Palmprint recognition method and apparatus, storage medium, and electronic device

Abstract

The present invention pertains to the technical field of artificial intelligence. Disclosed are a palmprint recognition method and apparatus, a storage medium, and an electronic device. The method comprises: acquiring at least one palm image sample for each of a plurality of known users; on the basis of each palm image sample, determining a palmprint region image and a first palmprint curve image of a corresponding palmprint; on the basis of the palmprint region image and the first palmprint curve image, training a feature extraction model, and obtaining a palmprint recognition model, the feature extraction model comprising a first feature extraction module and a second feature extraction module having the same network structure and shared parameters, the first feature extraction module being used to extract features of the palmprint region image, and the second feature extraction module being used to extract features of the first palmprint curve image; and performing palmprint recognition on the basis of the palmprint recognition model, thereby enabling data augmentation training of the palmprint recognition model and improving the palmprint recognition accuracy of the model.

Description

Palmprint recognition methods, devices, storage media and electronic devices Technical Field

[0001] This application belongs to the field of artificial intelligence technology, and in particular relates to a palmprint recognition method, device, storage medium and electronic device. Background Technology

[0002] With the widespread use of smart devices, people have increasingly higher requirements for the reliability, security, accuracy, and convenience of biometric technologies used for identity verification. Compared with commonly used biometric features such as voice, face, iris, fingerprint, and gait, palm prints have strong self-stability and individual variability, providing important evidence for identity verification and thus attracting widespread attention from many researchers.

[0003] Currently, deep learning-based palmprint recognition methods use learning models to extract features from palmprint images. However, due to the relatively complex acquisition and annotation of palmprint data, it is difficult to collect large-scale palmprint data samples for model training. This results in the model being unable to learn and generalize well, which in turn makes it difficult for the trained model to support large-scale palmprint recognition tasks. The accuracy of palmprint feature extraction is low, and the recognition effect is poor. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a palmprint recognition method, apparatus, storage medium, and electronic device, which can accurately extract palmprint features and improve the palmprint recognition effect.

[0005] Firstly, this application provides a palmprint recognition method, including:

[0006] Obtain at least one palm image sample for each of the multiple known users;

[0007] The palmprint region image and the first palmprint curve image are determined based on each palm image sample.

[0008] Based on the palmprint region image and the first palmprint curve image, a feature extraction model is trained to obtain a palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image.

[0009] Palmprint recognition is performed based on the palmprint recognition model.

[0010] In some embodiments, determining the palmprint region image and the first palmprint curve image based on each palm image sample includes:

[0011] Extract the image of the corresponding palm print region from each palm image sample to obtain the palm print region image;

[0012] The palmprint region image is input into a trained geometric curve generation model to generate a binarized geometric curve image, thus obtaining the first palmprint curve image corresponding to the palmprint.

[0013] In some embodiments, the training process of the geometric curve generation model includes:

[0014] The constructed geometric curve generation model is used to generate a binarized geometric curve image corresponding to each palmprint region image, thus obtaining a second palmprint curve image;

[0015] Generative adversarial training is performed on the geometric curve generation model based on the palmprint region image and the second palmprint curve image.

[0016] In some embodiments, extracting the image of the corresponding palm print region from each of the palm image samples includes:

[0017] Keypoint detection is performed on each of the palm image samples to obtain multiple keypoints;

[0018] Based on the image coordinates of the key points, the image of the corresponding palm print area is extracted from the palm image sample.

[0019] In some embodiments, training the feature extraction model based on the palmprint region image and the first palmprint curve image includes:

[0020] The first feature extraction module is used to extract features from the palmprint region image to obtain the first extracted features, and the second feature extraction module is used to extract features from the first palmprint curve image to obtain the second extracted features.

[0021] The feature extraction model is trained based on the target loss function, the first extracted feature, and the second extracted feature. The target loss function includes a weighted first loss function and a second loss function. The first loss function is used to determine the loss value based on the features in the palm print region image, and the second loss function is used to determine the loss value based on the features in the palm print region image and the features in the first palm print curve image.

[0022] In some embodiments, training the feature extraction model based on the target loss function, the first extracted feature, and the second extracted feature includes:

[0023] A first loss value is determined based on the first extracted feature and the first loss function, and a second loss value is determined based on the first extracted feature, the second extracted feature, and the second loss function.

