CN111507208A - An authentication method, device, device and medium based on sclera recognition - Google Patents

Abstract

The invention discloses an identity verification method, device, equipment and medium based on sclera recognition. The method obtains the sclera area image in the original eye image of the object to be recognized, and enhances the blood vessel structure in the sclera area image. and extraction to obtain the image information of the blood vessel structure in the scleral area image, based on the neural network model, the feature extraction of the image information of the blood vessel structure is carried out to obtain the characteristic information of the blood vessel structure, and the characteristic information of the scleral blood vessels is classified and identified. The result is authenticated. Or, the image information of the blood vessel structure is compared with the preset sample information of the scleral blood vessel, and the identity verification is performed according to the matching degree of the two. The method retains the overall contour features and the texture differences of details in the feature extraction, so that the blood vessel features can still maintain good recognizability when changing, and at the same time, when classifying and identifying, the scleral blood vessels can be better extracted through the neural network. Characteristics.

Description

An authentication method, device, device and medium based on sclera recognition

technical field

The present invention relates to the field of identity verification, in particular to an identity verification method, device, device and medium based on sclera identification.

Background technique

The identification method based on eye features has the advantages of high accuracy, high reliability, difficult to forge, non-contact and so on. Among them, the sclera, due to its abundant and complex vascular structure on its surface, is affected by genes, has significant differences among different individuals and does not change over time, and its collection requires only ordinary illumination, which reduces application requirements and is an ideal biometric identification. technology. At present, the research on sclera as a biometric identification method is far from enough. Factors such as image acquisition illumination and angle, and non-target area feature interference such as eyelashes and eyelids seriously affect the recognition accuracy.

A typical scleral identification system includes two parts: scleral blood vessel extraction and scleral identification. The scleral blood vessel extraction includes specific steps such as scleral region extraction, blood vessel segmentation, and blood vessel enhancement. With the development of deep learning, there are also methods of blood vessel extraction based on neural networks, but this method is extremely dependent on high-quality labeled datasets. Suitable for practical scenarios.

SUMMARY OF THE INVENTION

The invention provides an identity verification method, device, equipment and medium based on sclera recognition, so that the scleral blood vessels can still be well recognized when external environmental factors change and their own structures are affected, and the robustness of scleral recognition is improved. sex.

In one aspect, the present invention provides an authentication method based on scleral identification, the method comprising:

Obtain the original eye image information of the object to be recognized;

According to the brightness data of the original eye image information, the original eye image information is segmented and image processed to obtain an image of the sclera area;

Performing vascular structure enhancement on the sclera region image to obtain scleral vascular enhancement information;

extracting scleral blood vessels in the scleral blood vessel enhancement information to obtain scleral blood vessel area information;

Based on a preset neural network model, feature extraction is performed on the scleral blood vessel area information to obtain feature information of the scleral blood vessels;

According to the characteristic information of the scleral blood vessel, the identity information of the object to be identified is verified.

Another aspect provides an identity verification device based on sclera recognition, the device comprising: an original image acquisition module, an original image segmentation module, a blood vessel structure enhancement module, a blood vessel region extraction module, a blood vessel feature extraction module, and an identification module;

The original image acquisition module is used to acquire original eye image information;

The original image segmentation module is configured to segment the original eye image information according to the brightness data of the original eye image information to obtain an image of the sclera area;

The vascular structure enhancement module is used to enhance the vascular structure of the sclera region image to obtain scleral vascular enhancement information;

The blood vessel area extraction module is configured to extract the scleral blood vessels in the scleral blood vessel enhancement information to obtain the scleral blood vessel area information;

The blood vessel feature extraction module is configured to perform feature extraction on the information of the scleral blood vessel region according to a preset neural network model to obtain the feature information of the scleral blood vessels;

The identity recognition module is used for verifying the identity information of the object to be recognized according to the characteristic information of the scleral blood vessel.

Another aspect provides an apparatus comprising a processor and a memory, the memory having stored at least one instruction or at least one program, the at least one instruction or the at least one program being loaded by the processor and Executed to realize a scleral recognition-based authentication method as described above.

