CN115937917A

CN115937917A - Identity authentication method and device, electronic equipment and storage medium

Info

Publication number: CN115937917A
Application number: CN202211524511.4A
Authority: CN
Inventors: 康宏伟; 黄跃珍; 朱露露; 王洋
Original assignee: GRG Banking Equipment Co Ltd
Current assignee: GRG Banking Equipment Co Ltd
Priority date: 2022-11-30
Filing date: 2022-11-30
Publication date: 2023-04-07

Abstract

The application discloses an identity authentication method, an identity authentication device, electronic equipment and a storage medium, and belongs to the field of image processing. The identity authentication method comprises the following steps: acquiring a first finger vein image of a first user; performing image cutting on the first finger vein image to obtain a plurality of first finger vein subgraphs of different areas, wherein the image cutting strategy of the first finger vein image is determined based on the texture offset degree of the first finger vein image; acquiring a first global feature vector of a first finger vein image, and acquiring a plurality of first local feature vectors of a plurality of first finger vein subgraphs, wherein the first local feature vectors correspond to the first finger vein subgraphs one by one; and comparing the first global feature vector and the plurality of first local feature vectors with the identity authentication information of the registered second user in the identity library to obtain the identity authentication result of the first user, wherein the identity authentication information of the second user comprises the second global feature vector and the plurality of second local feature vectors. The method improves the accuracy and efficiency of finger vein recognition.

Description

Identity authentication method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of biometric identification technologies, and in particular, to an identity authentication method and apparatus, an electronic device, and a storage medium.

Background

Finger vein recognition is a biological characteristic recognition technology and plays an important role in the field of security protection. However, due to the limitation of the acquisition device, the acquired finger vein features often have rotation and translation to a certain degree, and the rotation and translation generated by the finger vein features can reduce the accuracy of finger vein recognition, so that the finger vein recognition efficiency is reduced, and the user experience is poor.

Disclosure of Invention

The present application is directed to solving at least one of the problems in the prior art. Therefore, the application provides an identity authentication method, an identity authentication device, electronic equipment and a storage medium, and the accuracy and efficiency of finger vein identification are effectively improved.

In a first aspect, the present application provides an identity authentication method, including:

acquiring a first finger vein image of a first user;

performing image cutting on the first finger vein image to obtain a plurality of first finger vein subgraphs of different areas, wherein an image cutting strategy of the first finger vein image is determined based on the texture offset degree of the first finger vein image;

acquiring a first global feature vector of the first finger vein image, and acquiring a plurality of first local feature vectors of the plurality of first finger vein subgraphs, wherein the first local feature vectors correspond to the first finger vein subgraphs one by one;

and comparing the first global feature vector and the plurality of first local feature vectors with the identity authentication information of a second user registered in an identity library to obtain the identity authentication result of the first user, wherein the identity authentication information of the second user comprises a second global feature vector and a plurality of second local feature vectors.

According to the identity authentication method, the image is cut according to different areas, the finger vein image is cut into a plurality of finger vein subgraphs, then the whole image of the user to be authenticated is compared with the whole image of the registered user, the finger vein subgraphs of the user to be authenticated are compared with the finger vein subgraphs of the registered user, the problem that the finger vein is poor in identification performance under the conditions of rotation and translation is solved, and therefore the accuracy and the efficiency of finger vein identification are improved.

According to an embodiment of the present application, the comparing the first global feature vector and the plurality of first local feature vectors with the authentication information of the second user registered in the identity repository to obtain the authentication result of the first user includes:

determining a global feature similarity between the first user and the second user based on the first global feature vector and the second global feature vector;

determining local feature similarities between the first user and the second user based on the first plurality of local feature vectors and the second plurality of local feature vectors;

and obtaining an authentication result of the first user based on at least one of the global feature similarity and the local feature similarity.

According to an embodiment of the present application, the obtaining an authentication result of the first user based on at least one of the global feature similarity and the local feature similarity includes:

obtaining the authentication result of the first user as the second user under the condition that the global feature similarity is larger than a first global threshold;

or, when the global feature similarity is less than or equal to a first global threshold and greater than a second global threshold, and the local feature similarity is greater than a first local threshold, obtaining that the authentication result of the first user is the second user, where the second global threshold is less than the first global threshold.

under the condition that the global feature similarity is smaller than or equal to a second global threshold, obtaining the identity verification result of the first user as an unregistered user;

or, when the local feature similarity is less than or equal to a first local threshold, obtaining that the authentication result of the first user is an unregistered user.