[0024] The comprehensive loss value is determined by weighting the first loss value and the second loss value.

[0025] The parameters of the feature extraction model are adjusted based on the comprehensive loss value to train the feature extraction model.

[0026] In some embodiments, the palmprint recognition based on the palmprint recognition model includes:

[0027] Acquire the target hand image of the user to be identified;

[0028] Based on the target palm image, determine the target palm print region image and the target palm print curve image of the corresponding palm print;

[0029] The target palmprint curve image and the target palmprint region image are input into the palmprint recognition model to obtain the palmprint feature data of the user to be identified.

[0030] Secondly, this application provides a palmprint recognition device, comprising:

[0031] The acquisition unit is used to acquire at least one palm image sample for each of the multiple known users;

[0032] The determining unit is used to determine the palmprint region image and the first palmprint curve image of the corresponding palmprint based on each palmprint image sample;

[0033] The training unit is used to train the feature extraction model based on the palmprint region image and the first palmprint curve image to obtain a palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image.

[0034] The recognition unit is used to perform palmprint recognition based on the palmprint recognition model.

[0035] In some embodiments, the determining unit is specifically used for:

[0036] Extract the image of the corresponding palm print region from each palm image sample to obtain the palm print region image;

[0037] The palmprint region image is input into a trained geometric curve generation model to generate a binarized geometric curve image, thus obtaining the first palmprint curve image corresponding to the palmprint.

[0038] In some embodiments, the determining unit is specifically used for:

[0039] Keypoint detection is performed on each of the palm image samples to obtain multiple keypoints;

[0040] Based on the image coordinates of the key points, the image of the corresponding palm print area is extracted from the palm image sample.

[0041] In some embodiments, the training unit is further configured to:

[0042] The constructed geometric curve generation model is used to generate a binarized geometric curve image corresponding to each palmprint region image, thus obtaining a second palmprint curve image;

[0043] Generative adversarial training is performed on the geometric curve generation model based on the palmprint region image and the second palmprint curve image.

[0044] In some embodiments, the training unit is specifically used for:

[0045] The first feature extraction module is used to extract features from the palmprint region image to obtain the first extracted features, and the second feature extraction module is used to extract features from the first palmprint curve image to obtain the second extracted features.

[0046] The feature extraction model is trained based on the target loss function, the first extracted feature, and the second extracted feature. The target loss function includes a weighted first loss function and a second loss function. The first loss function is used to determine the loss value based on the features in the palm print region image, and the second loss function is used to determine the loss value based on the features in the palm print region image and the features in the first palm print curve image.

[0047] In some embodiments, the training unit is specifically used for:

[0048] A first loss value is determined based on the first extracted feature and the first loss function, and a second loss value is determined based on the first extracted feature, the second extracted feature, and the second loss function.

[0049] The comprehensive loss value is determined by weighting the first loss value and the second loss value.

[0050] The parameters of the feature extraction model are adjusted based on the comprehensive loss value to train the feature extraction model.

[0051] In some embodiments, the identification unit is specifically used for:

[0052] Acquire the target hand image of the user to be identified;

[0053] Based on the target palm image, determine the target palm print region image and the target palm print curve image of the corresponding palm print;

[0054] The target palmprint curve image and the target palmprint region image are input into the palmprint recognition model to obtain the palmprint feature data of the user to be identified.

[0055] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the palmprint recognition method described in any of the above claims.

[0056] Fourthly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the palmprint recognition method described in any of the above claims.

[0057] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the palmprint recognition method described in any of the preceding claims.

[0058] The palmprint recognition method, apparatus, storage medium, electronic device, and computer program product provided in this application acquire at least one palm image sample from each of multiple known users; determine the palmprint region image and the first palmprint curve image based on each palm image sample; train a feature extraction model based on the palmprint region image and the first palmprint curve image to obtain a palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image. Palmprint recognition is performed based on the palmprint recognition model, that is, the model is trained using the image of the palmprint region and the curve image corresponding to the palmprint texture. This enables data augmentation training of the palmprint recognition model, ensuring that the model can learn the features of the main lines and fine lines of the palmprint well, so that the model can learn and generalize well, thereby improving the recognition accuracy of the model for large-scale palmprint recognition tasks and achieving good palmprint recognition results. Attached Figure Description