Another aspect provides a storage medium, the storage medium includes a processor and a memory, the memory stores at least one instruction or at least one program, the at least one instruction or the at least one program is executed by the processor Load and execute to realize the above-mentioned authentication method based on sclera recognition.

The present invention provides an identity verification method, device, device and medium based on sclera recognition, the method obtains the sclera area image in the original eye image of the object to be recognized, and enhances the blood vessel structure in the sclera area image and extraction to obtain the image information of the blood vessel structure in the sclera area image, based on the neural network model, the feature extraction is performed on the image information of the blood vessel structure to obtain the feature information of the blood vessel structure, and the feature information of the scleral blood vessel is classified and identified, according to the classification The result of identification is authenticated. Or, the image information of the blood vessel structure is compared with the preset sample information of the scleral blood vessel, and the identity verification can be performed according to the matching degree of the two. Through the enhancement and extraction of the vascular structure, the method adopts an improved non-learning vascular extraction method to get rid of the dependence on the labeling data set, and retains the overall contour feature and the texture difference of the details in the feature extraction, so that the vascular features change. At the same time, when classifying and identifying, the features of scleral blood vessels can be better extracted by neural network.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a schematic diagram of an application scenario of an authentication method based on sclera recognition provided by an embodiment of the present invention;

FIG. 2 is a flowchart of an authentication method based on sclera identification provided by an embodiment of the present invention;

3 is a flowchart of a method for obtaining an image of a sclera region in an identity verification method based on sclera identification provided by an embodiment of the present invention;

4 is a flowchart of a method for obtaining scleral blood vessel enhancement information in an identity verification method based on sclera identification provided by an embodiment of the present invention;

5 is a flowchart of a method for filtering a vascular structure in an authentication method based on sclera identification provided by an embodiment of the present invention;

6 is a flowchart of a method for obtaining scleral blood vessel area information in an identity verification method based on sclera identification provided by an embodiment of the present invention;

7 is a flowchart of a method for obtaining initial region information of scleral blood vessels in an authentication method based on sclera identification provided by an embodiment of the present invention;

8 is a flowchart of a method for obtaining characteristic information of scleral blood vessels in an authentication method based on sclera identification provided by an embodiment of the present invention;

9 is a schematic structural diagram of a dual-branch neural network in an authentication method based on sclera recognition provided by an embodiment of the present invention;

10 is a schematic structural diagram of a module of an authentication device based on sclera identification provided by an embodiment of the present invention;

FIG. 11 is a schematic diagram of a hardware structure of a device provided by an embodiment of the present invention for implementing the method provided by the embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

In the description of the present invention, it should be understood that the terms "first" and "second" are only used for description purposes, and cannot be interpreted as indicating or implying relative importance or the number of indicated technical features. Thus, a feature defined as "first" or "second" may expressly or implicitly include one or more of that feature. Also, the terms "first," "second," etc. are used to distinguish between similar objects and are not necessarily used to describe a particular order or precedence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein.

Please refer to FIG. 1 , which shows a schematic diagram of an application scenario of an authentication method based on sclera recognition provided by an embodiment of the present invention. The application scenario includes a user 110 , a verification terminal 120 and a server 130 , and the verification terminal 120 collects the user 110 's data. The original eye image is sent to the server 130 for detection. The server 130 processes the original eye image information to obtain an image of the sclera area in the original eye image information. Extraction to obtain the scleral blood vessel area information, and then perform feature extraction on the scleral blood vessel area information to obtain the characteristic information of the scleral blood vessel, according to the comparison result of the characteristic information of the scleral blood vessel and the scleral blood vessel sample information, or to the characteristic information of the scleral blood vessel Perform classification and identification to verify the user's identity information.