According to an embodiment of the present application, the obtaining a first global feature vector of the first finger vein map and obtaining a plurality of first local feature vectors of the plurality of first finger vein subgraphs includes:

inputting the first finger vein graph into a first layer of an identity verification model, obtaining a plurality of first global feature vectors output by the first layer, and inputting the plurality of first finger vein subgraphs into a second layer of the identity verification model, obtaining a plurality of first local feature vectors output by the second layer;

inputting the first global feature vector and the plurality of first local feature vectors to a third layer of the identity verification model, comparing the first global feature vector with the second global feature vector, and respectively comparing the plurality of first local feature vectors with the plurality of second local feature vectors to obtain an identity verification result of the first user output by the third layer; the identity verification model comprises the identity repository;

according to one embodiment of the application, the authentication model is trained by:

performing edge detection on the finger vein image sample, determining an interested area corresponding to the finger vein image sample, and performing image enhancement on the finger vein image sample to obtain a first image sample;

performing a data enhancement operation on the first image sample to obtain a plurality of second image samples, wherein the data enhancement operation comprises at least one of image cropping, local filling, image translation and image rotation;

determining a sample training set corresponding to the finger vein image samples based on the plurality of second image samples;

and inputting the sample training set into the identity verification model to be trained for training, and updating model parameters of the identity verification model to obtain the trained identity verification model.

According to an embodiment of the application, the authentication information of the second user is registered in the identity repository by:

acquiring a second finger vein image of the second user;

performing image cutting on the second finger vein image to obtain a plurality of second finger vein subgraphs of different areas, wherein the image cutting strategy of the second finger vein image is determined based on the texture offset degree of the second finger vein image;

acquiring a second global feature vector of the second finger vein image, and acquiring a plurality of second local feature vectors of the plurality of second finger vein subgraphs, wherein the second local feature vectors are in one-to-one correspondence with the second finger vein subgraphs;

storing the mapping relationship between the second global feature vector, the plurality of second local feature vectors and the second user in the identity library.

In a second aspect, the present application provides an authentication apparatus, comprising:

the first acquisition module is used for acquiring a first finger vein image of a first user;

the first processing module is used for carrying out image cutting on the first finger vein image to obtain a plurality of first finger vein subgraphs in different areas, and an image cutting strategy of the first finger vein image is determined based on the texture offset degree of the first finger vein image;

a second obtaining model, configured to obtain a first global feature vector of the first finger vein map, and obtain a plurality of first local feature vectors of the first finger vein subgraphs, where the first local feature vectors correspond to the first finger vein subgraphs one to one;

and the second processing module is used for comparing the first global feature vector and the plurality of first local feature vectors with the authentication information of a second user registered in an identity library to obtain an authentication result of the first user, wherein the authentication information of the second user comprises a second global feature vector and a plurality of second local feature vectors.

According to the identity authentication device, the image is cut according to different areas, the finger vein image is cut into the multiple finger vein subgraphs, then the overall image of the user to be authenticated is compared with the overall image of the registered user, the multiple finger vein subgraphs of the user to be authenticated are compared with the multiple finger vein subgraphs of the registered user, the problem that the finger veins are poor in identification performance under the conditions of rotation and translation is solved, and therefore the accuracy and the efficiency of finger vein identification are improved.

In a third aspect, the present application provides an electronic device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the identity verification method according to the first aspect when executing the computer program.

In a fourth aspect, the present application provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the identity verification method as described above in the first aspect.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a schematic flowchart of an identity authentication method provided in an embodiment of the present application;

fig. 2 is a second schematic flowchart of an authentication method according to an embodiment of the present application;

fig. 3 is a third schematic flowchart of an authentication method according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of an authentication device according to an embodiment of the present application;

fig. 5 is a hardware schematic diagram of an electronic device provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described clearly below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present disclosure.

The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.

The identity authentication method, the identity authentication apparatus, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail below with reference to fig. 1 to 5 through specific embodiments and application scenarios thereof.

As shown in fig. 1, the authentication method provided in the embodiment of the present application includes steps 110 to 140.

Step 110, a first finger vein image of a first user is obtained.

