first biometric feature and the reference biometric feature of the first type, load the image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory to replace the image processing parameters corresponding to the first type in the second memory.

[0198] In this way, after replacing the image processing parameters with the image processing parameters corresponding to the first type of biometric feature to be extracted, the currently loaded image processing parameters can be promptly replaced with the image processing parameters corresponding to the registered type with the highest recognition priority, that is, the image processing parameters with the highest recognition priority are preferentially loaded, which is beneficial to extracting high-quality biometric features based on the image processing parameters corresponding to the type with the highest recognition priority, and reduces the probability of switching image processing parameters during subsequent identity authentication, improving the accuracy and efficiency of identity authentication.

[0199] In one embodiment of the present application, the first recognition module 601 is specifically configured to recognize the initial feature region in the first image collected by the image acquisition component; if multiple initial feature regions are recognized, then based on the selection factor, determine the initial feature region whose type of biometric feature to be extracted belongs to the registered type from the multiple initial feature regions as the first feature region, where the selection factor includes: the recognition priority of the type of biometric feature to be extracted in the initial feature region, and / or, the image quality characterization value of the initial feature region.

[0200] In this way, the initial feature region with the highest recognition priority or the best image quality can be determined based on the selection factor as the first feature region, which is beneficial to extracting high-quality biometric features from the determined first feature region and improving the accuracy during subsequent identity authentication based on biometric features.

[0201] In one embodiment of the present application, if the identity authentication fails based on the first biometric feature and the reference biometric feature of the first type, the device further includes:

[0202] A second identity authentication module, configured to determine, based on the selection factor, the initial feature region whose type of biometric feature to be extracted belongs to the registered type from the initial feature regions that have not participated in the identity authentication as the new first feature region, and perform identity authentication based on the new first feature region.

[0203] In the case where multiple initial feature regions are recognized, if the identity authentication fails based on the first feature region determined last time, the new first feature region can continue to be selected from the initial feature regions that have not participated, and identity authentication is performed again based on the new first feature region, improving the success rate of identity authentication.

[0204] In one embodiment of the present application, the reference biometric feature is entered in the following manner:

[0205] If the second type is inconsistent with the third type, load the image processing parameters corresponding to the third type from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory, where the third type is: the registration type selected by the user; identify the second feature area of the registration type in the second image collected by the image acquisition component; perform image processing on the second feature area based on the image processing parameters loaded in the second memory; extract the second biometric feature of the processed second feature area as the reference biometric feature of the registration type, and store the reference biometric feature.

[0206] It can be seen that in this embodiment, before feature entry, the relationship between the registration type selected by the user and the currently loaded image processing parameters is considered. According to whether the registration type matches the second type corresponding to the currently loaded image processing parameters, it is determined whether to switch the image processing parameters, so that the image processing parameters match the biometric features to be extracted, so as to be able to extract accurate and high-quality biometric features. Furthermore, the identity authentication module can extract and store biometric features, and successfully complete the entry of basic biometric features. That is, through the flexible switching of image processing parameters, the image processing parameters can match the biometric features to be extracted in various situations, so that the reference biometric features of various biometric features can be entered based on the images collected by one image acquisition component, without setting multiple independent image acquisition components, reducing the number of hardware in the identity authentication module and lowering the hardware cost of identity recognition.

[0207] In an embodiment of the present application, if the image processing parameters corresponding to the third type are successfully loaded from the first memory to the second memory, the device further includes:

[0208] A third parameter loading module, configured to, after storing the reference biometric feature, load the image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory to replace the image processing parameters corresponding to the third type in the second memory.

[0209] In this way, after replacing the image processing parameters with the image processing parameters corresponding to the registration type, the currently loaded image processing parameters can be timely replaced with the image processing parameters corresponding to the registered type with the highest recognition priority, that is, the image processing parameters with the highest recognition priority are preferentially loaded, which is beneficial to extracting and entering high-quality biometric features based on the image processing parameters with the highest recognition priority, and reduces the probability of switching image processing parameters during subsequent feature entry, improving the quality of the entered features and the efficiency of feature entry.