In this embodiment of the present invention, the server 110 may include an independently running server, or a distributed server, or a server cluster composed of multiple servers. The server 110 may include a network communication unit, a processor, and memory, among others. Specifically, the server 110 may be used to process the original eye image information to finally obtain the scleral blood vessel area information, and then perform feature extraction on the scleral blood vessel area information to obtain the characteristic information of the scleral blood vessel, according to the characteristic information of the scleral blood vessel and the The comparison result of the scleral blood vessel sample information verifies the user's identity information.

Please refer to FIG. 2, which shows an authentication method based on sclera recognition, which can be applied to the server side, and the method includes:

S210. Obtain the original eye image information of the object to be recognized;

S220. According to the brightness data of the original eye image information, perform segmentation and image processing on the original eye image information to obtain a sclera area image;

Further, referring to FIG. 3 , according to the brightness data of the original eye image information, performing segmentation and image processing on the original eye image information to obtain an image of the sclera region includes:

S310. According to the brightness data of the original eye image information, segment the original eye image information to obtain an initial image of the first sclera region;

S320. Perform an expansion operation on the initial image of the first sclera region to obtain an expanded initial image of the first sclera region;

S330. Perform an erosion operation on the expanded initial image of the first sclera area to obtain an initial image of the second sclera area;

S340. Extract the maximum connected area on the initial image of the second sclera area to obtain an image of the sclera area.

Specifically, the original eye image information is segmented through a clustering algorithm to obtain a non-scleral area and a scleral area. The pixels in the original eye image information after binarization are divided into pixels in the sclera region and pixels in the non-sclera region. In a specific example, the pixels in the original eye image I can be divided by minimizing the following error function It is divided into two categories: scleral region and non-scleral region {C ₀ , C ₁ }.

Ip表示图像I中像素点p的灰度值。in,

Ip represents the gray value of pixel p in image I.

The initial image of the first sclera area obtained by the above method is an image of the sclera area with fractures, voids or discontinuous contour lines. The blood vessels on the sclera surface will divide the complete sclera area into multiple small pieces during the above clustering. Therefore, it is necessary to The morphological operation is performed on the initial image of the first sclera region, that is, the operation method of performing expansion and then corrosion, to obtain an initial image of the second sclera region with a relatively complete image. Perform the expansion operation on the initial image of the first sclera area, that is, the operation of finding the local maximum value, and calculate the maximum value of the pixel points in the area covered by the scleral blood vessels in the initial image of the first sclera area with the fixed anchor point as the center, so that the first sclera area The region with higher brightness in the initial image gradually grows to obtain the initial image of the first sclera region after expansion. Corrosion operation is performed on the initial image of the first scleral region after expansion, that is, the operation of finding the local minimum value, and the minimum value of the pixel points in the initial image of the first scleral region with the fixed anchor point as the center of the scleral blood vessel coverage area is calculated, so that the first The region with higher brightness in the initial image of a scleral region shrinks to obtain an initial image of the second scleral region.

Extracting the maximum connected domain on the initial image of the second sclera region to obtain a convex hull of the maximum connected domain in the initial image of the second sclera region, and the convex hull is the sclera region image. Input the initial image of the second sclera region, initialize the connected domain set Q, for each pixel p in the initial image of the second sclera region, initialize the queue L, if the gray value of the pixel Ip==1 and p has not been marked, the p is put into queue L. Initialize the current connected domain Qi. When L is not empty, take out the first element e of the queue and put it into Qi. For each element m of the four-neighborhood of e, if m==1 and m has not been marked, put m into the queue L. Put Qi into Q, and take out the largest set in Q as the final connected domain Qmax. The convex hull of the maximum connected domain Qmax is obtained using the Graham scanning method, which is the image of the sclera region. When scanning, traverse the entire maximum connected domain from the origin, remove the concave points in the maximum connected domain, and obtain the convex hull of the maximum connected domain Qmax, that is, the sclera region image.

The fractures and voids in the initial image of the first sclera region can be removed after the operations of dilation and erosion, but some voids may remain. A small amount of cavity remains, resulting in a complete image of the sclera area.