[0059] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 is a schematic flowchart of the palmprint recognition method provided in an embodiment of this application;

[0061] Figure 2 is another schematic flowchart of the palmprint recognition method provided in the embodiment of this application;

[0062] Figure 3 is a schematic diagram illustrating the first palmprint curve image provided in an embodiment of this application;

[0063] Figure 4 is a schematic diagram of the data augmentation training process of the feature extraction model provided in the embodiments of this application;

[0064] Figure 5 is a schematic diagram of the palmprint recognition device provided in the embodiment of this application;

[0065] Figure 6 is a schematic diagram of the structure of the electronic device provided in an embodiment of this application;

[0066] Figure 7 is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. Detailed Implementation

[0067] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0068] This application provides a palmprint recognition method, device, storage medium, electronic device, and computer program product.

[0069] Please refer to Figure 1, which is a flowchart illustrating the palmprint recognition method provided in this embodiment. This palmprint recognition method is applied in an electronic device and can be executed by the electronic device or a functional module or entity within the electronic device. The palmprint recognition method includes the following steps 101-104, wherein:

[0070] 101. Obtain at least one palm image sample for each of the multiple known users;

[0071] 102. Determine the palmprint region image and the first palmprint curve image for each palmprint image sample;

[0072] 103. Based on the palmprint region image and the first palmprint curve image, the feature extraction model is trained to obtain a palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image.

[0073] 104. Palmprint recognition is performed based on this palmprint recognition model.

[0074] The palmprint recognition method provided in this application determines the palmprint region image and the first palmprint curve image by acquiring palm image samples of known users, and uses the palmprint region image and the first palmprint curve image for model training. That is, the model is trained using the image of the palmprint region and the curve image corresponding to the palmprint texture, thereby realizing data augmentation training of the palmprint recognition model, ensuring that the model learns the features of the main lines and fine lines of the palmprint well, enabling the model to learn and generalize well, thereby improving the recognition accuracy of the model for large-scale palmprint recognition tasks and achieving good palmprint recognition results.

[0075] The following will provide a detailed explanation of steps 101-104 above.

[0076] 101. Obtain at least one palm image sample for each of the multiple known users.

[0077] In this process, images of each known user's palm can be captured using image acquisition devices such as cameras. If the captured image is determined to be a palm image and passes the palm quality detection algorithm threshold, it is used as a palm image sample, for example, denoted as G. These images retain the original features of the palm print.

[0078] In some embodiments, since various noises and deformations may be introduced during image acquisition, such as environmental noise, equipment noise, geometric deformation, nonlinear deformation, etc., in order to avoid the effective features in the image being masked by noise or deformation and affecting the image sample quality, preprocessing can be performed before the image sample is processed. Preprocessing includes, but is not limited to, denoising processing and correction processing.

[0079] For example, denoising the original hand image sample G can effectively remove noise from the image, resulting in a clearer image, denoted as G1. Taking Gaussian filtering for denoising as an example, the formula is: Where x and y are the coordinate components of pixels in the image, and σ is the standard deviation of the Gaussian function. σ determines the width of the Gaussian function, thus affecting the smoothness of the filter. The larger the value of σ, the flatter the Gaussian curve, and the smoother the filtering effect; the smaller the value of σ, the steeper the Gaussian curve, and the more image details can be preserved.

[0080] Next, the denoised image G1 is subjected to image correction to correct the distortion in the image, and the resulting image is denoted as G2. Image correction can include geometric correction and grayscale correction. Taking the perspective transformation method in geometric correction as an example, it projects the image onto a new plane, which is mainly a mapping from the original two-dimensional plane (x,y) to the new two-dimensional plane (x',y').

[0081] 102. Determine the palmprint region image and the first palmprint curve image for each palmprint image sample.

[0082] Among them, the palmprint region image is the image of the area where the palmprint is located. The first palmprint curve image is the geometric curve image corresponding to the palmprint texture, and it is a binarized image.

[0083] In some embodiments, please refer to Figure 2, which is another schematic flowchart of the palmprint recognition method provided in this application embodiment. The above step 102 specifically includes the following steps 1021 and 1022, wherein:

[0084] 1021. Extract the image of the corresponding palm print area from each palm image sample to obtain the palm print area image.