The first user is a user to be authenticated, and the first finger vein map is the finger vein map of the first user.

A first finger vein map of a first user may be acquired by a finger vein collection apparatus.

The finger vein acquisition device can transmit a finger vein sample through infrared light and acquire a finger vein image by using the camera, and can also transmit the finger vein sample through near infrared light and acquire the finger vein image by using the camera.

The finger vein acquisition device for acquiring the first finger vein image of the first user can be a camera provided with an infrared LED lamp, the infrared LED lamp emits infrared rays above a finger, the camera shoots a finger vein image in the other direction of the finger, the finger vein image is acquired from the camera, an ROI sample is obtained after the finger vein image is preprocessed, and the first finger vein image can be acquired after the ROI sample is subjected to data enhancement.

And 120, performing image segmentation on the first finger vein image to obtain a plurality of first finger vein subgraphs of different areas, wherein the image segmentation strategy of the first finger vein image is determined based on the texture offset degree of the first finger vein image.

Image segmentation is a technique that divides an image into several specific regions.

The first finger vein subgraph is a plurality of different first finger vein graph areas obtained after image cutting is carried out on the first finger vein graph; the image cutting strategy is based on different conditions, and a rule of cutting the first finger vein image is determined; the texture deviation degree of the first finger vein image is the deviation degree of the first finger vein image in the horizontal and vertical directions compared with the upright sample.

The erecting sample is a finger vein image obtained by irradiating a finger with near-infrared light and using a CCD camera when the finger is square.

In this embodiment, when image segmentation is performed on the first finger vein image, firstly, image comparison in the horizontal and vertical directions is performed on the first finger vein image and the upright sample, so as to determine the texture offset degree of the first finger vein image, determine an image segmentation strategy of the first finger vein image according to the texture offset degree of the first finger vein image, and perform image segmentation on the first finger vein image according to the determined image segmentation strategy, so as to obtain a plurality of first finger vein subgraphs.

Step 130, obtaining a first global feature vector of the first finger vein map, and obtaining a plurality of first local feature vectors of the plurality of first finger vein subgraphs, wherein the first local feature vectors correspond to the first finger vein subgraphs one to one.

The first global feature vector is a representation of global features of a first finger vein graph of the first user, the first local feature vector is a representation of local features of the first finger vein graph of the first user, and the local features of the first vein subgraph are obtained after cutting according to the cutting rule.

The first finger vein subgraph is also provided with a plurality of first local feature vectors, and the first finger vein subgraph corresponds to the first local feature vectors one to one.

Step 140, comparing the first global feature vector and the plurality of first local feature vectors with the identity authentication information of the second user registered in the identity library to obtain the identity authentication result of the first user, wherein the identity authentication information of the second user comprises the second global feature vector and the plurality of second local feature vectors.

The identity library comprises identity verification information of a plurality of registered users, and the identity verification information comprises a global feature vector and a plurality of local feature vectors corresponding to the registered users.

In this embodiment, after a first global feature vector and a plurality of first local feature vectors of a user whose identity is to be verified are obtained, the first global feature vector and the plurality of first local feature vectors are compared with second user identity verification information in an identity library, wherein the first global feature vector is used for comparison with the second global feature vector, and the first local feature vectors are compared with the second local feature vectors, so that an identity verification result of the first user is determined.

In the related technology, a finger vein feature extraction and identification method based on topographic point classification is provided, finger vein image information of different scales is acquired by using a multi-scale Gaussian filter, the finger vein images of different scales are subjected to image processing to acquire image features, a user to be registered is compared with a registered user through the image features to obtain a finger vein identification result, and the method cannot solve the problem that the performance of the finger vein is poor under rotation and translation, and is low in accuracy and efficiency and high in time complexity.

In the embodiment of the application, a plurality of first finger vein subgraphs are obtained in a sub-region cutting mode, and finger vein identification is performed based on a sub-region mutual matching technology.

In some embodiments, the step 140 of comparing the first global feature vector and the plurality of first local feature vectors with the authentication information of the second user registered in the identity repository to obtain the authentication result of the first user may include:

determining global feature similarity between the first user and the second user based on the first global feature vector and the second global feature vector;

determining a local feature similarity between the first user and the second user based on the plurality of first local feature vectors and the plurality of second local feature vectors;

the global feature similarity is a numerical value describing a degree of similarity between the first global feature vector and the second global feature vector, and the local feature similarity is a numerical value describing a degree of similarity between the first local feature vector and the second local feature vector.

