Finger vein recognition method, device, module and medium

Abstract

The present invention belongs to the field of finger vein recognition and relates to data analysis technology. It is used to solve the problem that the existing finger vein recognition method needs to compare the authentication image with the finger vein images of all legal users stored in the database one by one, resulting in low authentication efficiency. It specifically refers to a vein recognition method, device, module and medium, including a base, the surface of which is provided with an active light source, a processor and an image sensor, the base is fixedly mounted with a lens through a fixing seat, and a filter is arranged in the lens; the processor is communicatively connected with an image acquisition module, a feature comparison module, an image comparison module and a storage module; the image acquisition module is used to acquire the finger vein image of the user; the present invention can acquire the finger vein image of the user, collect the finger vein image by near-infrared light irradiation and an image sensor, and then extract features of the finger vein image to provide data support for the feature comparison process.

Description

Technical Field

[0001] The present invention belongs to the field of finger vein recognition and relates to data analysis technology, specifically to a vein recognition method, device, module and medium. Background Art

[0002] Finger vein recognition is a technology that uses finger vein images for identity recognition. It uses the vein pattern image obtained after near-infrared rays penetrate the finger to perform personal recognition. It is the world's most advanced biometric recognition technology with high precision and high speed.

[0003] When performing identification and authentication, the existing finger vein recognition method needs to compare the authentication image with the finger vein images of legitimate users stored in the database one by one. This comparison method is inefficient, and all finger vein images need to be retrieved for comparison during each identity authentication. Once the system is attacked by a network attack, all finger vein images are at risk of leakage, posing a great security risk.

[0004] Please propose a solution to the above technical problems. Summary of the invention

[0005] The purpose of the present invention is to provide a finger vein recognition method, device, module and medium, which are used to solve the problem that the existing finger vein recognition method needs to compare the authentication image with the finger vein images of all legitimate users stored in the database one by one, resulting in low authentication efficiency;

[0006] The technical problem to be solved by the present invention is: how to provide a finger vein recognition method, device, module and medium for efficient authentication.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] The finger vein recognition device comprises a base, an active light source, a processor and an image sensor are arranged on the surface of the base, a lens is fixedly mounted on the base through a fixing seat, and a filter is arranged in the lens;

[0009] The processor is communicatively connected to an image acquisition module, a feature comparison module, an image comparison module and a storage module;

[0010] The image acquisition module is used to acquire the finger vein image of the user: when entering identity information, the active light source is turned on, and the light of the active light source passes through the filter to generate near-infrared light with a wavelength of 960nm. After the near-infrared light is absorbed by the finger vein, the finger vein image is acquired through the image sensor, and the acquired finger vein image is feature extracted to obtain area data, trunk data, branch data and angle data. The area data, trunk data, branch data and angle data constitute feature parameters of the finger vein image, and the finger vein image is matched with the feature parameters and sent to the storage module through the processor for storage;

[0011] The feature comparison module is used to perform feature comparison analysis when authenticating a user: when authenticating a user, the active light source is turned on and the finger vein image of the user is obtained through the image sensor, the finger vein image of the user is marked as an authentication image, and feature extraction is performed on the authentication image to obtain area data, trunk data, branch data and angle data, all feature parameters are retrieved through the storage module, and the authentication image and the feature parameters are compared in area;

[0012] The image comparison module is used to perform image comparison analysis when authenticating a user.

[0013] As a preferred embodiment of the present invention, the area data is the area value of the finger vein in the finger vein image, the trunk data is the number value of the main veins in the finger vein image, the branch data is the number value of the branch veins in the finger vein image, and the angle data is the maximum value of the angle between the branch vein and the trunk vein in the vein image.

[0014] As a preferred embodiment of the present invention, the specific process of performing area comparison between the authentication image and the feature parameters includes: marking the absolute value of the difference between the area data of the authentication image and the area data in the feature parameters as a face difference value, obtaining the face difference threshold through the storage module, and comparing the face difference value with the face difference threshold: if the face difference value is less than the face difference value, marking the corresponding feature parameter as a preliminary parameter; if the face difference value is greater than or equal to the face difference threshold, marking the corresponding feature parameter as an invalid parameter; performing feature comparison between the authentication image and the preliminary parameters.