[0210] In one embodiment of the present application, if the image processing parameters corresponding to the third type are successfully loaded from the first memory to the second memory, the device further includes:

[0211] A fourth parameter loading module, configured to, when the second feature region is not recognized and there are registered types, load the image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory to replace the image processing parameters corresponding to the third type in the second memory;

[0212] And / or

[0213] A fifth parameter loading module, configured to, when the second feature region is not recognized and there are no registered types, load the image processing parameters corresponding to the type with the highest priority from the first memory to the second memory to replace the image processing parameters corresponding to the third type in the second memory.

[0214] In this case, it indicates that the feature entry fails and there are registered types. The image processing parameters can be replaced with the image processing parameters corresponding to the registered type with the highest recognition priority, which is beneficial to extracting and entering high-quality biometric features based on the image processing parameters corresponding to the registered type with the highest recognition priority, and reduces the probability of image processing parameter switching during subsequent feature entry; or, it indicates that the feature entry fails and there are no registered types. Therefore, the image processing parameters can be replaced with the image processing parameters corresponding to the type with the highest recognition priority among all types, which is beneficial to extracting and entering high-quality biometric features based on the image processing parameters corresponding to the type with the highest recognition priority, and reduces the probability of image processing parameter switching during subsequent feature entry.

[0215] In one embodiment of the present application, the image acquisition component is: an infrared image acquisition component;

[0216] And / or

[0217] The types of the biometric features include at least two of the following types:

[0218] Palm, face, back of hand, eye, auricle, finger.

[0219] In this way, identity authentication can be performed based on biometric features with rich types, further improving the convenience of identity authentication.

[0220] An embodiment of the present application further provides an identity authentication module, as Figure 7 shown, including:

[0221] An image acquisition component 701, configured to acquire an image and send the acquired image to a processor 704;

[0222] A first memory 702 for storing multiple sets of image processing parameters, each set of image processing parameters corresponding to a type of biometric feature;

[0223] A second memory 703 for loading a set of image processing parameters from the multiple sets of image processing parameters;

[0224] A processor 704 for executing the foregoing identity authentication method.

[0225] Among them, the first memory 702 is a non-volatile memory, the second memory 703 is a volatile memory, and the above identity authentication module may further include a communication bus and / or a communication interface. The processor 704, the communication interface, the first memory 702, and the second memory 703 complete mutual communication through the communication bus.

[0226] The communication bus mentioned in the above identity authentication module may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0227] The communication interface is used for communication between the above identity authentication module and other devices.

[0228] The above processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0229] In an embodiment of the present application, the above image acquisition component is: an infrared image acquisition component.

[0230] In an embodiment of the present application, the above module further includes: an infrared lamp, which is communicatively connected to the image acquisition component and is used to emit infrared light in response to a lighting instruction sent by the image acquisition component.

[0231] In another embodiment provided by the present application, a computer-readable storage medium is further provided. A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the steps of the above identity authentication method are implemented.

[0232] In another embodiment provided by the present application, a computer program product including instructions is further provided. When it runs on a computer, the computer is caused to execute any one of the identity authentication methods in the above embodiments.

[0233] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, a computer, a server, or a data center to another website, a computer, a server, or a data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a solid-state disk (SSD), etc.

[0234] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0235] Each embodiment in this specification is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, module, and storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0236] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are all included in the protection scope of the present application.