In this embodiment, a first global feature vector and a plurality of first local feature vectors are collectively represented as a set, and a first feature vector set can be obtained

Wherein->

For a first global feature vector>

Is a plurality of first local feature vectors.

The second global feature vector and the plurality of second local feature vectors are collectively represented by a set, so that a set of second feature vectors can be obtained

Wherein->

For a second global feature vector>

A plurality of second local feature vectors.

Will gather S _r And set S _t Calculating cosine similarity to obtain K = { K = { (K) } _G ,K _L }。

Wherein the content of the first and second substances,

the global feature similarity with the highest matching degree between the authentication information of the first user and the authentication information of the second user is determined, and the degree is greater than or equal to>

The local feature similarity is the local feature similarity with the highest matching degree between the authentication information of the first user and the authentication information of the second user, and the second user corresponding to the local feature similarity is the registered user with the highest matching degree with the authentication information of the first user in the identity library.

Wherein M represents that there are M second users in the identity library, N represents the number of sub-regions, distance (·) represents a distance function for measuring the distance between two feature vectors, and cosine similarity is used as the distance function in the present application.

Wherein the cutting strategy of the sub-area is determined by the texture offset degree of the finger vein sample.

For example, as shown in fig. 2, assuming that the width and height of the finger vein sample are w and h respectively, if the deviation degree of the finger vein sample from the vertical sample in the longitudinal and transverse directions is Δ w and Δ h respectively, and 4 sub-regions are selected to be cut, the following sub-regions are cut: l is ₁ (0,0,w-Δw,h-Δh)、L ₂ (Δw,Δh,w-Δw,h-Δh)、L ₃ (Δw,0,w-Δw,h-Δh)、L ₄ (0,. DELTA.h, w-. DELTA.w, h-. DELTA.h). The parenthesis represents the cutting start point coordinate and the region length of the sub-region in the original finger vein image, and the cutting start point coordinate, the cutting start point coordinate and the region length are respectively the X-direction start position, the Y-direction start position, the X-direction width and the Y-direction width.

In actual implementation, because texture offsets generated by different finger vein acquisition devices are different, the coordinates of sub-region cutting and the number of sub-regions can be modified by changing the form of the configuration file, so that sub-regions with different numbers and sizes can be acquired.

In some embodiments, the authentication result of the first user is obtained based on at least one of the global feature similarity and the local feature similarity.

At least one of the representations may be an identity verification result of the first user based on the global feature similarity and the local feature similarity.

In this embodiment, the result may be determined only by the global feature similarity, or may be determined by the global feature similarity and the local feature similarity.

In some embodiments, obtaining the authentication result of the first user based on at least one of the global feature similarity and the local feature similarity comprises:

under the condition that the global feature similarity is larger than a first global threshold, obtaining an identity verification result of the first user as a second user;

or, under the condition that the global feature similarity is smaller than or equal to the first global threshold and larger than the second global threshold, and the local feature similarity is larger than the first local threshold, obtaining the authentication result of the first user as the second user, wherein the second global threshold is smaller than the first global threshold.

The first global threshold is a critical value for measuring global feature similarity, when the global feature similarity of the first user is greater than the first global threshold, the first user finger vein feature is very similar to the second user finger vein feature on the whole, and the authentication result of the first user is the second user.

The second global threshold is also a critical value for measuring the global feature similarity, and the second global threshold is smaller than the first global threshold, when the global feature similarity of the first user is smaller than or equal to the first global threshold and larger than the second global threshold, it indicates that the first user is not very similar to the second user's finger vein feature on the whole at this time, and it needs to consider the additional local feature similarity.

The first local threshold is a critical value for measuring the degree of local feature similarity, and when the global feature similarity of the first user is smaller than or equal to the first global threshold and larger than the second global threshold, and the local feature similarity of the first user is larger than the first local threshold, the authentication result of the first user is also the second user.

In some embodiments, obtaining the authentication result of the first user based on at least one of the global feature similarity and the local feature similarity includes:

or, obtaining the authentication result of the first user as an unregistered user when the local feature similarity is smaller than or equal to the first local threshold.

