Palm data processing method and apparatus, computer device and storage medium

Abstract

A palm data processing method, executed by a computer device. The method comprises: receiving a user request sent by a user terminal, the user request carrying first palm image data and a user account (202); extracting a first palmprint feature from the first palm image data, and matching the first palmprint feature with at least one unbound palmprint feature stored in a preset storage position, the unbound palmprint feature being registered by means of a palm verification terminal, and being associated with palmprint registration information (204); when a target palmprint feature matching the first palmprint feature is present amongst the at least one unbound palmprint feature, acquiring target palmprint registration information associated with the target palmprint feature (206); on the basis of the target palmprint registration information, generating an authorization confirmation prompt, and feeding back the authorization confirmation prompt to the user terminal (208); and receiving authorization confirmation information fed back by the user terminal, verifying the authorization confirmation information, and when the authorization confirmation information passes the verification, binding the user account and the target palmprint feature (210).

Description

Palm data processing method, device, computer equipment and storage medium

[0001] Related applications

[0002] This application claims priority to Chinese patent application number 2024100066568, filed on January 2, 2024, entitled “Method, device, computer equipment and storage medium for activating palm verification services,” the entire text of which is hereby incorporated by reference. Technical Field

[0003] The present application relates to the field of computer technology, and in particular to a palm data processing method, apparatus, computer equipment, storage medium, and computer program product. Background Art

[0004] With the development of computer technology, palm verification services have emerged. Palm verification services can be applied to a variety of scenarios, such as payment scenarios, work clocking-in scenarios, etc. By activating the palm verification service, you can conveniently use palm verification for identity authentication.

[0005] In the traditional method, the way to activate the palm verification service is that the target user enters the palm print characteristics on the palm verification terminal. The palm print verification terminal displays a graphic code for binding. The target user scans the graphic code by logging into a user terminal with a user account and completes the binding of the user account and palm print characteristics according to the instructions.

[0006] However, the traditional method requires the target user to use the palm verification terminal and the user terminal at the same time to complete the binding of the user account and the palm print feature. The operation is cumbersome and the binding efficiency is low. Summary of the Invention

[0007] The present application provides a palm data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product.

[0008] In a first aspect, the present application provides a palm data processing method, which is executed by a computer device, and the method comprises:

[0009] A palm data processing method, executed by a computer device, comprising:

[0010] receiving a user request sent by a user terminal, wherein the user request carries the first palm image data and a user account;

[0011] extracting a first palmprint feature from the first palm image data;

[0012] matching the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location; the unbound palmprint feature is registered through a palm verification terminal and is associated with palmprint registration information;

[0013] When there is a target palmprint feature matching the first palmprint feature among the at least one unbound palmprint feature, obtaining target palmprint registration information associated with the target palmprint feature;

[0014] generating an authorization confirmation prompt based on the target palmprint registration information, and feeding back the authorization confirmation prompt to the user terminal;

[0015] receiving authorization confirmation information fed back by the user terminal, and verifying the authorization confirmation information; and

[0016] When the authorization confirmation information passes the verification, the user account and the target palmprint feature are bound.

[0017] In a second aspect, the present application further provides a palm data processing device, the device comprising:

[0018] a request receiving module, configured to receive a user request sent by a user terminal, wherein the user request carries the first palm image data and a user account;

[0019] a feature matching module, configured to extract a first palmprint feature from the first palm image data and match the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location; the unbound palmprint feature is registered through a palm verification terminal and is associated with palmprint registration information;

[0020] an information acquisition module, configured to, when a target palmprint feature matching the first palmprint feature exists in the at least one unbound palmprint feature, acquire target palmprint registration information associated with the target palmprint feature;

[0021] a confirmation prompt generating module, configured to generate an authorization confirmation prompt based on the target palmprint registration information, and feed back the authorization confirmation prompt to the user terminal; and

[0022] The binding module is used to receive the authorization confirmation information fed back by the user terminal, verify the authorization confirmation information, and bind the user account and the target palmprint feature when the authorization confirmation information passes the verification.

[0023] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the palm data processing method described above when executing the computer program.

[0024] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the palm data processing method described above when executed by a processor.

[0025] In a fifth aspect, the present application further provides a computer program product, which includes a computer program that implements the above-mentioned palm data processing method when executed by a processor.

[0026] The details of one or more embodiments of the present application are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the present application will become apparent from the description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the disclosed drawings without any creative work.

[0028] FIG1 is a diagram illustrating an application environment of a palm data processing method according to an embodiment;

[0029] FIG2 is a schematic flow chart of a palm data processing method according to an embodiment;

[0030] FIG3 is a schematic diagram showing a palm authentication service activation portal in one embodiment;

[0031] FIG4 is a schematic diagram of a collection interface of a user terminal in one embodiment;

[0032] FIG5 is a schematic diagram showing an authorization confirmation prompt in one embodiment;

[0033] FIG6 is a schematic diagram showing a palmprint authorization verification prompt in one embodiment;

[0034] FIG7 is a schematic diagram showing a password verification prompt in one embodiment;

[0035] FIG8 is a schematic diagram showing a successful binding prompt in one embodiment;

[0036] FIG9 is a schematic diagram of a palm authentication terminal according to an embodiment;

[0037] FIG10 is a flow chart of a palm data processing method according to another embodiment;

[0038] FIG11 is a schematic flow chart of a palm data processing method according to another embodiment;

[0039] FIG12 is a flow chart of a palm data processing method according to yet another embodiment;

[0040] FIG13 is a schematic diagram of interface changes of a user terminal in one embodiment;

[0041] FIG14 is a block diagram of a palm data processing device according to an embodiment;

[0042] FIG15 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0044] The palm data processing method provided in the embodiments of the present application can be applied in the application environment shown in Figure 1 . In this embodiment, a user terminal 102 communicates with a server 104 via a network, and a palm verification terminal 106 communicates with the server 104. A data storage system can store data that the server 104 needs to process. The data storage system can be integrated with the server 104, or it can be located in the cloud or on another server. The server 104 receives a user request uploaded by the user terminal 102, where the user request carries first palm image data and a user account. The server 104 extracts a first palm print feature from the first palm image data, matches the first palm print feature with at least one unbound palm print feature stored in a preset storage location, and registers the unbound palm print feature through the palm verification terminal 106 and is associated with palm print registration information. When a target palm print feature that matches the first palm print feature is present in the at least one unbound palm print feature, the server 104 obtains target palm print registration information associated with the target palm print feature, generates an authorization confirmation prompt based on the target palm print registration information, and feeds back the authorization confirmation prompt to the user terminal 102. The server 104 receives authorization confirmation information fed back by the user terminal 102, and verifies the authorization confirmation information. When the authorization confirmation information passes the verification, the server 104 binds the user account and the target palm print feature to activate the palm verification service for the user account.

[0045] The user terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, portable wearable devices, and aircraft, among others. IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, among others. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, among others. The server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers. The palm verification terminal 106 may be, but is not limited to, a device with an image data acquisition function, such as a camera, camcorder, scanner, or lidar image acquisition device, or various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices integrated with an image acquisition device, among others. IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, among others. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, among others. The embodiments of the present invention may be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, assisted driving, and the like.

[0046] In one embodiment, as shown in FIG2 , a palm data processing method is provided. The method can be executed by a terminal or a server alone, or by a terminal and a server in collaboration. In the embodiment of the present application, the method is described using the server as an example, and includes the following steps:

[0047] Step 202: Receive a user request sent by a user terminal, where the user request carries the first palm image data and the user account.

[0048] The term "user terminal" refers to the terminal used by the target user, who is the user requesting the palm verification service. The target user can be determined based on the specific application scenario. For example, in a payment scenario, the target user could be the purchaser. Another example is a user who clocks in for work. A palm verification service refers to a service that requires palm verification for identity verification. Specifically, it can refer to a service that utilizes palm print features obtained through palm print recognition for identity verification. For example, a palm verification service could be a palm verification payment service. Another example is a palm verification clock-in service.

[0049] Among them, the first palm image data refers to the image data containing the palm image collected and uploaded by the user terminal, and the palm image is the effect formed by the palm of the target user using the user terminal. The palm refers to the organ with weight-bearing or grasping function at the end of the limbs of a living being (especially a natural person), which can include the palm and the sole of the foot. The palm refers to the limb part including the palm and five fingers (thumb, index finger, middle finger, ring finger and little finger). The user account refers to the account used by the target user using the user terminal when logging into the target platform on the user terminal. The target platform refers to the platform that provides palm verification services. For example, the target platform can specifically be an instant messaging application. For another example, the target platform can be an organizational communication application, such as an enterprise communication application.

[0050] Specifically, when a target user using a user terminal wishes to activate the palm authentication service, the user terminal uploads a user request to the server. The server then receives the user request, which includes the first palm image data and the user account. In a specific application, when the user terminal is used to log in to the user account of the target platform, the target user uses the user terminal to capture the first palm image data and upload the user request to the server.

[0051] In a specific application, as shown in Figure 3, when a user uses a user terminal to log in to a user account on a target platform, if the target user has not yet activated the palm verification service, a palm verification service activation portal will be displayed on the user terminal. The target user can enter the palm verification service activation process through this palm verification service activation portal. After entering the palm verification service activation process, the target user uses the user terminal to capture a palm image stream. Then, using an image optimization algorithm, the user completes palm detection, gesture liveness verification, and image quality detection steps, filters out the first palm image data that meets the quality requirements, and uploads the user's request to the server. The palm image stream can specifically be a palm color image stream.