Claims

1. An identity authentication method, characterized in that: A processor applied to an identity authentication module, wherein the identity authentication module further comprises: an image acquisition component, a non-volatile first memory and a volatile second memory, wherein the first memory stores a plurality of sets of image processing parameters, each set of image processing parameters corresponding to a type of biometric feature, and the second memory is loaded with a set of image processing parameters from the plurality of sets of image processing parameters, wherein the method comprises: Identifying a first feature area in a first image captured by the image acquisition component; If the first type of the biometric feature to be extracted in the first feature area is inconsistent with the second type corresponding to the image processing parameters loaded in the second memory, and the first type is a registered type, then the image processing parameters corresponding to the first type are loaded from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory, wherein the registered type is: the type of the reference biometric feature that has been entered; Performing image processing on the first feature area based on the image processing parameters loaded in the second memory, and extracting a first biometric feature of the processed first feature area; Identity authentication is performed based on the first biometric characteristic and a reference biometric characteristic of the first type.

2. The method according to claim 1, characterized in that If the image processing parameters corresponding to the first type are successfully loaded from the first memory to the second memory, the method further includes: After completing identity authentication based on the first biometric feature and the reference biometric feature of the first type, image processing parameters corresponding to the registered type with the highest recognition priority are loaded from the first memory to the second memory to replace the image processing parameters corresponding to the first type in the second memory.

3. The method according to claim 1, characterized in that The identifying a first feature area in the first image captured by the image acquisition component includes: Identifying an initial feature area in a first image captured by the image acquisition component; If multiple initial feature areas are identified, based on a selection factor, an initial feature area whose type of biometric feature to be extracted belongs to a registered type is determined from the multiple initial feature areas as the first feature area, wherein the selection factor includes: the recognition priority of the type of biometric feature to be extracted in the initial feature area, and / or the image quality characterization value of the initial feature area.

4. The method according to claim 3, characterized in that If identity authentication based on the first biometric feature and the first type of reference biometric feature fails, the method further includes: Based on the selection factor, an initial feature region whose type of biometric feature to be extracted belongs to a registered type is determined from the initial feature region that has not participated in identity authentication, and is used as a new first feature region, and identity authentication is performed based on the new first feature region.

5. The method according to claim 1, characterized in that The baseline biometrics are entered as follows: If the second type is inconsistent with the third type, loading the image processing parameters corresponding to the third type from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory, wherein the third type is: a registration type selected by a user; Identifying a second characteristic region of the registration type in a second image captured by the image capture component; performing image processing on the second feature area based on the image processing parameters loaded in the second memory; The second biometric feature of the processed second feature area is extracted as a reference biometric feature of the registration type, and the reference biometric feature is stored.

6. The method according to claim 5, characterized in that If the image processing parameters corresponding to the third type are successfully loaded from the first memory to the second memory, the method further includes: After storing the reference biometric feature, image processing parameters corresponding to the registered type with the highest recognition priority are loaded from the first memory to the second memory to replace the image processing parameters corresponding to the third type in the second memory.

7. The method according to claim 5, characterized in that If the image processing parameters corresponding to the third type are successfully loaded from the first memory to the second memory, the method further includes: When the second feature area is not identified and there is a registered type, loading image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory to replace the image processing parameters corresponding to the third type in the second memory; and / or When the second feature area is not identified and there is no registered type, image processing parameters corresponding to the type with the highest priority are loaded from the first memory to the second memory to replace the image processing parameters corresponding to the third type in the second memory.

8. The method according to any one of claims 1 to 7, characterized in that The image acquisition component is: an infrared image acquisition component; and / or The types of the biometric features include at least two of the following types: Palms, face, back of hands, eyes, ears, fingers.