An unregistered user indicates that the user is not registered in the identity repository prior to authentication, and a matching second user cannot be found in the identity repository.

A specific embodiment is described below to determine whether the first user is a registered second user.

For example, when the first global threshold is 80, the second global threshold is 60, and the first local threshold is 75.

If the global feature similarity of the first user and the second user is 90 and the local feature similarity is 50, at this time, the global feature similarity 90 of the first user and the second user is greater than the first global threshold 80, and the authentication result of the first user is the second user.

If the global feature similarity between the first user and the second user is 70 and the local feature similarity is 85, the identity verification result of the first user is the second user because the global feature similarity 75 between the first user and the second user is smaller than the first global threshold and larger than the second global threshold, and meanwhile, the local feature similarity between the first user and the second user is 85 and larger than the first local threshold.

If the global feature similarity between the first user and the second user is 65 and the local feature similarity is 70, the global feature similarity 75 between the first user and the second user is smaller than the first global threshold and larger than the second global threshold, but the local feature similarity between the first user and the second user is 70 and smaller than the first local threshold, the authentication result of the first user is an unregistered user.

If the global feature similarity of the first user and the second user is 50 and the local feature similarity is 80, because the global feature similarity of the first user and the second user is smaller than the second global threshold at this time, and because the overall similarity of the first user and the second user is too low, the local feature similarity is not concerned at this time, and the authentication result of the first user can be obtained as an unregistered user.

In some embodiments, obtaining a first global feature vector of a first finger vein map and obtaining a plurality of first local feature vectors of a plurality of first finger vein subgraphs comprises:

inputting the first finger vein graph into a first layer of an identity verification model to obtain a plurality of first global feature vectors output by the first layer, and inputting the plurality of first finger vein subgraphs into a second layer of the identity verification model to obtain a plurality of first local feature vectors output by the second layer;

the identity verification model is obtained by training a recognition network by using a plurality of finger vein pattern books.

The identification network can be a mobilenet 1, a ShuffleNet and a mobilefenet, and because the mobilenet 1 identification network and the ShuffleNet identification network adopt an average pooling layer, each unit has the same weight when the finger vein is identified, so that the accuracy of the finger vein identification is reduced.

The mobile faceNet recognition network adopts the global depth convolutional layer to replace the average pooling layer, so that different positions of the finger vein image can have different importance degrees in the finger vein recognition process, and the accuracy of finger vein recognition is improved.

In this embodiment, the authentication model may identify the network for mobilefaceNet.

The first layer of the authentication model is used for obtaining and outputting a first global feature vector of the first finger vein image, and the second layer of the authentication model is used for obtaining and outputting a plurality of first local feature vectors of a plurality of first finger vein subgraphs.

In actual execution, the first finger vein graph is input to a first layer of the identity verification model, the output of the first layer of the identity verification model is obtained to be the first global feature vector, the multiple first finger vein subgraphs are input to a second layer of the identity verification model, and the output of the multiple second layers of the identity verification model is obtained to be the multiple first local feature vectors.

In some embodiments, comparing the first global feature vector and the plurality of first local feature vectors with the authentication information of the second user registered in the identity repository to obtain the authentication result of the first user includes:

inputting the first global feature vector and the plurality of first local feature vectors into a third layer of the identity verification model, comparing the first global feature vector with the second global feature vector, and respectively comparing the corresponding plurality of first local feature vectors with the plurality of second local feature vectors to obtain an identity verification result of the first user output by the third layer;

the authentication model includes an identity repository.

In this embodiment, the third layer of the authentication model includes: the device comprises a global feature similarity calculation module, a local feature similarity calculation module and a comparison module.

The global feature similarity calculation module is used for obtaining global feature similarity between the first user and the user which is most matched in the identity library, and the local feature similarity calculation module is used for obtaining local feature similarity between the first user and the user which is most matched in the identity library.

The comparison module is used for judging the size of the global feature similarity and the first global threshold or the second global threshold and the size of the local feature similarity and the first local threshold, and outputting the identity verification result of the first user based on the judgment result.

In some embodiments, as shown in fig. 3, the authentication model is trained by:

and performing edge detection on the finger vein image sample, determining an interested area corresponding to the finger vein image sample, and performing image enhancement on the finger vein image sample to obtain a first image sample.