[0052] Palm detection refers to detecting whether there is a palm in the image stream. If there is a palm, feature points or outlines are displayed at the corresponding position. Gesture liveness detection refers to guiding the target user to perform certain gestures to further verify whether it is a live palm. Gestures can include flapping the palm up and down, swaying left and right, making a scissors hand gesture, etc. In this embodiment, gesture liveness detection can mainly include the following steps:

[0053] First, palm keypoint detection involves detecting palm keypoints, such as fingertips and knuckles, from preprocessed image data. Specifically, palm keypoint detection can be achieved by inputting the preprocessed image data into a pretrained deep learning model for palm keypoint detection. Examples of deep learning models include OpenPose (pose detection model) and PoseNet (pose estimation model).

[0054] Secondly, the posture description is to calculate the description quantity of the palm posture based on the detected key points. The description quantity here can be the distance, angle, etc. between key points. Taking the description quantity as the distance between key points as an example, the calculation formula can be: Among them, p1(x1, y1) and p2(x2, y2) are the coordinates of two key points respectively, and the angle between the key points can be calculated by the cosine function.

[0055] Finally, there is the gesture change judgment, which is to judge whether the gesture has changed by analyzing the palm posture description in the continuous frame image. Specifically, it can be analyzed by motion vector analysis, optical flow method, etc. Taking motion vector analysis as an example, its calculation formula can be: Δd=d(p1 t , p2 t )-d(p1 t-1 , p2 t-1 ), where p1 t , p2 t are the coordinates of the two key points in the t-th frame image, d(p1 t , p2 t ) refers to the distance between key points p1 and p2 in the t-th frame image, p1 t-1 , p2 t-1 are the coordinates of the two key points in the t-1 frame image, d(p1 t-1 , p2 t-1 ) refers to the distance between key points p1 and p2 in the t-1th frame image. As long as the calculated Δd is less than the error threshold, the gesture is considered to have changed.

[0056] In a specific application, when the target user uses the user terminal to capture a palm image stream, the capture interface of the user terminal may be as shown in FIG4 , including a capture prompt (i.e., “Please aim at your palm” in FIG4 ) and a capture progress (the capture progress is 20% in FIG4 , and the capture is completed when the capture progress reaches 100%).

[0057] Step 204: extract a first palmprint feature from the first palm image data; match the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location; the unbound palmprint feature is registered through a palm verification terminal and associated with palmprint registration information.

[0058] Palm prints refer to the individual lines on the palm surface from the fingertips to the wrist, including main lines, wrinkles, veins, ridge endings, and bifurcation points. The shape of palm prints is genetically controlled. Even if the skin peels off for some reason, the new lines retain their original structure. Everyone's palm prints are unique; even twins have similar, but never identical, lines. Therefore, palm prints can be used to determine a person's identity.

[0059] The first palmprint feature refers to a palmprint feature used to characterize the first palm image data. The palmprint feature is used to represent the characteristics of the target user's palm lines. The palmprint feature may include the characteristics of at least one of the lines on the palm, such as the palm and the back of the hand. The palmprint feature may be represented by a vector, a matrix, or other forms. The palmprint feature may include, for example, features in multiple dimensions such as point features, texture features, line features, and geometric features. Point features refer to surface features of the skin on the palm, such as singular points and line shapes formed locally by palm papillary lines. Texture features refer to the characteristics of relatively shallow, fine lines on the palm surface. Line features refer to the characteristics of relatively deep lines on the palm surface. Geometric features may include features such as depth, width, length, and geometric shape.

[0060] The preset storage location can be local to the computer device that executes the above-mentioned palm data processing method, or it can be a storage device accessible to the computer. The computer device can be connected to the storage device via a cable or via the Internet. The preset storage location can also be a physical storage location indicated by a preset storage address. The physical storage location indicated by the preset storage address can change dynamically.

[0061] Unbound palmprint features refer to palmprint features that are not bound to an account on the target platform. Unbound palmprint features are registered through a palm verification terminal and are associated with palmprint registration information. Palmprint registration information refers to information uploaded during palmprint registration and used to identify and distinguish palmprint registrations. For example, palmprint registration information may specifically include the time of palmprint registration. Another example may include the location of palmprint registration. Another example may include palm information, such as whether the palm is left or right.

[0062] Specifically, the server may extract a first palmprint feature from the first palm image data using a feature extraction algorithm or a feature extraction model, and then match the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location using a feature matching algorithm to determine whether a target palmprint feature that matches the first palmprint feature is present in the at least one unbound palmprint feature. The feature extraction model may be pre-trained based on actual application scenarios.

[0063] In specific applications, the feature extraction algorithm can be configured according to the actual application scenario. For example, the feature extraction algorithm can be a filtering algorithm used for feature extraction, such as the Gabor filtering algorithm, the LBP (Local Binary Pattern) filtering algorithm, the HOG (Histogram of Oriented Gradients) filtering algorithm, etc. Taking the Gabor filtering algorithm as an example, its formula is as follows:

[0064] g(x,y;λ,θ,ψ,σ,γ)=exp((-x′ 2 +γ2*y′ 2 ) / (2*σ 2 )))*cos(2π*x′ / λ+ψ);

[0065] Where (x, y) represents the pixel coordinate position in the first palm image data, x′ = x*cos(θ) + y*sin(θ), y′ = -x*sin(θ) + y*cos(θ), λ represents the wavelength of the filter, θ represents the tilt angle of the Gabor kernel function image, ψ represents the phase offset, ranging from -180° to 180° (when ψ = 0, the white bar is the center, and when ψ = 180), σ represents the standard deviation of the Gaussian function, γ represents the spatial aspect ratio (length-to-width ratio), which determines the ellipticity of the Gabor kernel function image. The smaller γ is, the taller the kernel function image will be. σ represents the bandwidth, which is the variance of the Gaussian filter and is usually taken as 2π.

[0066] In specific applications, the feature matching algorithm can be configured according to the actual application scenario. For example, the feature matching algorithm can be a matching algorithm based on feature similarity. The feature similarity can be cosine similarity. For another example, the feature matching algorithm can be a matching algorithm based on feature distance. The feature distance can be Euclidean distance, Hamming distance, etc.

[0067] Step 206: When there is a target palm print feature matching the first palm print feature in at least one unbound palm print feature, target palm print registration information associated with the target palm print feature is obtained.

[0068] The target palmprint registration information refers to information uploaded when registering the target palmprint feature through the palm verification terminal, which is used to identify the target palmprint feature. For example, the target palmprint registration information can specifically include the palmprint registration time and palmprint registration location corresponding to the target palmprint feature.

[0069] Specifically, if at least one unbound palmprint feature contains a target palmprint feature that matches the first palmprint feature, indicating that the target user has previously registered their palmprint features offline through a palm verification terminal and has chosen to authorize and activate the palm verification service later through the user terminal, i.e., to choose to activate the palm verification service later through asynchronous authorization, the server will obtain the target palmprint registration information associated with the target palmprint feature in order to perform authorization based on the target palmprint registration information to activate the palm verification service for the user account. If at least one unbound palmprint feature does not contain a target palmprint feature that matches the first palmprint feature, the server will push a palm verification failure prompt to the user terminal, instructing the user to register their palmprint features again through the palm verification terminal to activate the palm verification service for the user account.

[0070] Step 208: Generate an authorization confirmation prompt based on the target palmprint registration information, and feed back the authorization confirmation prompt to the user terminal.

[0071] The authorization confirmation prompt refers to a prompt for confirming the authorization of the palm authentication service, that is, a prompt for confirming the activation of the palm authentication service.

[0072] Specifically, the server will generate an authorization confirmation prompt based on the target palmprint registration information and send this confirmation prompt back to the user terminal, prompting the target user using the user terminal to confirm the authorization of the palm verification service and to confirm the activation of the palm verification service. In specific applications, the authorization confirmation prompt can be used to confirm the target palmprint registration information, that is, to allow the target user to verify whether the target palmprint registration information is correct. The authorization confirmation prompt can also be used to verify the target user, that is, to allow the target user to supplement the target palmprint registration information to verify their identity. It should be noted that the authorization confirmation prompt generated for different purposes is different.

[0073] Step 210: Receive the authorization confirmation information fed back by the user terminal, verify the authorization confirmation information; and when the authorization confirmation information passes the verification, bind the user account and the target palmprint feature.

[0074] Among them, the authorization confirmation information refers to the information that the target user feeds back through the user terminal to confirm the authorization of the palm verification service. The authorization confirmation information can be used to determine whether the target user authorizes the activation of the palm verification service and whether the palm verification service can be activated for the target user's user account.

[0075] Specifically, after receiving the authorization confirmation prompt, the target user can feedback authorization confirmation information through the user terminal. After receiving the authorization confirmation information feedback from the user terminal, the server will verify the authorization confirmation information to determine whether the target user has authorized the activation of the palm verification service. If the authorization confirmation information passes the verification, it means that the target user has authorized the activation of the palm verification service and the palm verification service can be activated for the target user's user account. The server will bind the user account and the target palm print feature to activate the palm verification service for the user account. If the authorization confirmation information fails the verification, it means that the target user has not authorized the activation of the palm verification service or the palm verification service cannot be activated for the target user's user account. The server will push a palm verification failure prompt to the user terminal, instructing the user to re-register the palm print feature through the palm verification terminal to activate the palm verification service for the user account.