S230. Perform vascular structure enhancement on the scleral region image to obtain scleral vascular enhancement information;

Further, referring to FIG. 4 , the scleral blood vessel enhancement information obtained by performing vascular structure enhancement on the scleral region image includes:

S410. Perform image brightness redistribution on the sclera area image to obtain a sclera area image after brightness redistribution;

S420. Filter the blood vessel structure in the scleral region image after brightness redistribution to obtain enhanced information of scleral blood vessels.

Specifically, vascular structure enhancement is performed on the image of the sclera region, the vascular structure is highlighted, and the scleral vascular enhancement information is obtained. The limited contrast adaptive histogram equalization method (CLAHE) can be used for the scleral area image first, and the image brightness of the scleral area image can be redistributed to change the image contrast. Remember that the scleral area image after the brightness redistribution is I _CLAHE .

The CLAHE algorithm performs histogram equalization in a rectangular area around the currently processed pixel to expand the local contrast, display the details of the smooth area, and effectively limit the noise amplification.

Then, the scleral blood vessel texture of the scleral region image I _CLAHE after luminance redistribution is enhanced by Gabor filter to obtain the enhanced information of scleral blood vessels. The Gabor filter can extract the local spatial and frequency domain information of the target to enhance the vascular structure.

Specifically, referring to FIG. 5 , the filtering of the blood vessel structure in the scleral region image after the brightness redistribution is performed to obtain the enhanced information of scleral blood vessels includes:

S510. Filter different angles of the blood vessel structure in the scleral region image after the brightness redistribution, to obtain filtering results of the blood vessel structure at different angles;

S520. Use the maximum filtering result among the filtering results of the blood vessel structures at different angles as scleral blood vessel enhancement information.

Specifically, since blood vessels have multiple directions, it is necessary to filter the blood vessel structures from different angles during the filtering operation, and select the largest filtering result in each angle, that is, the clearest part of the blood vessel structure, as the scleral blood vessel enhancement information output. A typical complex expression for a Gabor filter is as follows:

where (x, y) is the original pixel coordinate, (x', y') is the rotated pixel coordinate, λ is the sine factor wavelength, θ is the angle of the Gabor kernel function, ψ is the phase shift, δ is the standard deviation of the Gaussian function, γ is the spatial aspect ratio, which is used to represent the ellipticity of the Gabor filter. The calculation process of blood vessel enhancement using Gabor filter is as follows:

where I _CLAHE (x, y) is the pixel value at (x, y) position, g(x, y; θ) is a Gabor filter with a specific angle θ, due to the multi-directional nature of blood vessels, it can start at 0 degrees, and each Sub-increment π/8 Gabor filter with eight different angles θ. The maximum value in the Gabor filtering results corresponding to different angles is selected as the enhancement result I _Gabor (x, y) at the (x, y) position.

After the vascular structure is enhanced, the difference between the vascular structure and the background area can be more obvious, so that the image of the blood vessel is clearer, thereby facilitating the subsequent extraction of the blood vessel area, and obtaining a relatively complete image of the blood vessel area with more features.

S240. Extract the scleral blood vessels in the scleral blood vessel enhancement information to obtain scleral blood vessel area information;

Further, referring to FIG. 6 , the scleral blood vessels in the scleral blood vessel enhancement information are extracted, and the obtained scleral blood vessel area information includes:

S610. Determine initial area information of scleral blood vessels in the scleral blood vessel enhancement information according to a preset blood vessel area extraction algorithm;

S620. According to the preset blood vessel scale, match the tubular structures in the initial area information to obtain scleral blood vessel area information.

Specifically, the edge detection enhancement filter Frangi filtering algorithm based on Hessian matrix (Hessian) is used to extract blood vessel features. Firstly, Gaussian smoothing is performed on the image I _Gabor filtered by Gabor, and the Gaussian smoothing parameter σ is the standard deviation. For the linear structure of vessels, the output of the filter is maximum when the scale factor σ best matches the actual width of the vessel.