[0085] Specifically, step 1021 above may include:

[0086] Keypoint detection is performed on each palm image sample to obtain multiple keypoints;

[0087] Based on the image coordinates of this key point, the image of the corresponding palm print area is extracted from the palm image sample.

[0088] Since the original palm image samples may contain regions unrelated to palm prints, which can significantly affect palm print feature extraction and recognition, keypoint detection can be performed on the preprocessed palm image samples G2 to refine subsequent palm feature localization. These keypoints help define the geometric structure and features of the palm print, eliminate non-palm print regions, and thus improve the accuracy of subsequent palm print recognition. Keypoint detection standardizes and aligns the palm image samples, reducing recognition errors caused by changes in palm position and angle. n palm feature points at the troughs between the fingers can be selected as keypoints. Deep learning techniques are used to detect and determine the coordinates of the palm feature points in each image sample G2, denoted by a set β, where β = {(a,b),...,(a...b)}. n ,b n)}, where a and b are the coordinate components of the palm feature points. Then, based on the coordinates β of the detected palm feature points, the location of the palm print area can be determined, that is, the location of the region of interest (ROI) of the palm. The image of this region is extracted from the palm image sample as the palm print region image, denoted as G'. Typically, this region contains information such as the main lines of the palm print, wrinkles, fine textures, ridge ends, and bifurcation points.

[0089] 1022. Input the palmprint region image into the trained geometric curve generation model to generate a binarized geometric curve image, thus obtaining the first palmprint curve image corresponding to the palmprint.

[0090] Since the main lines and fine lines of the palm print play a crucial role in palm print recognition, while muscle color and distribution have almost no impact, to enhance the effective feature information such as the main lines, wrinkles, and bifurcation points of the palm print, a corresponding geometric curve image (i.e., the first palm print curve image S, see Figure 3) can be drawn based on the palm print features in the palm print region image G' to simulate the palm print texture, thereby improving the utilization rate of key feature information in the palm print region image. The drawing of the geometric curve image can be achieved by pre-training a geometric curve generation model, or by other methods, which are not limited here. When drawing the geometric curve image by pre-training a geometric curve generation model, the geometric curve generation model can be a model capable of converting between different types of images (this scheme mainly realizes the conversion from real images captured by the camera to drawn geometric curve images), such as BicycleGAN, CycleGAN, etc., but is not limited to these models.

[0091] In some embodiments, the geometric curve generation model can be trained using a generative adversarial approach, with training data including real images and drawn geometric curve images. The real images can be palmprint region images of the known users mentioned above, or palmprint region images of other known users; there is no limitation here. For example, when the real images can be palmprint region images of the known users mentioned above, the training process of the geometric curve model may include:

[0092] The constructed geometric curve generation model is used to generate a binarized geometric curve image corresponding to each palmprint region image, thus obtaining the second palmprint curve image;

[0093] Based on the palmprint region image and the second palmprint curve image, the geometric curve generation model is subjected to generative adversarial training.

[0094] In the model training phase, the real palmprint region image G' is first input into the geometric curve generation model to randomly generate a binarized geometric curve image (i.e., the second palmprint curve image). Then, the real palmprint region image G' and the second palmprint curve image are simultaneously input into the geometric curve generation model as a pair of samples to perform generative adversarial training. Once the geometric curve generation model is trained, in the subsequent training of the feature extraction model, only the real palmprint region image G' needs to be input into the trained geometric curve generation model again to obtain a first palmprint curve image S with a high degree of matching.

[0095] 103. Based on the palmprint region image and the first palmprint curve image, the feature extraction model is trained to obtain the palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image.

[0096] The first feature extraction module is mainly used to extract the overall features of the palm print, while the second feature extraction module is mainly used to extract the key features of the main lines and fine lines of the palm print. The two feature extraction modules share parameters during training. Parameter sharing means that different parts or all of the two networks share the same weights and bias parameters, rather than learning parameters independently. This can significantly reduce the number of parameters in the entire system and improve computational efficiency. Through parameter sharing, the two networks can jointly learn a set of parameters that perform better on a wider range of data, thereby improving the model's generalization ability.