[0015] As a preferred embodiment of the present invention, the specific process of feature comparison between the authentication image and the preliminary parameters includes: marking the absolute value of the difference between the trunk data of the authentication image and the trunk data of the preliminary parameters as the main difference ZC, marking the absolute value of the difference between the branch data of the authentication image and the branch data of the preliminary parameters as the branch difference FC, marking the absolute value of the difference between the angle data of the authentication image and the angle data of the preliminary parameters as the angle difference JC; obtaining the deviation coefficient PC of the preliminary parameters by numerically calculating the main difference ZC, the branch difference FC and the angle difference JC; marking the preliminary parameters as secondary parameters or invalid parameters through the deviation coefficient PC.

[0016] As a preferred embodiment of the present invention, the specific process of the image comparison and analysis performed by the image comparison module during identity authentication includes: retrieving the finger vein image corresponding to the secondary parameter through the storage module and marking it as the analysis image, and performing image comparison between the authentication image and the analysis image one by one: enlarging the authentication image and the analysis image into pixel grid images and performing grayscale transformation, marking the pixel grids as ordinary grids or vein grids through a binary method, and then overlapping the authentication image and the analysis image to obtain the marking status of the pixel grids at the same position in the authentication image and the analysis image: if the pixel grids at the same position are marked as ordinary grids or vein grids in both the authentication image and the analysis image, the pixel grids at the corresponding position are marked as unified grids; otherwise, the pixel grids at the corresponding position are marked as bifurcated grids; the ratio of the number of unified grids to the number of pixel grids in the analysis image is marked as a unified coefficient, and the analysis image is marked as a matching image or an invalid image through the unified coefficient. After all the analysis images are compared with the authentication image, the number of matching images is obtained and whether the image authentication is successful is determined by the number of matching images.

[0017] As a preferred embodiment of the present invention, the specific process of marking the analysis image as a matching image or an invalid image includes: obtaining a unified threshold through a storage module, and comparing the unified coefficient with the unified threshold: if the unified coefficient is greater than or equal to the unified threshold, the corresponding analysis image is marked as a matching image; if the unified coefficient is less than the unified threshold, the corresponding analysis image is marked as an invalid image.

[0018] As a preferred embodiment of the present invention, the specific process of determining whether image authentication is successful includes: if the number of matching objects is one, the image comparison is determined to be successful, the identity information of the corresponding matching object is matched with the authenticated user, and an authentication success signal is generated and sent to the processor; if the number of matching objects is greater than one, the image comparison is determined to be successful, the identity information of the matching object with the largest unified coefficient value is matched with the authenticated user, and an authentication success signal is generated and sent to the processor; if the number of matching objects is zero, the image comparison is determined to be failed, an authentication failure signal is generated and sent to the processor.

[0019] The finger vein recognition method comprises the following steps:

[0020] Step 1: Obtain the user's finger vein image: When entering identity information, turn on the active light source. The light of the active light source passes through the filter to generate near-infrared light with a wavelength of 960nm. After the near-infrared light is absorbed by the finger vein, the finger vein image is collected through the image sensor, and the feature parameters are obtained by extracting the feature of the finger vein image.

[0021] Step 2: Perform feature comparison analysis during identity authentication: When the authenticating user performs identity authentication, the active light source is turned on and the user's finger vein image is obtained through the image sensor, the user's finger vein image is marked as the authentication image, the feature parameters are marked as invalid parameters or preliminary parameters through area comparison, and the authentication image is feature compared with the preliminary parameters and the preliminary parameters are marked as invalid parameters or secondary parameters;

[0022] Step 3: Perform image comparison and analysis during identity authentication: retrieve the finger vein image corresponding to the secondary parameter through the storage module and mark it as the analysis image, compare the authentication image with the analysis image one by one, and mark the analysis image as a matching image or an invalid image based on the comparison result, and determine whether the image comparison is successful based on the number of matching images.

[0023] The finger vein recognition module includes an active light source, a lens, a filter and an image sensor. The image sensor is electrically connected to the processor through a wire.