The edge detection is based on points with obvious brightness change in the identified finger vein image samples, so that irrelevant information is removed, and important structural attributes of the image are retained, so that the data volume is greatly reduced, and the region of interest is the region which is obtained by removing the irrelevant information from the vein image samples after the edge detection.

There are many operators for edge detection, including loG operator, laplacian operator, canny operator, etc., and in this embodiment, canny operator is used for edge detection.

The image enhancement is to improve the visual effect of an image, purposefully emphasize the whole or local characteristics of the image, change an original unclear image into clear or emphasize some interesting features or regions, enlarge the difference between different object features in the image, and inhibit the uninteresting features, thereby improving the image quality, enriching the information quantity, enhancing the image interpretation and identification effects, and meeting the requirements of some special analyses.

And performing data enhancement on the first image sample to obtain a plurality of second image samples, wherein the data enhancement operation comprises at least one of image cropping, local filling, image translation and image rotation.

The data enhancement is that a plurality of second image samples are transformed based on the first image samples in a geometric transformation mode, so that training data are increased, the generalization capability of the model is improved, and the imbalance of the samples is avoided.

The data enhancement may include only one image cropping, and may also include four types of image cropping, partial filling, image translation, and image selection.

And determining a sample training set corresponding to the finger vein image samples based on the plurality of second image samples.

And inputting the sample training set into the identity verification model to be trained for training, and updating the model parameters of the identity verification model to obtain the trained identity verification model.

In actual implementation, after an original infrared transmission finger vein image is collected, canny edge detection is carried out on the finger vein image, the background of a non-finger vein area in the image is removed, then image enhancement is carried out on the finger vein image through histogram equalization, the texture contrast of the finger vein image is improved, and a first image sample is obtained.

And obtaining a plurality of second image samples through data enhancement based on the obtained first image samples, and obtaining a sample training set corresponding to the finger vein image samples according to the plurality of second image samples.

And then inputting the sample training set into an identity verification model to be trained for training, updating model parameters of the identity verification model, and obtaining the trained identity verification model.

In this embodiment, the identity verification model to be trained selects a mobilefaceNet recognition network, and the loss function uses Arcface.

The Arcface loss function is shown below.

Wherein m is the number of images of a batch in the sample training set, n is the number of classes of samples in the sample training set, y _i Represents the class of the ith sample of the current batch, s is a scaling factor, theta _j η is the set interval size, which is a parameter of class j.

The Arcface loss function is used for evaluating functions of the identity verification model with different degrees of predicted values and real values, and the larger the value of the loss function is, the better the performance of the identity verification model is.

In some embodiments, as shown in fig. 3, the authentication information of the second user is registered in the identity repository by:

and acquiring a second finger vein image of the second user.

The finger vein acquisition device for acquiring the first finger vein image of the second user can be a camera provided with an infrared LED lamp, the infrared LED lamp emits infrared rays above a finger, the camera shoots a finger vein image in the other direction of the finger, the finger vein image is acquired from the camera, an ROI sample is obtained after the finger vein image is preprocessed, and the second finger vein image can be obtained after the ROI sample is subjected to data enhancement.

And performing image segmentation on the second finger vein image to obtain a plurality of second finger vein subgraphs of different areas, wherein the image segmentation strategy of the second finger vein image is determined based on the texture offset degree of the second finger vein image.

When the second finger vein image is subjected to image cutting, firstly, the second finger vein image and the upright sample are subjected to image comparison in the transverse direction and the longitudinal direction, so that the texture offset degree of the second finger vein image is determined, the image cutting strategy of the first finger vein image is determined according to the texture offset degree of the second finger vein image, and the second finger vein image is subjected to image cutting according to the determined image cutting strategy, so that a plurality of second finger vein subgraphs are obtained.

And acquiring a second global feature vector of the second finger vein image, and acquiring a plurality of second local feature vectors of a plurality of second finger vein subgraphs, wherein the second local feature vectors correspond to the second finger vein subgraphs one by one.

By putting the second finger vein map and the second finger vein subgraphs into the identity verification model, a second global feature vector of the second finger vein map and a second local feature vector of the second finger vein subgraphs can be obtained.

And the second local feature vectors correspond to the second finger vein subgraphs one by one.

And storing the mapping relation between the second global feature vector, the plurality of second local feature vectors and the second user in the identity library.

The mapping relation is the corresponding relation between the second user and the second global feature vector and the plurality of second local feature vectors.