[0097] In some embodiments, please continue to refer to Figure 2, step 103 above specifically includes:

[0098] 1031. Use the first feature extraction module to extract features from the palmprint region image to obtain the first extracted features, and use the second feature extraction module to extract features from the first palmprint curve image to obtain the second extracted features;

[0099] 1032. The feature extraction model is trained according to the target loss function, the first extracted feature and the second extracted feature. The target loss function includes a weighted first loss function and a second loss function. The first loss function is used to determine the loss value based on the features in the palm print region image, and the second loss function is used to determine the loss value based on the features in the palm print region image and the features in the first palm print curve image.

[0100] Furthermore, step 1032 specifically includes:

[0101] A first loss value is determined based on the first extracted feature and the first loss function, and a second loss value is determined based on the first extracted feature, the second extracted feature, and the second loss function;

[0102] The comprehensive loss value is determined by weighting the first loss value and the second loss value.

[0103] The parameters of the feature extraction model are adjusted based on the overall loss value to train the feature extraction model.

[0104] The first loss function primarily helps the model focus on the overall features of the palm print, while the second loss function primarily helps the model focus on the features of the main lines and fine lines of the palm print. The weights of the first and second loss functions can be adjusted as needed, allowing the model to pay more attention to samples that contribute to improved model performance during training. This helps the model learn more generalized features, thereby improving its performance on unseen data and increasing the accuracy of palm print recognition.

[0105] Please refer to Figure 4, which is a schematic diagram of the data augmentation training process of the feature extraction model provided in this embodiment. Since the features of the palmprint region image G' and the first palmprint curve image S have similar statistical characteristics, by sharing the parameters of the first feature extraction module and the second feature extraction module, the complexity of the model can be effectively reduced, and the training speed and generalization ability of the model can be improved. In addition to the first feature extraction module and the second feature extraction module, the feature extraction model also includes other network layers, such as an output layer for fusing the features (i.e., the feature matrix) extracted by the first feature extraction module and the features (i.e., the feature matrix) extracted by the second feature extraction module. This is not limited here.

[0106] During the training of the feature extraction model, both G' and S losses should be considered. The target loss function is designed as follows: Loss Total = Loss1 + μ·Loss2, where u is the weighting coefficient. Loss1 is the first loss function, and Loss2 is the second loss function. Loss1 and Loss2 are calculated for the palmprint region image G', and Loss2 is calculated for the palmprint curve image. Loss1 is the main loss function, and Loss2 helps the model pay more attention to the main lines and fine lines of the palmprint. Finally, the comprehensive loss Loss is calculated through a weighted method. Total The model parameters are iteratively updated based on the loss value. This is combined with the comprehensive loss... TotalThis method extracts key feature information such as the main lines and fine lines of palm prints, enhances the feature information of the main lines and fine lines of palm prints, greatly improves the utilization rate of palm print information, and enables palm print data enhancement training of the model. This helps to improve the palm print recognition accuracy of the model and solves the technical problem that the small size of the palm print dataset makes it difficult to support large-scale palm print recognition tasks. This method has made a contribution to large-scale palm print recognition tasks.

[0107] 104. Palmprint recognition is performed based on this palmprint recognition model.

[0108] Once the palmprint recognition model is trained based on known user palm image samples, it can be used to perform large-scale palmprint recognition tasks with high recognition accuracy.

[0109] In some embodiments, please continue to refer to Figure 2, step 104 above specifically includes:

[0110] 1041. Obtain the target hand image of the user to be identified;

[0111] 1042. Based on the target palm image, determine the target palm print region image and the target palm print curve image;

[0112] 1043. Input the target palmprint curve image and the target palmprint region image into the palmprint recognition model to obtain the palmprint feature data of the user to be identified.

[0113] In the inference stage of the palmprint recognition model, the target palm image of the user to be identified can be acquired and preprocessed. Key point detection is performed on the preprocessed image, and the target palmprint region image is extracted based on the detected key points. Then, the target palmprint region image is input into the geometric curve generation model to obtain the target palmprint curve image. Then, the target palmprint curve image and the target palmprint region image are simultaneously input into the palmprint recognition model to obtain palmprint feature data. After that, the palmprint feature data can be matched with the data in the palmprint feature library to determine the identity of the user to be identified. The palmprint feature library stores the palmprint feature data of known users.