Specifically, referring to FIG. 7 , the determination of the initial region information of the scleral blood vessels in the scleral blood vessel enhancement information according to the preset blood vessel region extraction algorithm includes:

S710. Calculate the tubular feature parameter of each pixel in the scleral blood vessel enhancement information according to a preset blood vessel region extraction algorithm;

S720. Classify the pixels in the scleral blood vessel enhancement information according to the tubular feature parameter of each pixel to obtain initial area information of the scleral blood vessel.

Specifically, under the current scale σ, the second-order partial derivatives G _xx , G _xy and G _yy of each pixel point p in the two directions of x and y in the image I _Gabor after blood vessel enhancement are calculated.

Using the second-order partial derivatives G _xx , G _xy and G _yy to convolve the image I _Gabor to get:

I _xx =G _xx *I _E

I _xy =G _xy *I _E

I _yy =G _yy *I _E

Use I _xx , I _xy and I _yy to form an image Hessian matrix

Calculate the eigenvalues λ ₁ and λ ₂ of the Hessian matrix (let λ ₁ be the smaller absolute value), and construct the variables R _b and S:

The blood vessel area in the sclera is a tubular structure, and the response value of the second-order Gaussian derivative is relatively large. The background of the eye sclera is a uniform part, and the response value of the second-order Gaussian derivative is relatively small. Therefore, the eigenvalues of the Hessian matrix at the blood vessel points are large and small, the eigenvalues of the Hessian matrix at the blood vessel intersections are both large, and the eigenvalues of the Hessian matrix at the background points are both very small, which can distinguish the background area and the blood vessel area. .

Therefore, the responsivity function of the vascular region in the scleral vascular enhancement information is:

where β is used to adjust and distinguish the sensitivity of the blocky structure in the background region and the tubular structure in the blood vessel region, and c affects the overall smoothness of the filtered image. The response function of pixel p belonging to the blood vessel region under multi-scale is:

Through the edge detection enhancement filtering Frangi filtering algorithm based on Hessian matrix, the pixels with tubular characteristics in the enhanced membrane vessel information can be obtained. Therefore, the pixels belonging to the vessel area in the enhanced scleral vessel information can be extracted to form the information of the scleral vessel area.

S250. Based on a preset neural network model, feature extraction is performed on the scleral blood vessel area information to obtain feature information of the scleral blood vessels;

Further, referring to FIG. 8 , the feature extraction is performed on the information of the scleral blood vessel region based on the preset neural network model, and the obtained feature information of the scleral blood vessel includes:

S810. Perform multi-scale feature extraction on the scleral blood vessel area information to obtain blood vessel contour distribution feature information in different dimensions;

S820. Perform feature fusion on the blood vessel contour distribution feature information of different dimensions to obtain fusion feature information of scleral blood vessels;

S830. Perform dimensionality reduction on the fusion feature information of the scleral blood vessels to obtain the feature information of the scleral blood vessels.

Specifically, the neural network model constructs a neural network structure with dual branches (stem branch and leaf branch), as shown in Figure 9. Before the network is branched, multi-layer convolution is used to extract the initial layer features, which reduces the dimension of branch features and thus reduces the amount of network computation.

Stem branch is a multi-scale feature extractor, which is stacked by multiple convolutional structures, which can extract the distribution features of blood vessel contours at different levels within the information of the scleral blood vessel region. The length can be 1 and 2 respectively, and the output dimension is reduced to half of the input feature dimension.

由茎分支第l层的茎特征

和叶分支第l-1层的聚合特征为

经聚合操作得到：As a multi-layer fusion device, the leaf branch can enhance the fusion of the overall contour information and the local detail feature of the blood vessel contour distribution feature information of different dimensions through the aggregation operation. Aggregated features at layer l of leaf branches

Stem features of layer l branched from stem

The aggregated features of layer l-1 of the leaf branch are

After the aggregation operation, we get:

为聚合操作，

经最大池化降低维度，后送入1×1卷积得到与

维度相同的特征，将其与

合并，完成聚合操作。in

for the aggregation operation,

The dimension is reduced by maximum pooling, and then sent to 1×1 convolution to obtain the

features of the same dimension, compare it with

Merge to complete the aggregation operation.