[0076] The palm data processing method receives a user request uploaded by a user terminal and extracts a first palmprint feature from the first palm image data carried in the user request. This allows the extraction of the palmprint feature required for activating the palm verification service from the user terminal. By matching the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location, the unbound palmprint feature registered by the palm verification terminal can be matched with the palmprint feature uploaded by the user terminal. Furthermore, if the target palmprint feature exists, the method generates an authorization confirmation prompt based on the target palmprint registration information associated with the target palmprint feature. The authorization confirmation prompt is then fed back to the user terminal to instruct the user terminal to complete the palm verification service authorization confirmation. Upon receiving the authorization confirmation information fed back by the user terminal and verifying that the authorization confirmation information passes verification, the user account and the target palmprint feature are bound to activate the palm verification service for the user account. This entire process allows the palm verification service to be activated through asynchronous authorization, eliminating the need for the target user to cooperate with both the palm verification terminal and the user terminal to complete the activation. This streamlines the activation process and improves the efficiency of activating the palm verification service.

[0077] In one embodiment, matching the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location includes:

[0078] For each unbound palmprint feature stored in a preset storage location, determining a feature similarity between the first palmprint feature and the unbound palmprint feature;

[0079] When there is a first similar palmprint feature whose feature similarity with the first palmprint feature is greater than the similarity threshold, and the number of the first similar palmprint features is only one, the first similar palmprint feature is used as a target palmprint feature that matches the first palmprint feature.

[0080] The feature similarity is used to describe the degree of similarity between the first palmprint feature and the unbound palmprint feature. The higher the feature similarity, the more similar the first palmprint feature and the unbound palmprint feature are. It is understood that if the target user has previously registered their palmprint features offline through a palm verification terminal, the registered palmprint features will be stored in the server as unbound palmprint features. Therefore, by matching the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location, it is possible to determine whether the target user has previously registered their palmprint features offline through a palm verification terminal.

[0081] Specifically, for each unbound palmprint feature stored in a preset storage location, the server calculates the feature similarity between the first palmprint feature and the unbound palmprint feature, then compares the feature similarity with the similarity threshold. If there is a first similar palmprint feature whose feature similarity with the first palmprint feature is greater than the similarity threshold, and there is only one first similar palmprint feature, the first similar palmprint feature is directly used as the target palmprint feature to match the first palmprint feature. The similarity threshold can be configured according to the actual application scenario. For example, the similarity threshold can be 90% or 95%.

[0082] It should be noted that when there is only one first similar palmprint feature, it means that there is a unique palmprint feature that matches the first palmprint feature among at least one unbound palmprint feature. Therefore, the server can directly use the first similar palmprint feature as the target palmprint feature that matches the first palmprint feature. However, when there are multiple first similar palmprint features, the server needs to further compare the feature similarities corresponding to each of the multiple first similar palmprint features to determine whether there is a target palmprint feature that matches the first palmprint feature among the multiple first similar palmprint features.

[0083] In a specific application, the server can calculate the feature similarity of the first palmprint feature and the unbound palmprint feature through a pre-configured similarity algorithm, or can calculate the feature similarity of the first palmprint feature and the unbound palmprint feature through a pre-trained similarity calculation model. The pre-configured similarity algorithm can be configured according to the actual application scenario. For example, the pre-configured similarity algorithm can be a cosine similarity algorithm. It can be understood that the first palmprint feature and the unbound palmprint feature can both be feature vectors, and the feature similarity of the first palmprint feature and the unbound palmprint feature can be evaluated by calculating the cosine value of the angle between the two vectors. The pre-trained similarity calculation model can also be trained according to the actual application scenario. By inputting the first palmprint feature and the unbound palmprint feature into the pre-trained similarity calculation model, the similarity calculation model can output the feature similarity.

[0084] In this embodiment, by determining the feature similarity between the first palmprint feature and the unbound palmprint feature, the feature similarity can be used to determine the first similar palmprint feature, and further, when the number of the first similar palmprint features is only one, the target palmprint feature can be directly determined.

[0085] In one embodiment, the palm data processing method further includes:

[0086] When there are multiple first similar palmprint features, comparing the feature similarities corresponding to the multiple first similar palmprint features to obtain a similarity comparison result;

[0087] When the similarity comparison result satisfies the existence condition of the first target palmprint feature, the first similar palmprint feature having the highest feature similarity to the first palmprint feature is used as the target palmprint feature that matches the first palmprint feature.

[0088] Among them, the existence condition of the first target palmprint feature refers to the condition for the existence of the target palmprint feature determined based on the feature similarity, which can be configured according to the actual application scenario. For example, the existence condition of the first target palmprint feature can specifically be that among the feature similarities corresponding to multiple first similar palmprint features, the difference between the maximum feature similarity and the second largest feature similarity is greater than a preset first difference threshold. Among them, the preset first difference threshold can be configured according to the actual application scenario. For another example, the existence condition of the first target palmprint feature can specifically be that among the feature similarities corresponding to multiple first similar palmprint features, the ratio of the maximum feature similarity to the second largest feature similarity is greater than a preset first ratio threshold. Among them, the preset first ratio threshold can be configured according to the actual application scenario.

[0089] Specifically, when there are multiple first similar palmprint features, it means that the method of screening feature similarity based on the similarity threshold cannot directly determine whether there is a target palmprint feature matching the first palmprint feature in at least one unbound palmprint feature. There may be situations such as unreasonable setting of the similarity threshold, resulting in the number of screened first similar palmprint features being multiple. Therefore, it is necessary to further compare the feature similarities corresponding to the multiple first similar palmprint features to obtain a similarity comparison result, and then determine whether the similarity comparison result meets the existence condition of the first target palmprint feature. When the similarity comparison result meets the existence condition of the first target palmprint feature, the first similar palmprint feature with the highest feature similarity to the first palmprint feature will be used as the target palmprint feature matching the first palmprint feature.

[0090] In a specific application, when comparing the feature similarities corresponding to multiple first similar palmprint features, the server will first sort the multiple feature similarities, determine the maximum feature similarity and the second largest feature similarity, and then calculate at least one of the difference and ratio between the maximum feature similarity and the second largest feature similarity, and use at least one of the difference and ratio between the maximum feature similarity and the second largest feature similarity as the similarity comparison result.

[0091] In a specific application, the existence condition of the first target palmprint feature may be that the difference between the maximum feature similarity and the second largest feature similarity is greater than a preset first difference threshold. In this case, as long as the difference between the maximum feature similarity and the second largest feature similarity in the similarity comparison result is greater than the preset first difference threshold, the similarity comparison result can be considered to satisfy the existence condition of the first target palmprint feature. The existence condition of the first target palmprint feature may be that the ratio of the maximum feature similarity to the second largest feature similarity is greater than a preset first ratio threshold. In this case, as long as the ratio of the maximum feature similarity to the second largest feature similarity in the similarity comparison result is greater than the preset first ratio threshold, the similarity comparison result can be considered to satisfy the existence condition of the first target palmprint feature.

[0092] In a specific application, the existence condition of the first target palmprint feature may be that the difference between the maximum feature similarity and the second largest feature similarity is greater than a preset first difference threshold or the ratio of the maximum feature similarity to the second largest feature similarity is greater than a preset first ratio threshold. In this case, as long as the difference between the maximum feature similarity and the second largest feature similarity in the similarity comparison result is greater than the preset first difference threshold or the ratio of the maximum feature similarity to the second largest feature similarity is greater than the preset first ratio threshold, the similarity comparison result can be considered to meet the existence condition of the first target palmprint feature.

[0093] In a specific application, assuming the similarity threshold is 80%, there are two first similar palmprint features, where the feature similarity between the first first similar palmprint feature and the first palmprint feature is 98%, and the feature similarity between the second first similar palmprint feature and the first palmprint feature is 85%. By comparing the two feature similarities, the server can obtain a similarity comparison result that the difference between the two feature similarities is 13%, and the ratio of the two feature similarities is 1.15. If the first target palmprint feature exists under the condition that the difference between the maximum feature similarity and the second largest feature similarity is greater than a preset first difference threshold (10%) or the ratio between the maximum feature similarity and the second largest feature similarity is greater than a preset first ratio threshold (1.1), the server will use the first first similar palmprint feature as the target palmprint feature that matches the first palmprint feature.

[0094] It can be understood that by comparing the maximum feature similarity and the second largest feature similarity, when the difference between the two is greater than the first difference threshold or the ratio meets the first ratio threshold, it is considered that the similarity comparison result meets the existence condition of the first target palmprint feature. Only when it is ensured that there are differences between multiple first similar palmprint features can the existence of the target palmprint feature be determined, and the first similar palmprint feature with the highest feature similarity to the first palmprint feature is used as the target palmprint feature. This can avoid the situation where the target palmprint feature cannot be determined due to unreasonable setting of the similarity threshold.