[0114] As described above, the palmprint recognition method provided in this application involves acquiring at least one palm image sample from each of multiple known users; determining the palmprint region image and the first palmprint curve image based on each palm image sample; training a feature extraction model based on the palmprint region image and the first palmprint curve image to obtain a palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image. Palmprint recognition is performed based on the palmprint recognition model, that is, the model is trained using the image of the palmprint region and the curve image corresponding to the palmprint texture. This enables data augmentation training of the palmprint recognition model, ensuring that the model can learn the features of the main lines and fine lines of the palmprint well, allowing the model to learn and generalize well, thereby improving the recognition accuracy of the model for large-scale palmprint recognition tasks and achieving good palmprint recognition results.

[0115] According to the method described in the above embodiments, this application also provides a palmprint recognition device for performing the steps in the above palmprint recognition method. Please refer to Figure 5, which is a schematic diagram of the structure of the palmprint recognition device 200 provided in this application embodiment. This palmprint recognition device 200 is applied in an electronic device and can be executed by the electronic device or a functional module or functional entity within the electronic device. Specifically, the palmprint recognition device 200 includes an acquisition unit 201, a determination unit 202, a training unit 203, and a recognition unit 204, wherein:

[0116] Acquisition unit 201 is used to acquire at least one palm image sample of each of the multiple known users;

[0117] The determining unit 202 is used to determine the palmprint region image and the first palmprint curve image of the corresponding palmprint based on each palm image sample;

[0118] Training unit 203 is used to train the feature extraction model based on the palmprint region image and the first palmprint curve image to obtain a palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image.

[0119] The recognition unit 204 is used to perform palmprint recognition based on the palmprint recognition model.

[0120] In some embodiments, the determining unit 202 is specifically used for:

[0121] Extract the image of the corresponding palm print region from each palm image sample to obtain the palm print region image;

[0122] The palmprint region image is input into a trained geometric curve generation model to generate a binarized geometric curve image, thus obtaining the first palmprint curve image corresponding to the palmprint.

[0123] In some embodiments, the determining unit 202 is specifically used for:

[0124] Keypoint detection is performed on each palm image sample to obtain multiple keypoints;

[0125] Based on the image coordinates of the key point, the image of the corresponding palm print area is extracted from the palm image sample.

[0126] In some embodiments, the training unit 203 is further configured to:

[0127] The constructed geometric curve generation model is used to generate a binarized geometric curve image corresponding to each palmprint region image, thus obtaining the second palmprint curve image;

[0128] Based on the palmprint region image and the second palmprint curve image, the geometric curve generation model is subjected to generative adversarial training.

[0129] In some embodiments, the training unit 203 is specifically used for:

[0130] The first feature extraction module is used to extract features from the palm print region image to obtain the first extracted features, and the second feature extraction module is used to extract features from the first palm print curve image to obtain the second extracted features.

[0131] The feature extraction model is trained based on the target loss function, the first extracted feature, and the second extracted feature. The target loss function includes a weighted first loss function and a second loss function. The first loss function is used to determine the loss value based on the features in the palm print region image, and the second loss function is used to determine the loss value based on the features in the palm print region image and the features in the first palm print curve image.

[0132] In some embodiments, the training unit 203 is specifically used for:

[0133] A first loss value is determined based on the first extracted feature and the first loss function, and a second loss value is determined based on the first extracted feature, the second extracted feature, and the second loss function;

[0134] The comprehensive loss value is determined by weighting the first loss value and the second loss value.

[0135] The parameters of the feature extraction model are adjusted based on the overall loss value to train the feature extraction model.

[0136] In some embodiments, the identification unit 204 is specifically used for:

[0137] Acquire the target hand image of the user to be identified;

[0138] Based on the target palm image, determine the target palm print region image and the target palm print curve image;

[0139] The palmprint curve image and the palmprint region image of the target are input into the palmprint recognition model to obtain the palmprint feature data of the user to be identified.

[0140] It should be noted that the specific details of each module unit in the palmprint recognition device 200 have been described in detail in the embodiments of the palmprint recognition method, and will not be repeated here.