S260. Verify the identity information of the object to be identified according to the characteristic information of the scleral blood vessel.

作为巩膜血管结构的高维特征，送入由全连接层和softmax层组成的分类器完成巩膜识别。

经全连接层

后经过降维操作被整合重排列为一维向量，后使用softmax分类器获得最后的分类结果T：Specifically, the top-level features of the dual-branch network are

As a high-dimensional feature of the scleral vascular structure, it is sent to a classifier composed of a fully connected layer and a softmax layer to complete the sclera identification.

fully connected layer

After the dimensionality reduction operation, it is integrated and rearranged into a one-dimensional vector, and then the softmax classifier is used to obtain the final classification result T:

The classification result T is the category of the characteristic information of the scleral blood vessel, and the characteristic of the scleral blood vessel can be identified according to the obtained classification result, so as to verify the identity information of the object to be identified.

The regional information of the scleral blood vessels can also be compared with the preset scleral sample information, and the identity information of the object to be identified is verified according to the size of the matching degree.

The embodiment of the present invention provides an identity verification method based on sclera recognition. The method obtains the sclera region image in the original eye image of the object to be recognized, and enhances and extracts the blood vessel structure in the sclera region image. The image information of the blood vessel structure in the image of the sclera area, based on the neural network model, the image information of the blood vessel structure is feature extraction, the feature information of the blood vessel structure is obtained, the feature information of the scleral blood vessel is classified and identified, and the classification and identification results are carried out. Authentication. Or the image information of the blood vessel structure is compared with the preset sample information of the scleral blood vessel, and the identity verification can be performed according to the matching degree of the two. The method can get rid of the dependence on the labeling data set, and retain the overall contour features and the texture differences of the details in the feature extraction, so that the blood vessel features can still maintain good recognizability when they change. Neural network for better vessel feature extraction.

An embodiment of the present invention also provides an identity verification device based on sclera identification, see FIG. 10 , the device includes: an original image acquisition module 1010 , an original image segmentation module 1020 , a blood vessel structure enhancement module 1030 , and a blood vessel region extraction module 1040 , a blood vessel feature extraction module 1050 and an identity recognition module 1060;

The original image acquisition module 1010 is used to acquire original eye image information;

The original image segmentation module 1020 is configured to segment the original eye image information according to the brightness data of the original eye image information to obtain a sclera region image;

The vascular structure enhancement module 1030 is configured to enhance the vascular structure of the scleral region image to obtain scleral vascular enhancement information;

The blood vessel region extraction module 1040 is configured to extract the scleral blood vessels in the scleral blood vessel enhancement information to obtain the scleral blood vessel region information;

The blood vessel feature extraction module 1050 is configured to perform feature extraction on the scleral blood vessel region information based on a preset neural network model to obtain feature information of the scleral blood vessels;

The identity recognition module 1060 is configured to verify the identity information of the object to be recognized according to the characteristic information of the scleral blood vessel.

The apparatuses provided in the above embodiments can execute the methods provided in any of the embodiments of the present invention, and have corresponding functional modules and beneficial effects for executing the methods. For technical details not described in detail in the foregoing embodiments, reference may be made to an authentication method based on scleral identification provided by any embodiment of the present invention.

This embodiment also provides a computer-readable storage medium, where computer-executable instructions are stored in the storage medium, and the computer-executable instructions are loaded by a processor to execute the above-mentioned scleral identification-based identity in this embodiment Authentication method.

This embodiment also provides a device, the device includes a processor and a memory, wherein the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute the above-mentioned one in this embodiment. An authentication method based on scleral recognition.