[0095] In this embodiment, when there are multiple first similar palmprint features, a similarity comparison result can be obtained by comparing the feature similarities corresponding to the multiple first similar palmprint features. Then, by judging whether the similarity comparison result satisfies the existence condition of the first target palmprint feature, it is possible to determine whether the target palmprint feature exists. Therefore, when the target palmprint feature exists, the first similar palmprint feature with the highest feature similarity can be used as the target palmprint feature that matches the first palmprint feature.

[0096] In one embodiment, matching the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location includes:

[0097] For each unbound palmprint feature stored in a preset storage location, determining a feature distance between the first palmprint feature and the unbound palmprint feature;

[0098] When there is a second similar palmprint feature whose feature distance to the first palmprint feature is less than the distance threshold, and the number of the second similar palmprint features is only one, the second similar palmprint feature is used as the target palmprint feature to match the first palmprint feature.

[0099] The feature distance is used to describe the degree of similarity between the first palmprint feature and the unbound palmprint feature. The closer the feature distance, the more similar the first palmprint feature and the unbound palmprint feature are. It is understood that if the target user has previously registered their palmprint features offline through a palm verification terminal, the registered palmprint features will be stored in the server as unbound palmprint features. Therefore, by matching the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location, it is possible to determine whether the target user has previously registered their palmprint features offline through a palm verification terminal.

[0100] Specifically, for each unbound palmprint feature stored in a preset storage location, the server calculates the characteristic distance between the first palmprint feature and the unbound palmprint feature, then compares the characteristic distance with the distance threshold. If there is a second similar palmprint feature whose characteristic distance with the first palmprint feature is less than the distance threshold, and there is only one second similar palmprint feature, the second similar palmprint feature is directly used as the target palmprint feature to match the first palmprint feature. The distance threshold can be configured according to the actual application scenario.

[0101] It should be noted that when there is only one second-similar palmprint feature, it means that there is a unique palmprint feature that matches the first palmprint feature among at least one unbound palmprint feature. Therefore, the server can directly use this second-similar palmprint feature as the target palmprint feature to match the first palmprint feature. However, when there are multiple second-similar palmprint features, the server needs to further compare the feature distances corresponding to the multiple second-similar palmprint features to determine whether there is a target palmprint feature that matches the first palmprint feature among the multiple second-similar palmprint features.

[0102] In specific applications, the server can calculate the feature distance between the first palmprint feature and the unbound palmprint feature using a preconfigured distance algorithm. The preconfigured distance algorithm can be configured according to the actual application scenario. For example, the preconfigured distance algorithm can be a Euclidean distance algorithm, a Hamming distance algorithm, or the like. Euclidean distance is a commonly used distance definition, referring to the true distance between two points in m-dimensional space, or the natural length of a vector (i.e., the distance from the point to the origin). The Euclidean distance in two-dimensional and three-dimensional space is the actual distance between two points. The Hamming distance represents the number of different characters in corresponding positions of two (same-length) strings. We use d(x,y) to represent the Hamming distance between two characters x and y. Perform an XOR operation on two strings and count the number of 1s. This number is the Hamming distance.

[0103] In a specific application, the first palmprint feature and the unbound palmprint feature can both be feature vectors. The Euclidean distance algorithm can be used to calculate the distance between the two vectors, and the distance between the two vectors can be used as the feature distance. Alternatively, the Hamming distance algorithm can be used to calculate the number of different elements in corresponding element positions of the two vectors, i.e., the Hamming distance, and the Hamming distance between the two vectors can be used as the feature distance.

[0104] In this embodiment, by determining the characteristic distance between the first palmprint feature and the unbound palmprint feature, the characteristic distance can be used to determine the second similar palmprint feature, and further, when the number of the second similar palmprint features is only one, the target palmprint feature can be directly determined.

[0105] In one embodiment, the palm data processing method further includes:

[0106] When there are multiple second similar palmprint features, comparing the feature distances corresponding to the multiple second similar palmprint features to obtain a distance comparison result;

[0107] When the distance comparison result satisfies the existence condition of the second target palmprint feature, the second similar palmprint feature having the shortest feature distance to the first palmprint feature is used as the target palmprint feature that matches the first palmprint feature.

[0108] Among them, the second target palmprint feature existence condition refers to the condition for the existence of the target palmprint feature determined based on the feature distance, and can be configured according to the actual application scenario. For example, the second target palmprint feature existence condition can specifically be that among the feature distances of multiple second similar palmprint features and the first palmprint feature, the difference between the minimum feature distance and the second minimum feature distance is greater than a preset second difference threshold. Among them, the preset second difference threshold can be configured according to the actual application scenario. For another example, the second target palmprint feature existence condition can specifically be that among the feature distances of multiple second similar palmprint features and the first palmprint feature, the ratio of the minimum feature distance to the second minimum feature distance is greater than a preset second ratio threshold. Among them, the preset second ratio threshold can be configured according to the actual application scenario.

[0109] Specifically, when there are multiple second similar palmprint features, it means that the method of screening feature distance based on distance threshold cannot directly determine whether there is a target palmprint feature matching the first palmprint feature in at least one unbound palmprint feature. There may be situations such as unreasonable setting of the distance threshold, resulting in the number of screened second similar palmprint features being multiple. Therefore, it is necessary to further compare the feature distances corresponding to the multiple second similar palmprint features to obtain a distance comparison result, and then determine whether the distance comparison result meets the existence condition of the second target palmprint feature. When the distance comparison result meets the existence condition of the second target palmprint feature, the second similar palmprint feature with the closest feature distance to the first palmprint feature will be used as the target palmprint feature matching the first palmprint feature.

[0110] In a specific application, when comparing the feature distances corresponding to multiple second similar palmprint features, the server will first sort the multiple feature distances, determine the minimum feature distance and the second minimum feature distance, and then calculate at least one of the difference and ratio between the minimum feature distance and the second minimum feature distance, and use at least one of the difference and ratio between the minimum feature distance and the second minimum feature distance as the distance comparison result.

[0111] In a specific application, the existence condition of the second target palmprint feature may be that the difference between the minimum feature distance and the second minimum feature distance is greater than a preset second difference threshold. In this case, as long as the difference between the minimum feature distance and the second minimum feature distance in the distance comparison result is greater than the preset second difference threshold, the distance comparison result can be considered to meet the existence condition of the second target palmprint feature. The existence condition of the second target palmprint feature may be that the ratio of the minimum feature distance to the second minimum feature distance is greater than a preset second ratio threshold. In this case, as long as the ratio of the minimum feature distance to the second minimum feature distance in the distance comparison result is greater than the preset second ratio threshold, the distance comparison result can be considered to meet the existence condition of the second target palmprint feature.

[0112] In a specific application, the existence condition of the second target palmprint feature may be that the difference between the minimum feature distance and the second minimum feature distance is greater than a preset second difference threshold or the ratio of the minimum feature distance to the second minimum feature distance is greater than a preset second ratio threshold. In this case, as long as the difference between the minimum feature distance and the second minimum feature distance in the distance comparison result is greater than the preset second difference threshold or the ratio of the minimum feature distance to the second minimum feature distance is greater than the preset second ratio threshold, the distance comparison result can be considered to meet the existence condition of the second target palmprint feature.

[0113] It can be understood that by comparing the minimum feature distance and the second minimum feature distance, when the difference between the two is greater than the second difference threshold or the ratio meets the second ratio threshold, it is considered that the distance comparison result meets the existence condition of the second target palmprint feature. Only when it is ensured that there are differences between multiple second similar palmprint features can the existence of the target palmprint feature be determined, and the second similar palmprint feature with the closest feature distance to the first palmprint feature is used as the target palmprint feature. This can avoid the situation where the target palmprint feature cannot be determined due to unreasonable setting of the distance threshold.

[0114] In this embodiment, when there are multiple second similar palmprint features, a distance comparison result can be obtained by comparing the feature distances corresponding to the multiple second similar palmprint features. Then, by judging whether the distance comparison result satisfies the existence condition of the second target palmprint feature, it is possible to determine whether the target palmprint feature exists. Therefore, when the target palmprint feature exists, the second similar palmprint feature with the closest feature distance can be used as the target palmprint feature that matches the first palmprint feature.

[0115] In one embodiment, the authorization confirmation prompt is used to indicate confirmation of the target palmprint registration information. Receiving authorization confirmation information fed back by the user terminal and verifying the authorization confirmation information include:

[0116] Receive authorization confirmation information fed back by the user terminal, and when the authorization confirmation information includes a confirmation keyword, determine that the authorization confirmation information passes the verification.

[0117] Specifically, the authorization confirmation prompt is used to indicate confirmation of the target palmprint registration information. The target user only needs to confirm whether the target palmprint registration information is correct through the user terminal. The authorization confirmation prompt fed back by the server will include the target palmprint registration information. After receiving the authorization confirmation prompt, the user terminal will display the authorization confirmation prompt including the target palmprint registration information for the target user to confirm. After confirming that the target palmprint registration information is correct, the target user can feedback authorization confirmation information including a confirmation keyword through the user terminal. The server receives the authorization confirmation information fed back by the user terminal and identifies whether the confirmation keyword is included in the authorization confirmation information. If the confirmation keyword is included in the authorization confirmation information, it is determined that the authorization confirmation information has passed verification.