In this embodiment, a second user is searched in the identity library, and after the second user is obtained, based on the mapping relationship between the second user and the second global feature vector and the plurality of second local feature vectors, the second global feature vector and the plurality of second local feature vectors corresponding to the second user may be obtained.

Similarly, the second user may also be obtained by searching the identity repository for the second global feature vector and the plurality of second local feature vectors.

The identity authentication method may be applied to the terminal, and may be specifically executed by hardware or software in the terminal.

The terminal includes, but is not limited to, a portable communication device such as a mobile phone or a tablet computer having a touch sensitive surface (e.g., a touch screen display and/or a touch pad). It should also be understood that in some embodiments, the terminal may not be a portable communication device, but rather a desktop computer having a touch-sensitive surface (e.g., a touch screen display and/or touchpad).

In the following various embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and joystick.

In the identity authentication method provided in the embodiment of the present application, an execution subject of the identity authentication method may be an electronic device or a functional module or a functional entity capable of implementing the identity authentication method in the electronic device, the electronic device mentioned in the embodiment of the present application includes, but is not limited to, a mobile phone, a tablet computer, a camera, a wearable device, and the like, and the identity authentication method provided in the embodiment of the present application is described below with the electronic device as the execution subject.

In the identity authentication method provided by the embodiment of the application, the execution subject can be an identity authentication device. In the embodiment of the present application, an authentication method executed by an authentication apparatus is taken as an example to describe the authentication apparatus provided in the embodiment of the present application.

The embodiment of the application also provides an identity authentication device.

As shown in fig. 4, the authentication apparatus includes: a first acquisition module 410, a first processing module 420, a second acquisition module 430, and a second processing module 440.

A first obtaining module 410, configured to obtain a first finger vein map of a first user;

the first processing module 420 is configured to perform image segmentation on the first finger vein map to obtain multiple first finger vein subgraphs of different regions, where an image segmentation policy of the first finger vein map is determined based on a texture offset degree of the first finger vein map;

a second obtaining module 430, configured to obtain a first global feature vector of the first finger vein map, and obtain a plurality of first local feature vectors of the plurality of first finger vein subgraphs, where the first local feature vectors correspond to the first finger vein subgraphs one to one;

the second processing module 440 is configured to compare the first global feature vector and the plurality of first local feature vectors with the authentication information of the second user registered in the identity repository to obtain an authentication result of the first user, where the authentication information of the second user includes the second global feature vector and the plurality of second local feature vectors.

According to the identity authentication device, the images are cut according to different areas, the finger vein graph is cut into a plurality of finger vein subgraphs, then the whole image of the user to be authenticated is compared with the whole image of the registered user, the finger vein subgraphs of the user to be authenticated are compared with the finger vein subgraphs of the registered user, the problem that the finger veins are poor in recognition performance under the conditions of rotation and translation is solved, and therefore the accuracy and the efficiency of finger vein recognition are improved.

In some embodiments, the second processing module 440 is further configured to:

and obtaining an identity verification result of the first user based on at least one of the global feature similarity and the local feature similarity.

In some embodiments, the second processing module 440 is further configured to:

or obtaining the authentication result of the first user as the second user under the condition that the global feature similarity is smaller than or equal to the first global threshold and larger than the second global threshold, and the local feature similarity is larger than the first local threshold, wherein the second global threshold is smaller than the first global threshold.

In some embodiments, the second processing module 440 is further configured to:

In some embodiments, the second obtaining module 430 is further configured to:

inputting the first global feature vector and the plurality of first local feature vectors into a third layer of the identity verification model, comparing the first global feature vector with the second global feature vector, and respectively comparing the plurality of first local feature vectors with the plurality of second local feature vectors to obtain an identity verification result of the first user output by the third layer;

the identity verification model comprises an identity library;

wherein, the identity verification model is trained on finger vein image samples.

In some embodiments, the first obtaining module 410 is configured to:

In some embodiments, the second obtaining module 430 is configured to obtain a second finger vein map of the second user;

the second processing module 440 is configured to perform image segmentation on the second finger vein map to obtain a plurality of second finger vein subgraphs of different areas, where an image segmentation policy of the second finger vein map is determined based on a texture offset degree of the second finger vein map;

the second obtaining module 430 is configured to obtain a second global feature vector of the second finger vein map, and obtain a plurality of second local feature vectors of a plurality of second finger vein subgraphs, where the second local feature vectors correspond to the second finger vein subgraphs one to one;

the second processing module 440 is configured to store the mapping relationship between the second global feature vector, the plurality of second local feature vectors, and the second user in the identity repository.