[0141] As described above, the palmprint recognition device 200 provided in this application embodiment acquires at least one palm image sample of each known user among multiple known users through the acquisition unit 201; the determination unit 202 determines the palmprint region image and the first palmprint curve image of the corresponding palmprint based on each palm image sample; the training unit 203 trains the feature extraction model based on the palmprint region image and the first palmprint curve image to obtain a palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image; the recognition unit 204 performs palmprint recognition based on the palmprint recognition model, that is, it uses the image of the palmprint region and the curve image corresponding to the palmprint texture to train the model, thereby realizing data augmentation training of the palmprint recognition model, ensuring that the model can learn and generalize well, and thus improving the recognition accuracy of the model for large-scale palmprint recognition tasks, resulting in good palmprint recognition performance.

[0142] In some embodiments, the palmprint recognition device in this application can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a server, which can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. This application does not impose specific limitations.

[0143] In some embodiments, as shown in FIG6, this application embodiment also provides an electronic device 300, including a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301. When the program is executed by the processor 301, it implements the various processes of the above-described palmprint recognition method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0144] It should be noted that the electronic devices in the embodiments of this application include the aforementioned mobile electronic devices and non-mobile electronic devices.

[0145] Figure 7 is a schematic diagram of the hardware structure of an electronic device that implements an embodiment of this application.

[0146] The electronic device 400 includes, but is not limited to, components such as: radio frequency unit 401, network module 402, audio output unit 403, input unit 404, sensor 405, display unit 406, user input unit 407, interface unit 408, memory 409, and processor 410.

[0147] In some embodiments, when the processor 410 executes the program, it performs the following steps:

[0148] Obtain at least one palm image sample for each of the multiple known users;

[0149] The palmprint region image and the first palmprint curve image are determined based on each palm image sample.

[0150] Based on the palmprint region image and the first palmprint curve image, the feature extraction model is trained to obtain the palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image.

[0151] Palmprint recognition is performed based on this palmprint recognition model.

[0152] In some embodiments, the processor 410 is specifically used for:

[0153] Extract the image of the corresponding palm print region from each palm image sample to obtain the palm print region image;

[0154] The palmprint region image is input into a trained geometric curve generation model to generate a binarized geometric curve image, thus obtaining the first palmprint curve image corresponding to the palmprint.

[0155] In some embodiments, the processor 410 is further configured to:

[0156] The constructed geometric curve generation model is used to generate a binarized geometric curve image corresponding to each palmprint region image, thus obtaining the second palmprint curve image;

[0157] Based on the palmprint region image and the second palmprint curve image, the geometric curve generation model is subjected to generative adversarial training.

[0158] In some embodiments, the processor 410 is specifically used for:

[0159] Keypoint detection is performed on each palm image sample to obtain multiple keypoints;

[0160] Based on the image coordinates of the key point, the image of the corresponding palm print area is extracted from the palm image sample.

[0161] In some embodiments, the processor 410 is specifically used for:

[0162] The first feature extraction module is used to extract features from the palm print region image to obtain the first extracted features, and the second feature extraction module is used to extract features from the first palm print curve image to obtain the second extracted features.

[0163] The feature extraction model is trained based on the target loss function, the first extracted feature, and the second extracted feature. The target loss function includes a weighted first loss function and a second loss function. The first loss function is used to determine the loss value based on the features in the palm print region image, and the second loss function is used to determine the loss value based on the features in the palm print region image and the features in the first palm print curve image.

[0164] In some embodiments, the processor 410 is specifically used for:

[0165] A first loss value is determined based on the first extracted feature and the first loss function, and a second loss value is determined based on the first extracted feature, the second extracted feature, and the second loss function;

[0166] The comprehensive loss value is determined by weighting the first loss value and the second loss value.

[0167] The parameters of the feature extraction model are adjusted based on the overall loss value to train the feature extraction model.

[0168] In some embodiments, the processor 410 is specifically used for:

[0169] Acquire the target hand image of the user to be identified;

[0170] Based on the target palm image, determine the target palm print region image and the target palm print curve image;

[0171] The palmprint curve image and the palmprint region image of the target are input into the palmprint recognition model to obtain the palmprint feature data of the user to be identified.