[0118] In a specific application, the target palmprint registration information includes the palmprint registration time and the palmprint registration location. The authorization confirmation prompt displayed by the user terminal can be as shown in Figure 5, including the target palmprint registration information. Furthermore, as shown in Figure 5, in addition to displaying the target palmprint registration information, other prompt information (i.e., "Confirm Binding Palm" in Figure 5) and authorization confirmation controls (i.e., "Authorize" in Figure 5) and authorization cancellation controls (i.e., "Cancel" in Figure 5) will also be displayed on the user terminal. If the target user confirms that the target palmprint registration information is correct, a trigger event for the authorization confirmation control can be initiated. In response to the trigger event for the authorization confirmation control, the user terminal will feedback authorization confirmation information including a confirmation keyword. Among them, the confirmation keyword can be configured according to the actual application scenario. For example, the confirmation keyword can specifically be confirmation authorization.

[0119] In addition, if the target user finds that the target palm print registration information is incorrect, he or she can initiate a trigger event for the authorization cancellation control. In response to the trigger event for the authorization cancellation control, the user terminal will feedback authorization confirmation information that does not include a confirmation keyword. After receiving the authorization confirmation information, the server will determine that the authorization confirmation information has failed the verification because it cannot recognize the confirmation keyword from the authorization confirmation information. It will feedback a confirmation authorization cancellation prompt to the user terminal and stop activating the palm verification service.

[0120] In this embodiment, based on the authorization confirmation information fed back by the user terminal, the authorization confirmation information can be verified by determining whether the authorization confirmation information includes a confirmation keyword.

[0121] In one embodiment, the authorization confirmation prompt is used to indicate feedback of palmprint authorization verification information. Receiving the authorization confirmation information fed back by the user terminal and verifying the authorization confirmation information include:

[0122] Receive authorization confirmation information fed back by the user terminal, and extract palmprint authorization verification information from the authorization confirmation information;

[0123] When the palmprint authorization verification information is consistent with the target palmprint registration information, it is determined that the authorization confirmation information has passed the verification.

[0124] The palmprint authorization verification information refers to information used to verify palmprint authorization. For example, the palmprint authorization verification information may specifically refer to information used to check the target palmprint registration information to verify the identity of the target user.

[0125] Specifically, the authorization confirmation prompt is used to indicate the feedback of palmprint authorization verification information. The target user needs to feedback the palmprint authorization verification information through the user terminal so that the server can determine whether to activate the palm verification service for the target user's user account. It is understandable that since the target user has already registered the target palmprint features offline through the palm verification terminal and chooses to authorize the activation of the palm verification service through the user terminal later, the target user is aware of the target palmprint registration information. By having the target user feedback the palmprint authorization verification information through the user terminal and comparing the palmprint authorization verification information with the target palmprint registration information to see if they are consistent, the identity of the target user can be verified, which can improve the security of activating the palm verification service.

[0126] Specifically, the authorization confirmation prompt fed back by the server will include a palmprint authorization verification prompt. After receiving the authorization confirmation prompt, the user terminal will display the palmprint authorization verification prompt for the target user to perform palmprint authorization verification. The target user can feedback palmprint authorization verification information through the user terminal. After receiving the authorization confirmation information fed back by the user terminal, the server will extract the palmprint authorization verification information from the authorization confirmation information, compare the palmprint authorization verification information with the target palmprint registration information to see if they are consistent. When the palmprint authorization verification information is consistent with the target palmprint registration information, it is determined that the authorization confirmation information has passed the verification.

[0127] In a specific application, the target palmprint registration information includes the palmprint registration time and the palmprint registration location. The palmprint authorization verification prompt displayed by the user terminal can be as shown in Figure 6, prompting the target user to enter the palmprint registration time and the palmprint registration location for palmprint authorization verification. Furthermore, as shown in Figure 6, in addition to displaying the palmprint authorization verification prompt, the user terminal will also display a verification information submission control (i.e., "Submit" in Figure 6). After the target user enters the palmprint registration time and the palmprint registration location, he can initiate a trigger event for the verification information submission control. In response to the trigger event for the verification information submission control, the user terminal will feedback authorization confirmation information including palmprint authorization verification information. Among them, the palmprint authorization verification information includes the palmprint registration time and the palmprint registration location entered by the target user.

[0128] In addition, as shown in FIG6 , an authorization cancellation control (i.e., “Cancel” in FIG6 ) will also be displayed on the user terminal. If the target user is unable to enter the palm print registration time and location, a trigger event for the authorization cancellation control may be initiated. In response to the trigger event for the authorization cancellation control, the user terminal will feedback authorization confirmation information including authorization cancellation information. After receiving the authorization confirmation information, the server will identify the authorization cancellation information in the authorization confirmation information and determine that the authorization confirmation information has failed verification. The server will feedback a prompt confirming the authorization cancellation to the user terminal and stop activating the palm verification service.

[0129] In this embodiment, based on the authorization confirmation information fed back by the user terminal, the palmprint authorization verification information in the authorization confirmation information can be used to verify the authorization confirmation information.

[0130] In one embodiment, when the authorization confirmation information passes verification, binding the user account and the target palmprint feature to activate the palm verification service for the user account includes:

[0131] When the authorization confirmation information passes the verification, the password verification prompt corresponding to the user account is pushed to the user terminal;

[0132] Receive the password verification information fed back by the user terminal. When the verification password in the password verification information is consistent with the resource transfer password of the user account, bind the user account and the target palm print feature to activate the palm verification service of the user account.

[0133] The password verification prompt is used to prompt the user to enter the resource transfer password corresponding to the user account to verify the identity of the target user.

[0134] Specifically, when the authorization confirmation information passes verification, in order to further improve the security of the palm authentication service for activating the user account, the server needs to verify the identity of the target user again. At this time, the server will push the password verification prompt corresponding to the user account to the user terminal, instructing the target user to enter the resource transfer password corresponding to the user account in order to verify their identity. After receiving the password verification prompt, the user terminal will display the password verification prompt. The target user can enter the password for identity verification on the user terminal. In response to the target user's input event, the user terminal will use the password entered by the target user for identity verification as the verification password, generate and feedback password verification information to the server. After receiving the password verification information feedback from the user terminal, the server will compare the verification password in the password verification information with the resource transfer password of the user account to see if they are consistent. If the verification password in the password verification information is consistent with the resource transfer password of the user account, it means that the identity authentication of the target user has passed. The server will bind the user account and the target palm print feature to activate the palm authentication service for the user account.

[0135] In a specific application, the password verification prompt displayed by the user terminal may be as shown in FIG7 , prompting the target user to enter the resource transfer password corresponding to the user account for identity verification. As shown in FIG7 , the resource transfer password may be a combination of multiple digits, and the displayed virtual keyboard is a numeric keypad. Alternatively, the resource transfer password may be a combination of multiple characters and digits. It is understood that the number of elements in the resource transfer password is fixed. For example, when the number of digits entered by the target user reaches the fixed number of elements corresponding to the resource transfer password, the user terminal will use the digits entered by the target user in the order in which they were entered as the verification password, generate password verification information, and send it back to the server. The fixed number of elements can be configured according to the actual application scenario. For example, the fixed number of elements can be 4. After the target user enters 4 digits, the user terminal will directly use the 4 digits entered by the target user as the verification password. In a specific application, after binding the user account and the target palmprint features, the server will push a successful binding notification to the user terminal, informing the user terminal that the binding was successful, i.e., that the palm verification service has been enabled for the user account. In a specific application, the successful binding prompt displayed by the user terminal may be as shown in FIG8 .

[0136] In this embodiment, when the authorization confirmation information passes the verification, the password verification prompt corresponding to the user account is pushed to the user terminal, which can indicate the feedback of the password verification information to verify the identity of the target user. On the basis of receiving the password verification information fed back by the user terminal, the verification password in the password verification information can be used to verify the identity of the target user. Then, when it is consistent with the resource transfer password of the user account, the user account and the target palm print feature can be bound to activate the palm verification service of the user account, which can improve the security of activating the palm verification service of the user account.

[0137] In one embodiment, the palm data processing method further includes:

[0138] receiving palm registration information uploaded by a palm verification terminal, the palm registration information carrying second palm image data and palm print registration information;

[0139] A second palmprint feature is extracted from the second palm image data, the second palmprint feature is stored as an unbound palmprint feature, and is associated with the palmprint registration information in the palm registration information.

[0140] The palm registration information refers to the information uploaded through the palm verification terminal for palm print registration, which carries the second palm image data and palm print registration information. The second palm image data refers to the image data containing the palm image collected and uploaded by the palm verification terminal. It is understood that when the target user registers their palm print through the palm verification terminal, the palm verification terminal will collect and upload their second palm image data.

[0141] Specifically, when activating the palm verification service, you must first register your palm print offline using a palm verification terminal. For example, the registered user will go to the palm verification terminal to collect a second palm image. After collecting the second palm image data, the palm verification terminal will generate palm registration information based on the second palm image data, the collection time, and the collection location. This palm registration information will then be uploaded to the server. The palm registration information contains the second palm image data and the palm print registration information. After receiving the palm registration information, the server will extract the second palm print feature from the second palm image data, store it as an unbound palm print feature, and associate it with the palm print registration information in the palm registration information to complete the palm print registration. Any registered user can be the target user or another user. After completing palm print registration, the server will send a registration completion notification to the palm verification terminal.