9. An identity authentication device, characterized in that: A processor applied to an identity authentication module, wherein the identity authentication module further comprises: an image acquisition component, a non-volatile first memory and a volatile second memory, wherein the first memory stores a plurality of sets of image processing parameters, each set of image processing parameters corresponding to a type of biometric feature, and the second memory is loaded with a set of image processing parameters from the plurality of sets of image processing parameters, wherein the device comprises: A first recognition module, used to recognize a first feature area in the first image captured by the image acquisition component; A first parameter loading module, configured to load the image processing parameters corresponding to the first type from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory, if the first type of the biometric feature to be extracted in the first feature area is inconsistent with the second type corresponding to the image processing parameters loaded in the second memory, and the first type is a registered type, wherein the registered type is: the type of the reference biometric feature that has been entered; A first feature extraction module, configured to perform image processing on the first feature area based on the image processing parameters loaded in the second memory, and extract a first biometric feature of the processed first feature area; The first identity authentication module is used to perform identity authentication based on the first biometric feature and the first type of reference biometric feature.

10. The device according to claim 9, characterized in that If the image processing parameters corresponding to the first type are successfully loaded from the first memory to the second memory, the apparatus further comprises: a second parameter loading module, configured to load the image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory after completing identity authentication based on the first biometric feature and the reference biometric feature of the first type, so as to replace the image processing parameters corresponding to the first type in the second memory; and / or The first recognition module is specifically used to recognize an initial feature region in the first image captured by the image acquisition component; if multiple initial feature regions are recognized, an initial feature region of a registered type of biometric feature to be extracted is determined from the multiple initial feature regions based on a selection factor as the first feature region, wherein the selection factor includes: a recognition priority of the type of biometric feature to be extracted in the initial feature region, and / or an image quality characterization value of the initial feature region; and / or If the identity authentication based on the first biometric feature and the first type of reference biometric feature fails, the device further includes: a second identity authentication module, configured to determine, based on the selection factor, from the initial feature region that has not participated in the identity authentication, an initial feature region of a type of biometric feature to be extracted that belongs to a registered type, as a new first feature region, and perform identity authentication based on the new first feature region; and / or The reference biometric feature is entered in the following manner: if the second type is inconsistent with the third type, the image processing parameters corresponding to the third type are loaded from the first memory to the second memory to replace the image processing parameters corresponding to the second type in the second memory, wherein the third type is: a registration type selected by a user; identifying a second feature area of ​​the registration type in the second image captured by the image acquisition component; performing image processing on the second feature area based on the image processing parameters loaded in the second memory; extracting the second biometric feature of the processed second feature area as the reference biometric feature of the registration type, and storing the reference biometric feature; and / or If the image processing parameters corresponding to the third type are successfully loaded from the first memory to the second memory, the apparatus further comprises: a third parameter loading module, configured to load the image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory after storing the reference biometric feature, so as to replace the image processing parameters corresponding to the third type in the second memory; and / or If the image processing parameters corresponding to the third type are successfully loaded from the first memory to the second memory, the device further includes: a fourth parameter loading module, which is used to load the image processing parameters corresponding to the registered type with the highest recognition priority from the first memory to the second memory when the second feature area is not recognized and there is a registered type, so as to replace the image processing parameters corresponding to the third type in the second memory; and / or a fifth parameter loading module, which is used to load the image processing parameters corresponding to the type with the highest priority from the first memory to the second memory when the second feature area is not recognized and there is no registered type, so as to replace the image processing parameters corresponding to the third type in the second memory; and / or The image acquisition component is: an infrared image acquisition component; and / or the type of the biological feature includes at least two of the following types: palm, face, back of hand, eye, auricle, finger.

11. An identity authentication module, characterized in that: include: An image acquisition component, used for acquiring images and sending the acquired images to a processor; A non-volatile first memory for storing a plurality of sets of image processing parameters, each set of image processing parameters corresponding to a type of biometric feature; a volatile second memory, used for loading a set of image processing parameters from among the plurality of sets of image processing parameters; The processor is used to execute the method according to any one of claims 1 to 8.

12. The module according to claim 11, characterized in that: The image acquisition component is: an infrared image acquisition component.

13. The module according to claim 11, characterized in that: The module also includes: An infrared lamp is communicatively connected to the image acquisition component and is used to emit infrared light in response to a light-on instruction sent by the image acquisition component.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images