The identity authentication device in the embodiment of the present application may be an electronic device, or may be a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal, or may be a device other than a terminal. The electronic Device may be, for example, a Mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic Device, a Mobile Internet Device (MID), an Augmented Reality (AR)/Virtual Reality (VR) Device, a robot, a wearable Device, an ultra-Mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the like, and may also be a server, a Network Attached Storage (Network Attached Storage, NAS), a personal computer (NAS), a Television (TV), an assistant, a teller machine, a self-service machine, and the like, and the embodiments of the present application are not limited in particular.

The authentication device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which is not specifically limited in the embodiment of the present application.

The identity authentication device provided in the embodiment of the present application can implement each process implemented by the method embodiments of fig. 1 to 5, and is not described here again to avoid repetition.

In some embodiments, as shown in fig. 5, an electronic device 500 is further provided in an embodiment of the present application, and includes a processor 501, a memory 502, and a computer program stored in the memory 502 and capable of being executed on the processor 501, where the computer program, when executed by the processor 501, implements each process of the above-mentioned embodiment of the identity verification method, and can achieve the same technical effect, and is not described here again to avoid repetition.

It should be noted that the electronic device in the embodiment of the present application includes the mobile electronic device and the non-mobile electronic device described above.

The embodiment of the present application further provides a non-transitory computer-readable storage medium, where a computer program is stored on the non-transitory computer-readable storage medium, and when executed by a processor, the computer program implements each process of the above-mentioned embodiment of the identity verification method, and can achieve the same technical effect, and is not described herein again to avoid repetition.

The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read only memory ROM, a random access memory RAM, a magnetic or optical disk, and the like.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a component of' 8230; \8230;" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element. Further, it should be noted that the scope of the methods and apparatus of the embodiments of the present application is not limited to performing the functions in the order illustrated or discussed, but may include performing the functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application or portions thereof that contribute to the prior art may be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the method according to the embodiments of the present application.

While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.

In the description herein, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.

Claims

1. An identity verification method, comprising:

acquiring a first finger vein image of a first user;

acquiring a first global feature vector of the first finger vein map, and acquiring a plurality of first local feature vectors of the plurality of first finger vein subgraphs, wherein the first local feature vectors correspond to the first finger vein subgraphs one by one;

and comparing the first global feature vector and the plurality of first local feature vectors with the identity verification information of a second user registered in an identity library to obtain an identity verification result of the first user, wherein the identity verification information of the second user comprises a second global feature vector and a plurality of second local feature vectors.

2. The identity authentication method according to claim 1, wherein comparing the first global feature vector and the plurality of first local feature vectors with the identity authentication information of the second user registered in the identity repository to obtain the identity authentication result of the first user comprises:

3. The identity verification method according to claim 2, wherein obtaining the identity verification result of the first user based on at least one of the global feature similarity and the local feature similarity comprises:

4. The identity verification method according to claim 2, wherein obtaining the identity verification result of the first user based on at least one of the global feature similarity and the local feature similarity comprises:

5. The identity verification method of any one of claims 1-4, wherein obtaining the first global feature vector of the first finger vein map and obtaining the plurality of first local feature vectors of the plurality of first finger vein subgraphs comprises:

6. The authentication method according to claim 5, wherein the authentication model is trained by:

7. The authentication method according to claim 1, wherein the authentication information of the second user is registered in the identity repository by:

acquiring a second finger vein image of the second user;

acquiring a second global feature vector of the second finger vein map, and acquiring a plurality of second local feature vectors of the plurality of second finger vein subgraphs, wherein the second local feature vectors correspond to the second finger vein subgraphs one to one;

8. An authentication apparatus, comprising:

a second obtaining module, configured to obtain a first global feature vector of the first finger vein map, and obtain a plurality of first local feature vectors of the plurality of first finger vein subgraphs, where the first local feature vectors correspond to the first finger vein subgraphs one to one;

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

10. A non-transitory computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, is adapted to carry out the authentication method according to any one of claims 1 to 7.