[0142] In specific applications, the palm verification terminal captures the second palm image data similarly to the user terminal's process for capturing the first palm image data. The palm verification terminal first performs image acquisition, collecting a palm image stream. Then, using an optimization algorithm, it completes image preprocessing and image quality detection, liveness detection, infrared and color image registration, and quality inspection. It then selects the second palm image data that meets quality standards and uploads the palm registration information to the server. The palm image stream can specifically include a palm color image stream and an infrared image stream.

[0143] Among them, image preprocessing and image quality detection refer to the alignment, filtering, grayscale conversion and other steps of the collected original image to improve the image quality and select high-quality image data (clear and feature-rich) to enter the next step. Liveness detection refers to capturing infrared image data of the palm based on infrared imaging, and then analyzing the texture features and blood vessel distribution in the infrared image data to determine whether it is alive. At the same time, it can be combined with depth, thermal imaging, pulse detection and other methods to further detect and determine whether it is a live palm. Infrared and color images refer to image alignment through coordinate mapping, cropping and other methods. Quality detection refers to further testing of the selected high-quality image data to ensure that the image data meets the multi-dimensional threshold and screen out the second palm image data. Among them, the multi-dimensionality can be image quality, blur, feature information richness, exposure, etc.

[0144] In a specific application, a palm verification terminal may include a color camera and an infrared camera, as shown in Figure 9. The color camera can be used to capture second palm image data, and the infrared camera can be used to capture infrared image data. Furthermore, the palm verification terminal should be equipped with an infrared light, a light ring (for fill light and interaction), an infrared camera, a color camera, and an optional touchscreen. The infrared light supplements the infrared light, enhancing the infrared camera's acquisition capabilities. The light ring guides registered users to the current acquisition area, and fill light enhances the color camera's acquisition capabilities. The touchscreen provides interactive guidance. Registered users can use the touchscreen to select "Authorize and activate later," allowing them to authorize and activate the palm verification service later on the user terminal. It should be noted that without a touchscreen, the palm verification terminal can be configured to operate in asynchronous registration mode, with a light ring effect indicating whether the registration is successful (the light ring uses different colors, including green, red, and yellow). Furthermore, the palm verification terminal should be capable of running image optimization algorithms, graphics rendering, database storage, and sufficient performance for recognition logic. It should also be capable of connecting to a network and hosting a backend recognition service.

[0145] In this embodiment, after receiving the palm registration information uploaded by the palm verification terminal, palm print registration can be achieved by extracting the second palm print feature from the second palm image data, storing the second palm print feature as an unbound palm print feature, and associating it with the palm print registration information in the palm registration information.

[0146] In one embodiment, the palm data processing method further includes:

[0147] The second palm print feature is matched with at least one bound palm print feature stored in a preset storage location. When there is no palm print feature matching the second palm print feature in the at least one bound palm print feature, the process proceeds to the step of storing the second palm print feature as an unbound palm print feature.

[0148] The bound palmprint feature refers to the palmprint feature that has been bound to the account of the target platform.

[0149] Specifically, after extracting the second palmprint feature, the server will match the second palmprint feature with at least one bound palmprint feature stored in a preset storage location to determine whether the second palmprint feature is an unregistered new palmprint feature. When there is no palmprint feature matching the second palmprint feature in at least one bound palmprint feature, it indicates that the second palmprint feature is a new palmprint feature, and the server will store the second palmprint feature as an unbound palmprint feature.

[0150] In a specific application, the server may use a feature matching algorithm to match the second palmprint feature with at least one bound palmprint feature stored in a preset storage location. The feature matching algorithm may be configured according to the actual application scenario. For example, the feature matching algorithm may be based on feature similarity. The feature similarity may be cosine similarity. Another example is based on feature distance. The feature distance may be Euclidean distance, Hamming distance, or the like.

[0151] In this embodiment, by matching the second palmprint feature with at least one bound palmprint feature stored in a preset storage location, it is possible to determine whether the second palmprint feature is a new palmprint feature through feature matching. Palmprint registration can then be performed only when the second palmprint feature is a new palmprint feature. By performing verification during the registration process, duplicate palmprint registration or incorrect binding of palmprint features can be avoided.

[0152] In one embodiment, the palm data processing method further includes:

[0153] receiving a palm registration request uploaded by a palm verification terminal, wherein the palm registration request carries third palm image data;

[0154] extracting a third palmprint feature from the third palm image data, and matching the third palmprint feature with at least one bound palmprint feature stored in a preset storage location;

[0155] When there is no palm print feature matching the third palm print feature in at least one bound palm print feature, a palm registration prompt is pushed to the palm verification terminal to instruct the user to upload palm registration information for registration through the palm verification terminal.

[0156] Specifically, a registered user who needs to register a palm print will upload a palm registration request through a palm verification terminal. The palm registration request carries the third palm image data. After receiving the palm registration request uploaded by the palm verification terminal, the server will extract the third palm print feature from the third palm image data, and match the third palm print feature with at least one bound palm print feature stored in a preset storage location to determine whether the third palm print feature is an unregistered new palm print feature. When there is no palm print feature matching the third palm print feature in at least one bound palm print feature, it indicates that the third palm print feature is a new palm print feature. The server will push a palm registration prompt to the palm verification terminal to instruct the registered user to upload the palm registration information through the palm verification terminal for registration.

[0157] In a specific application, the server may use a feature matching algorithm to match the third palmprint feature with at least one bound palmprint feature stored in a preset storage location. The feature matching algorithm may be configured according to the actual application scenario. For example, the feature matching algorithm may be based on feature similarity. The feature similarity may be cosine similarity. Another example is based on feature distance. The feature distance may be Euclidean distance, Hamming distance, or the like.

[0158] In this embodiment, by matching the third palmprint feature with at least one bound palmprint feature stored in a preset storage location, it is possible to determine whether the third palmprint feature is a new palmprint feature through feature matching. Then, only when the third palmprint feature is a new palmprint feature can a palm registration prompt be pushed to the palm verification terminal to instruct palmprint registration. By using the verification-before-registration approach, duplicate palmprint registration or incorrect binding of palmprint features can be avoided.

[0159] In one embodiment, the inventors believe that, with traditional methods, after collecting palm image data when activating a palm verification service, the target user is required to use a user terminal to scan a graphic code and complete the binding of the user account with the palm print feature according to the instructions before the palm verification service for the user account can be activated. If the target user does not have a user terminal or a user account at the time, the palm verification service cannot be activated, which will cause the loss of users using the target platform. In addition, the activation process using traditional methods is cumbersome and requires authorization to complete the activation, resulting in low efficiency in activating the palm verification service. In addition, the traditional method also has the following two problems: first, blocking registration, where the palm verification terminal cannot continue to be used while the palm print is being entered; second, the probability of incorrect binding is high, because the graphic code displayed on the palm verification terminal can easily be scanned by others to authorize the binding.

[0160] Based on this, the present application proposes a palm data processing method. For situations where the target user does not have a user terminal and cannot be authorized in real time, the user can first enter the palm print feature on the palm verification terminal and choose to authorize the platform identity later. Then, when the user terminal authorization conditions allow, the user can log in to the user account of the target platform through the user terminal, and collect and upload the first palm image data through the user terminal. This allows the server to extract the first palm print feature from the first palm image data and match the first palm print feature with at least one unbound palm print feature stored in a preset storage location to achieve asynchronous authorization of palm print feature matching, thereby activating the palm verification service for the user account. It is understandable that the present application can be applied to group collection scenarios, scenarios without mobile terminals, etc., and can be used to activate the palm verification service for the target platform account of people without mobile terminals, such as the elderly and students.

[0161] In one embodiment, the technical concept of the palm data processing method of the present application can be shown in Figure 10. The target user first collects palm data on the palm verification terminal, so that the palm verification terminal collects second palm image data (as shown in Figure 10, the palm verification terminal can collect color image data and infrared image data), selects "Authorize Later", and the palm verification terminal then uploads the palm registration information to the server, so that the server extracts the second palmprint feature from the second palm image data (it should be noted that the extracted features can only be the color image data features), stores the second palmprint feature as an unbound palmprint feature, and associates it with the palmprint registration information in the palm registration information. On this basis, the target user activates the palm verification service online and collects palm data on the user terminal, so that the user terminal collects the first palm image data and uploads the user request to the server, so that the server extracts the first palm print feature from the first palm image data and matches the first palm print feature with at least one unbound palm print feature stored in a preset storage location, that is, performs a verification and comparison. When there is a target palm print feature that matches the first palm print feature in the at least one unbound palm print feature, the target palm print registration information associated with the target palm print feature is obtained. Based on the target palm print registration information, an authorization confirmation prompt is generated and fed back to the user terminal for the target user to confirm again so that the authorization is completed and activated. The target user can feedback the authorization confirmation information through the user terminal. The server receives the authorization confirmation information fed back by the user terminal and verifies the authorization confirmation information. When the authorization confirmation information passes the verification, the user account and the target palm print feature are bound to activate the palm verification service for the user account.

[0162] In one embodiment, as shown in FIG11 , it is understood that after collecting the second palm image data, the palm verification terminal may also first extract the second palmprint feature from the second palm image data, and then upload the palm registration information to the server. In this case, the palm registration information carries the second palmprint feature, and upon receiving the palm registration information, the server can directly store the second palmprint feature as an unbound palmprint feature, without further image feature extraction. Furthermore, after collecting the first palm image data, the user terminal may also first extract the first palmprint feature from the first palm image data, and then upload the user request to the server. In this case, the user request carries the first palmprint feature, and upon receiving the user request, the server can directly match the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location, without further image feature extraction.