The device may be a computer terminal, a mobile terminal, or a server, and the device may also participate in forming the apparatus or system provided by the embodiments of the present invention. As shown in FIG. 11 , the server 11 (or the computer terminal 11 or the mobile terminal 11 ) may include one or more processors 1102 (the processor 1102 may include but Not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1104 for storing data, and a transmission device 1106 for a communication function. In addition, it may also include: a display, an input/output interface (I/O interface), a network interface, a power supply, and/or a camera. Those of ordinary skill in the art can understand that the structure shown in FIG. 11 is only a schematic diagram, which does not limit the structure of the above-mentioned electronic device. For example, the server 11 may also include more or fewer components than that shown in FIG. 11 , or have a different configuration than that shown in FIG. 11 .

It should be noted that the one or more processors 1102 and/or other data processing circuits described above may generally be referred to herein as "data processing circuits." The data processing circuit may be embodied in whole or in part as software, hardware, firmware or any other combination. Furthermore, the data processing circuit may be a single independent processing module, or integrated in whole or in part into any of the other elements in the server 11 (or computer terminal). As referred to in the embodiments of the present application, the data processing circuit acts as a kind of processor control (eg, selection of a variable resistance termination path connected to an interface).

The memory 1104 can be used to store software programs and modules of the application software, such as program instructions/data storage devices corresponding to the methods described in the embodiments of the present invention, the processor 1102 executes the software programs and modules stored in the memory 1104 by running the software programs and modules. Various functional applications and data processing are implemented to realize the above-mentioned method for generating time-series behavior capture frames based on self-attention network. Memory 1104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, memory 1104 may further include memory located remotely from processor 1102, which may be connected to server 11 through a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

Transmission means 1106 is used to receive or transmit data via a network. The specific example of the above-mentioned network may include the wireless network provided by the communication provider of the server 11 . In one example, the transmission device 1106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through the base station so as to communicate with the Internet. In one example, the transmission device 1106 may be a radio frequency (Radio Frequency, RF) module, which is used for wirelessly communicating with the Internet.

The display may be, for example, a liquid crystal display (LCD) of the touch screen type which enables the user to interact with the user interface of the server 11 (or computer terminal).

This specification provides method operation steps as described in the embodiments or flow charts, but more or less operation steps may be included based on routine or non-creative work. The steps and sequences listed in the embodiments are only one way of execution sequence of many steps, and do not represent the only execution sequence. When an actual system or interrupt product is executed, the methods shown in the embodiments or the accompanying drawings may be executed sequentially or in parallel (eg, a parallel processor or a multi-threaded processing environment).

The structure shown in this embodiment is only a part of the structure related to the solution of the present application, and does not constitute a limitation on the equipment to which the solution of the present application is applied. The specific device may include more or more than shown. Fewer components, or combining some components, or having a different arrangement of components. It should be understood that the methods, apparatuses, etc. disclosed in this embodiment may be implemented in other manners. For example, the device embodiments described above are only illustrative. For example, the division of the modules is only a division of a logical function. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection of devices or unit modules through some interfaces.

Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes.