[0172] Those skilled in the art will understand that the electronic device 400 may also include a power supply (such as a battery) for powering various components. The power supply can be logically connected to the processor 410 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The electronic device structure shown in Figure 6 does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0173] It should be understood that, in this embodiment, the input unit 404 may include a graphics processing unit (GPU) 4041 and a microphone 4042. The GPU 4041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 406 may include a display panel 4061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 407 includes at least one of a touch panel 4071 and other input devices 4072. The touch panel 4071 is also called a touch screen. The touch panel 4071 may include a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0174] The memory 409 can be used to store software programs and various data. The memory 409 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 409 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 409 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0175] Processor 410 may include one or more processing units; processor 410 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 410.

[0176] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described palmprint recognition method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0177] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0178] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described palmprint recognition method.

[0179] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0180] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0181] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0182] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

[0183] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0184] In the description of this application, "multiple" means two or more.

[0185] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0186] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

Claims

1. A palmprint recognition method, characterized in that, include: Obtain at least one palm image sample for each of the multiple known users; The palmprint region image and the first palmprint curve image are determined based on each palm image sample. Based on the palmprint region image and the first palmprint curve image, a feature extraction model is trained to obtain a palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image. Palmprint recognition is performed based on the palmprint recognition model.

2. The palmprint recognition method according to claim 1, characterized in that, The step of determining the palmprint region image and the first palmprint curve image based on each palm image sample includes: Extract the image of the corresponding palm print region from each palm image sample to obtain the palm print region image; The palmprint region image is input into a trained geometric curve generation model to generate a binarized geometric curve image, thus obtaining the first palmprint curve image corresponding to the palmprint.

3. The palmprint recognition method according to claim 2, characterized in that, The training process of the geometric curve generation model includes: The constructed geometric curve generation model is used to generate a binarized geometric curve image corresponding to each palmprint region image, thus obtaining a second palmprint curve image; Generative adversarial training is performed on the geometric curve generation model based on the palmprint region image and the second palmprint curve image.

4. The palmprint recognition method according to claim 2, characterized in that, The step of extracting the image of the corresponding palm print region from each of the palm image samples includes: Keypoint detection is performed on each of the palm image samples to obtain multiple keypoints; Based on the image coordinates of the key points, the image of the corresponding palm print area is extracted from the palm image sample.

5. The palmprint recognition method according to claim 1, characterized in that, The step of training the feature extraction model based on the palmprint region image and the first palmprint curve image includes: The first feature extraction module is used to extract features from the palmprint region image to obtain the first extracted features, and the second feature extraction module is used to extract features from the first palmprint curve image to obtain the second extracted features. The feature extraction model is trained based on the target loss function, the first extracted feature, and the second extracted feature. The target loss function includes a weighted first loss function and a second loss function. The first loss function is used to determine the loss value based on the features in the palm print region image, and the second loss function is used to determine the loss value based on the features in the palm print region image and the features in the first palm print curve image.

6. The palmprint recognition method according to claim 5, characterized in that, The step of training the feature extraction model based on the target loss function, the first extracted feature, and the second extracted feature includes: A first loss value is determined based on the first extracted feature and the first loss function, and a second loss value is determined based on the first extracted feature, the second extracted feature, and the second loss function. The comprehensive loss value is determined by weighting the first loss value and the second loss value. The parameters of the feature extraction model are adjusted based on the comprehensive loss value to train the feature extraction model.

7. The palmprint recognition method according to any one of claims 1-6, characterized in that, The palmprint recognition based on the palmprint recognition model includes: Acquire the target hand image of the user to be identified; Based on the target palm image, determine the target palm print region image and the target palm print curve image of the corresponding palm print; The target palmprint curve image and the target palmprint region image are input into the palmprint recognition model to obtain the palmprint feature data of the user to be identified.

8. A palmprint recognition device, characterized in that, include: The acquisition unit is used to acquire at least one palm image sample for each of the multiple known users; The determining unit is used to determine the palmprint region image and the first palmprint curve image of the corresponding palmprint based on each palmprint image sample; The training unit is used to train the feature extraction model based on the palmprint region image and the first palmprint curve image to obtain a palmprint recognition model. The feature extraction model includes a first feature extraction module and a second feature extraction module with the same network structure and shared parameters. The first feature extraction module is used to extract features from the palmprint region image, and the second feature extraction module is used to extract features from the first palmprint curve image. The recognition unit is used to perform palmprint recognition based on the palmprint recognition model.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the palmprint recognition method as described in any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the palmprint recognition method as described in any one of claims 1-7.

Images