[0163] In one embodiment, as shown in FIG12 , taking the example of a palm verification terminal extracting second palmprint features from the second palm image data after collecting the second palm image data, and a user terminal extracting first palmprint features from the first palm image data after collecting the first palm image data or directly uploading the first palm image data, the palm data processing method of the present application can be composed of two parts: offline palm verification terminal entry and asynchronous authorization by the user terminal. The palm data processing method of the present application is described below based on FIG12 .

[0164] First, offline palm verification terminal entry includes four steps:

[0165] Step 1: Image acquisition: The target user goes to an offline palm verification terminal to collect palm data. The palm verification terminal collects palm color and infrared image streams.

[0166] Step 2, algorithm optimization: Input the image stream to the algorithm optimization stream, complete the algorithm steps such as palm detection, image quality judgment, liveness verification, and registration, and screen out color and infrared images that meet the quality standards.

[0167] Step 3: Feature extraction and upload: Extract the color and infrared features of the palm and register them to the server.

[0168] Among them, the palm verification terminal will extract the palm vein features from the pre-processed image, combine it with the registered on-site information (i.e. palm print registration information, including palm print registration time, palm print registration location, etc.), and register it to the server.

[0169] Among them, commonly used feature extraction methods include Gabor filtering algorithm, LBP (Local Binary Pattern) filtering algorithm, HOG (Histogram of Oriented Gradients) filtering algorithm, etc.

[0170] Step 4, offline entry completion: the server searches and confirms that it is a new palm, and returns the entry completion result to the palm verification terminal. The palm verification terminal interactively guides the target user to asynchronously authorize.

[0171] Specifically, the server can use a feature matching algorithm to match the palmprint features uploaded by the palm verification terminal with at least one bound palmprint feature stored in a preset storage location to determine whether the palmprint features uploaded by the palm verification terminal have been registered. If not, offline pre-entry is completed and the palmprint features uploaded by the palm verification terminal are stored as unbound palmprint features. The feature matching algorithm can be configured according to the actual application scenario. For example, the feature matching algorithm can be specifically based on feature similarity. The feature similarity can specifically be cosine similarity. For another example, the feature matching algorithm can be specifically based on feature distance. The feature distance can specifically be Euclidean distance, Hamming distance, etc.

[0172] Secondly, user terminal asynchronous authorization includes six steps:

[0173] Step 5, Login to the platform account: The target user registers and logs in to the target platform account (i.e. user account) to enter the authorization process.

[0174] Step 6: Secondary palm capture: The target user captures a palm color image stream through the user terminal.

[0175] The user terminal obtains the image stream through the camera and inputs it into the optimization algorithm.

[0176] Step 7, algorithm optimization: Input the image stream to the local algorithm optimization stream of the user terminal, complete the palm detection, gesture liveness verification, image quality detection and other steps, and screen out the color images that meet the quality standards.

[0177] Step 8, feature extraction and upload: extract the palm color feature (ie, the first palmprint feature) and submit it to the server, or directly upload the color image (ie, the first palm image data) and let the server complete the feature extraction.

[0178] Step 9, server search: The server searches for at least one unbound palmprint feature stored in the database based on the palm color feature or color image uploaded by the user terminal. If it matches the color feature collected by the palm verification terminal (i.e., the target palmprint feature), the server returns the target palmprint registration information to the user terminal, which may specifically be the palmprint registration time and palmprint registration location.

[0179] Step 10, target user authorization: display the target palmprint registration information, that is, the target user's offline palmprint registration time and location, the target user confirms that it is entered by himself, enters the resource transfer password (specifically, it can be a payment password) to confirm the identity authorization, and complete the activation of the palm verification service.

[0180] In one embodiment, during the activation of the palm authentication service, the interface of the user terminal may change as shown in FIG13 . First, the user terminal will display a palm image capture guide to guide the target user to enter the first palm image data. Secondly, after receiving the authorization confirmation prompt, a palmprint authorization verification prompt will be displayed for the target user to confirm whether the target palmprint registration information is correct. The target palmprint registration information includes the palmprint registration time and palmprint registration location. Secondly, when the authorization confirmation information passes the verification, the user terminal will display a password verification prompt to prompt the target user to enter the resource transfer password corresponding to the user account in order to verify their identity. Finally, after receiving the binding success prompt pushed by the server, the user terminal will display a binding success prompt to inform the target user that the palm authentication service has been activated for the user account.

[0181] It should be noted that, first, the user terminals in this application include but are not limited to mobile phones, tablets, smart watches, etc., and any computer device supported by the target platform can achieve online binding. Secondly, in this application, network recognition and local recognition are allowed. Palm print verification devices are not limited to the illustrations, as long as they can collect clear palm image data and guide registered users to slide their palms. Finally, the preferred algorithm flow, feature extraction, and feature matching algorithms in the embodiments of this application are not limited to the examples, and various other processing methods are also applicable.

[0182] It is understandable that the palm data processing method of the present application has the following advantages: First, it is highly efficient. When performing palm print registration, you can leave after collecting palm data without waiting, which is suitable for collective registration and activation scenarios. Second, it is convenient. It does not require the target user to cooperate with the user terminal for real-time authorization and activation. It is suitable for people such as the elderly and students who do not carry the user terminal with them. Third, it is safe. The palm verification service that collects palm image data multiple times through the palm verification terminal and the user terminal and activates the user account after multiple verifications can improve the security of activating the palm verification service. And in the case where the target user enters the palm print feature offline, it is necessary to use the user terminal online again to enter the palm print feature matching and activation, which can effectively reduce the probability of incorrect binding.

[0183] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0184] Based on the same inventive concept, embodiments of the present application also provide a palm data processing device for implementing the aforementioned palm data processing method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more palm data processing device embodiments provided below can be found in the aforementioned limitations of the palm data processing method and will not be further elaborated here.

[0185] In one embodiment, as shown in FIG14 , a palm data processing device is provided, comprising: a request receiving module 1402 , a feature matching module 1404 , an information acquisition module 1406 , a confirmation prompt generating module 1408 , and a binding module 1410 , wherein:

[0186] A request receiving module 1402 is configured to receive a user request uploaded by a user terminal, wherein the user request carries the first palm image data and a user account;

[0187] a feature matching module 1404 configured to extract a first palmprint feature from the first palm image data and match the first palmprint feature with at least one unbound palmprint feature stored in a preset storage location; the unbound palmprint feature is registered through a palm verification terminal and is associated with palmprint registration information;

[0188] An information acquisition module 1406 is configured to, when a target palm print feature matching the first palm print feature exists in the at least one unbound palm print feature, acquire target palm print registration information associated with the target palm print feature;

[0189] A confirmation prompt generating module 1408 is configured to generate an authorization confirmation prompt based on the target palmprint registration information, and feed the authorization confirmation prompt back to the user terminal;

[0190] The binding module 1410 is configured to receive the authorization confirmation information fed back by the user terminal, verify the authorization confirmation information, and bind the user account and the target palmprint feature when the authorization confirmation information passes the verification to activate the palm verification service for the user account.

[0191] The palm data processing device receives a user request from a user terminal and extracts a first palm print feature from the first palm image data included in the user request. This allows the extraction of the palm print feature required for activation of the palm verification service from the user terminal. By matching the first palm print feature with at least one unbound palm print feature stored in a preset storage location, the unbound palm print feature registered by the palm verification terminal can be matched with the palm print feature uploaded by the user terminal. Furthermore, if a target palm print feature exists, the device can obtain and generate an authorization confirmation prompt based on target palm print registration information associated with the target palm print feature. The authorization confirmation prompt is then fed back to the user terminal, instructing the user terminal to complete authorization confirmation for the palm verification service. Upon receiving the authorization confirmation information fed back by the user terminal and verifying that the authorization confirmation information passes verification, the user account and the target palm print feature are bound to activate the palm verification service for the user account. The entire process allows the activation of the palm verification service through asynchronous authorization, eliminating the need for the target user to cooperate with both the palm verification terminal and the user terminal to complete activation. This streamlines the activation process and improves the efficiency of activating the palm verification service.

[0192] In one embodiment, the feature matching module is further configured to determine, for each unbound palmprint feature stored in a preset storage location, a feature similarity between the first palmprint feature and the unbound palmprint feature; when there is a first similar palmprint feature whose feature similarity with the first palmprint feature is greater than a similarity threshold, and the number of the first similar palmprint features is single, use the first similar palmprint feature as a target palmprint feature to match the first palmprint feature.

[0193] In one embodiment, the feature matching module is further configured to, when there are multiple first similar palmprint features, compare the feature similarities corresponding to each of the multiple first similar palmprint features to obtain a similarity comparison result; and when the similarity comparison result satisfies the existence condition of the first target palmprint feature, use the first similar palmprint feature with the highest feature similarity to the first palmprint feature as the target palmprint feature that matches the first palmprint feature.