Those skilled in the art may further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of the two. Interchangeability, the above description has generally described the components and steps of each example in terms of function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions described in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. An identity verification method based on sclera identification, characterized in that the method comprises: Obtain the original eye image information of the object to be recognized; Performing segmentation and image processing on the original eye image information according to the brightness data of the original eye image information to obtain an image of the sclera area; Performing vascular structure enhancement on the sclera region image to obtain scleral vascular enhancement information; extracting scleral blood vessels in the scleral blood vessel enhancement information to obtain scleral blood vessel area information; Based on a preset neural network model, feature extraction is performed on the scleral blood vessel area information to obtain feature information of the scleral blood vessels; According to the characteristic information of the scleral blood vessel, the identity information of the object to be identified is verified. 2 . The identity verification method based on sclera recognition according to claim 1 , wherein, according to the brightness data of the original eye image information, the original eye image information is segmented and image processed to obtain 2 . Scleral region images include: segmenting the original eye image information according to the brightness data of the original eye image information to obtain an initial image of the first sclera region; performing an expansion operation on the initial image of the first sclera region to obtain an initial image of the first sclera region after expansion; performing an etching operation on the expanded initial image of the first sclera region to obtain an initial image of the second sclera region; Extracting the maximum connected area on the initial image of the second sclera area to obtain an image of the sclera area. 3 . The identity verification method based on sclera identification according to claim 1 , wherein the vascular structure enhancement is performed on the sclera region image to obtain sclera vascular enhancement information comprising: 4 . performing image brightness redistribution on the sclera area image to obtain a sclera area image after brightness redistribution; The blood vessel structure in the scleral region image after the brightness redistribution is filtered to obtain scleral blood vessel enhancement information. 4 . The identity verification method based on sclera identification according to claim 3 , wherein the filtering of the blood vessel structure in the sclera region image after the brightness redistribution is performed to obtain the sclera blood vessel enhancement information comprises: 5 . Filtering different angles of the blood vessel structure in the scleral region image after the brightness redistribution, to obtain the filtering results of the blood vessel structure at different angles; The maximum filtering result among the filtering results of the blood vessel structures at different angles is used as the scleral blood vessel enhancement information. 5 . The identity verification method based on sclera identification according to claim 1 , wherein the extracting the scleral blood vessels in the scleral blood vessel enhancement information to obtain the scleral blood vessel area information comprises: 6 . determining the initial region information of the scleral blood vessels in the scleral blood vessel enhancement information according to a preset blood vessel region extraction algorithm; According to the preset blood vessel scale, the tubular structures in the initial area information are matched to obtain the scleral blood vessel area information. 6 . The identity verification method based on sclera identification according to claim 5 , wherein, according to a preset blood vessel region extraction algorithm, determining the initial region information of scleral blood vessels in the scleral blood vessel enhancement information includes: 6 . : Calculate the tubular feature parameter of each pixel in the scleral blood vessel enhancement information according to a preset blood vessel region extraction algorithm; According to the tubular feature parameter of each pixel, the pixels in the scleral blood vessel enhancement information are classified to obtain the initial area information of the scleral blood vessel. 7 . The identity verification method based on sclera identification according to claim 1 , wherein, based on a preset neural network model, feature extraction is performed on the scleral blood vessel area information to obtain the feature information of the scleral blood vessels. 8 . include: Perform multi-scale feature extraction on the scleral blood vessel area information to obtain blood vessel contour distribution feature information in different dimensions; Perform feature fusion on the blood vessel contour distribution feature information of different dimensions to obtain fusion feature information of scleral blood vessels; Dimensionality reduction is performed on the fusion feature information of the scleral blood vessels to obtain scleral blood vessel feature information. 8. An identity verification device based on sclera recognition, characterized in that the device comprises: an original image acquisition module, an original image segmentation module, a blood vessel structure enhancement module, a blood vessel region extraction module, a blood vessel feature extraction module and an identity recognition module; The original image acquisition module is used to acquire original eye image information; The original image segmentation module is configured to segment the original eye image information according to the brightness data of the original eye image information to obtain an image of the sclera area; The vascular structure enhancement module is used to enhance the vascular structure of the sclera region image to obtain scleral vascular enhancement information; The blood vessel area extraction module is configured to extract the scleral blood vessels in the scleral blood vessel enhancement information to obtain the scleral blood vessel area information; The blood vessel feature extraction module is configured to perform feature extraction on the information of the scleral blood vessel region based on a preset neural network model to obtain the feature information of the scleral blood vessel; The identity recognition module is used for verifying the identity information of the object to be recognized according to the characteristic information of the scleral blood vessel. 9. A device, characterized in that the device comprises a processor and a memory, wherein the memory stores at least one instruction or at least a piece of program, and the at least one instruction or the at least one piece of program is loaded by the processor And execute to realize an authentication method based on sclera identification according to any one of claims 1-7. 10. A storage medium, characterized in that the storage medium comprises a processor and a memory, the memory stores at least one instruction or at least a piece of program, and the at least one instruction or the at least one piece of program is processed by the The device is loaded and executed to realize an authentication method based on sclera recognition according to any one of claims 1-7.

Images