[0194] In one embodiment, the feature matching module is further configured to determine, for each unbound palmprint feature stored in a preset storage location, a feature distance between the first palmprint feature and the unbound palmprint feature; and when there is a second similar palmprint feature whose feature distance to the first palmprint feature is less than a distance threshold, and the number of the second similar palmprint features is only one, use the second similar palmprint feature as a target palmprint feature to match the first palmprint feature.

[0195] In one embodiment, the feature matching module is further configured to, when there are multiple second similar palm print features, compare the feature distances corresponding to the multiple second similar palm print features to obtain a distance comparison result; and when the distance comparison result satisfies the second target palm print feature existence condition, use the second similar palm print feature with the closest feature distance to the first palm print feature as the target palm print feature that matches the first palm print feature.

[0196] In one embodiment, the authorization confirmation prompt is used to indicate confirmation of the target palmprint registration information. The binding module is further used to receive authorization confirmation information fed back by the user terminal. When the authorization confirmation information includes a confirmation keyword, it is determined that the authorization confirmation information has passed the verification.

[0197] In one embodiment, the authorization confirmation prompt is used to indicate the feedback of palmprint authorization verification information. The binding module is further used to receive the authorization confirmation information fed back by the user terminal, extract the palmprint authorization verification information from the authorization confirmation information, and determine that the authorization confirmation information has passed the verification when the palmprint authorization verification information is consistent with the target palmprint registration information.

[0198] In one embodiment, the binding module is also used to push the password verification prompt corresponding to the user account to the user terminal when the authorization confirmation information passes the verification, receive the password verification information fed back by the user terminal, and when the verification password in the password verification information is consistent with the resource transfer password of the user account, bind the user account and the target palm print feature to activate the palm verification service of the user account.

[0199] In one embodiment, the palm data processing device further includes a palm print registration module, which is configured to receive palm registration information uploaded through a palm verification terminal, the palm registration information carrying second palm image data and palm print registration information, extract a second palm print feature from the second palm image data, store the second palm print feature as an unbound palm print feature, and associate it with the palm print registration information in the palm registration information.

[0200] In one embodiment, the palmprint registration module is further configured to match the second palmprint feature with at least one bound palmprint feature stored in a preset storage location, and when there is no palmprint feature matching the second palmprint feature in the at least one bound palmprint feature, the second palmprint feature is stored as an unbound palmprint feature.

[0201] In one embodiment, the palm print registration module is further configured to receive a palm registration request uploaded through a palm verification terminal, the palm registration request carrying third palm image data, extract a third palm print feature from the third palm image data, match the third palm print feature with at least one bound palm print feature stored in a preset storage location, and when no palm print feature matching the third palm print feature exists in the at least one bound palm print feature, push a palm registration prompt to the palm verification terminal to instruct the user to upload palm registration information through the palm verification terminal for registration.

[0202] Each module in the aforementioned palm data processing device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a computer device's memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0203] In one embodiment, a computer device is provided. The computer device can be either a server or a terminal. For example, if the computer device is a server, its internal structure can be shown in FIG15 . The computer device includes a processor, memory, an input / output (I / O) interface, and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data such as at least one unauthorized palm print feature. The I / O interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When executed by the processor, the computer program implements a palm data processing method.

[0204] Those skilled in the art will understand that the structure shown in FIG15 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0205] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0206] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0207] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0208] It should be noted that the user information (including but not limited to target accounts, palm image data, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0209] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0210] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0211] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A palm data processing method, executed by a computer device, the method comprising: Receiving a user request sent by a user terminal, the user request carrying first palm image data and a user account; Extracting first palmprint features from the first palm image data; Matching the first palmprint features with at least one unbound palmprint feature stored at a preset storage location; the unbound palmprint features are registered through a palm verification terminal and are associated with palmprint registration information; When there is a target palmprint feature in the at least one unbound palmprint feature that matches the first palmprint feature, obtaining the target palmprint registration information associated with the target palmprint feature; Generating an authorization confirmation prompt based on the target palmprint registration information and feeding back the authorization confirmation prompt to the user terminal; Receiving the authorization confirmation information fed back by the user terminal and verifying the authorization confirmation information; And When the authorization confirmation information passes the verification, binding the user account and the target palmprint feature.

2. The method according to claim 1, the method further comprising: When the authorization confirmation information passes the verification and the user account and the target palmprint feature are bound, enabling the palm verification service for the user account.

3. The method according to claim 1 or 2, the matching of the first palmprint features with at least one unbound palmprint feature stored at a preset storage location includes: For each unbound palmprint feature stored at a preset storage location, determining the feature similarity between the first palmprint feature and the unbound palmprint feature; When there is a first similar palmprint feature whose feature similarity to the first palmprint feature is greater than a similarity threshold and the number of the first similar palmprint features is single, taking the first similar palmprint feature as the target palmprint feature that matches the first palmprint feature.

4. The method according to claim 3, the method further comprising: When the number of the first similar palmprint features is multiple, comparing the respective feature similarities of the multiple first similar palmprint features to obtain a similarity comparison result; When the similarity comparison result meets the existence condition of the first target palmprint feature, taking the first similar palmprint feature with the highest feature similarity to the first palmprint feature as the target palmprint feature that matches the first palmprint feature.

5. The method according to claim 1 or 2, the matching of the first palmprint features with at least one unbound palmprint feature stored at a preset storage location includes: For each unbound palmprint feature stored at a preset storage location, determining the feature distance between the first palmprint feature and the unbound palmprint feature; When there is a second similar palmprint feature whose feature distance to the first palmprint feature is less than a distance threshold and the number of the second similar palmprint features is single, taking the second similar palmprint feature as the target palmprint feature that matches the first palmprint feature.

6. The method according to claim 5, the method further comprising: When the number of the second similar palmprint features is multiple, comparing the respective feature distances of the multiple second similar palmprint features to obtain a distance comparison result; When the distance comparison result meets the second target palmprint feature existence condition, the second similar palmprint feature with the closest feature distance to the first palmprint feature is used as the target palmprint feature that matches the first palmprint feature.

7. The method according to any one of claims 1 to 6, wherein the authorization confirmation prompt is used to indicate confirmation of the target palmprint registration information; the receiving the authorization confirmation information fed back by the user terminal and verifying the authorization confirmation information includes: Receiving the authorization confirmation information fed back by the user terminal, and when the authorization confirmation information includes a confirmation keyword, determining that the authorization confirmation information passes the verification.

8. The method according to any one of claims 1 to 7, wherein the authorization confirmation prompt is used to indicate the feedback of palmprint authorization verification information; The receiving the authorization confirmation information fed back by the user terminal and verifying the authorization confirmation information includes: Receiving the authorization confirmation information fed back by the user terminal, and extracting the palmprint authorization verification information from the authorization confirmation information; When the palmprint authorization verification information is consistent with the target palmprint registration information, determining that the authorization confirmation information passes the verification.

9. The method according to any one of claims 1 to 8, wherein when the authorization confirmation information passes the verification, binding the user account and the target palmprint feature to activate the palm verification service of the user account includes: When the authorization confirmation information passes the verification, pushing a password verification prompt corresponding to the user account to the user terminal; Receiving the password verification information fed back by the user terminal, and when the verification password in the password verification information is consistent with the resource transfer password of the user account, binding the user account and the target palmprint feature to activate the palm verification service of the user account.

10. The method according to any one of claims 1 to 9, the method further includes: Receiving palm registration information uploaded through the palm verification terminal, where the palm registration information carries second palm image data and palmprint registration information; Extracting a second palmprint feature from the second palm image data, storing the second palmprint feature as an unbound palmprint feature, and associating it with the palmprint registration information in the palm registration information.

11. The method according to claim 10, the method further includes: Matching the second palmprint feature with at least one bound palmprint feature stored at a preset storage location, and when there is no palmprint feature in the at least one bound palmprint feature that matches the second palmprint feature, jumping to the step of storing the second palmprint feature as an unbound palmprint feature.

12. The method according to claim 10 or 11, the method further includes: Receiving a palm registration request uploaded through the palm verification terminal, where the palm registration request carries third palm image data; Extracting a third palmprint feature from the third palm image data, and matching the third palmprint feature with at least one bound palmprint feature stored at a preset storage location; When there is no palmprint feature in the at least one bound palmprint feature that matches the third palmprint feature, a palm registration prompt is pushed to the palm verification terminal to indicate uploading the palm registration information through the palm verification terminal for registration.

13. A palm data processing device, the device comprising: A request receiving module, configured to receive a user request sent by a user terminal, where the user request carries first palm image data and a user account; A feature matching module, configured to extract a first palmprint feature from the first palm image data, and match the first palmprint feature with at least one unbound palmprint feature stored at a preset storage location; the unbound palmprint feature is registered through a palm verification terminal and is associated with palmprint registration information; An information obtaining module, configured to, when there is a target palmprint feature in the at least one unbound palmprint feature that matches the first palmprint feature, obtain the target palmprint registration information associated with the target palmprint feature; A confirmation prompt generating module, configured to generate an authorization confirmation prompt based on the target palmprint registration information, and feedback the authorization confirmation prompt to the user terminal; And A binding module, configured to receive the authorization confirmation information fed back by the user terminal, verify the authorization confirmation information, and when the authorization confirmation information passes the verification, bind the user account and the target palmprint feature.

14. A computer device, comprising a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the method according to any one of claims 1 to 12 are implemented.

15. A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

16. A computer program product, comprising a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images