[0024] A computer storage medium stores a computer program, which implements a finger vein recognition method when executed by a processor.

[0025] The present invention has the following beneficial effects:

[0026] 1. The image acquisition module can acquire the user's finger vein image, collect the finger vein image through near-infrared light irradiation and image sensor, and then extract the features of the finger vein image to provide data support for the feature comparison process;

[0027] 2. The feature comparison module can be used to perform feature comparison analysis during identity authentication. First, the feature parameters are preliminarily screened through the area comparison results, and then the preliminarily selected parameters are further screened through the feature comparison results, thereby reducing the number of finger vein image comparisons, improving authentication efficiency, and reducing the risk of finger vein image leakage when the system is attacked;

[0028] 3. The image comparison module can be used to perform image comparison and analysis during identity authentication. The finger vein image can be segmented by combining image processing technology. The characteristic parameters of successful authentication are then extracted through the proportion of overlapping pixels in the finger vein image. After completing the initial screening and secondary screening, the final authentication analysis is performed through image comparison to improve the security of system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 is a system block diagram of Embodiment 1 of the present invention;

[0031] Figure 2 This is a flow chart of the method of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0032] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Embodiment 1

[0034] like Figure 1 As shown, the finger vein recognition device includes a base, an active light source, a processor and an image sensor are arranged on the surface of the base, a lens is fixedly mounted on the base through a fixing seat, and a filter is arranged in the lens.

[0035] The processor is communicatively connected with the image acquisition module, the feature comparison module, the image comparison module and the storage module.

[0036] The image acquisition module is used to acquire the user's finger vein image: when entering identity information, the active light source is turned on, and the light of the active light source generates near-infrared light with a wavelength of 960nm after passing through the filter. After the near-infrared light is absorbed by the finger vein, the finger vein image is collected through the image sensor, and the collected finger vein image is feature extracted to obtain area data, trunk data, branch data and angle data. The area data, trunk data, branch data and angle data constitute the feature parameters of the finger vein image, and the finger vein image is matched with the feature parameters and sent to the storage module through the processor for storage; the area data is the area value of the finger vein in the finger vein image, the trunk data is the number value of the trunk vein in the finger vein image, the branch data is the number value of the branch vein in the finger vein image, and the angle data is the maximum value of the angle between the branch vein and the trunk vein in the vein image; the user's finger vein image is acquired, the finger vein image is collected by near-infrared light irradiation and the image sensor, and then the finger vein image is feature extracted to provide data support for the feature comparison process.

[0037] The feature comparison module is used to perform feature comparison analysis when the authenticated user is authenticated: when the authenticated user is authenticated, the active light source is turned on and the user's finger vein image is obtained through the image sensor, the user's finger vein image is marked as the authentication image, and the feature extraction is performed on the authentication image to obtain area data, trunk data, branch data and angle data. All feature parameters are retrieved through the storage module, and the authentication image and feature parameters are compared in area: the absolute value of the difference between the area data of the authentication image and the area data in the feature parameter is marked as the face difference value, the face difference threshold is obtained through the storage module, and the face difference value is compared with the face difference threshold: if the face difference value is less than the face difference value, the corresponding feature parameter is marked as the preliminary parameter; if the face difference value is greater than or equal to the face difference threshold, the corresponding feature parameter is marked as an invalid parameter; the authentication image and the preliminary parameter are compared in features: the absolute value of the difference between the trunk data of the authentication image and the trunk data of the preliminary parameter is marked as the main difference value ZC, and the absolute value of the difference between the branch data of the authentication image and the branch data of the preliminary parameter is marked as the branch difference value FC, the absolute value of the difference between the angle data of the authentication image and the angle data of the preliminary parameters is marked as the angle difference JC; the deviation coefficient PC of the preliminary parameters is obtained by the formula PC=α1*ZC+α2*FC+α3*JC, where α1, α2 and α3 are all proportional coefficients, and α1>α2>α3>1; the deviation threshold PCmax is obtained through the storage module, and the deviation coefficient PC of the preliminary parameters is compared with the deviation threshold PCmax: if the deviation coefficient PC is less than the deviation threshold PCmax, it is determined that the feature comparison of the preliminary parameters is successful, and the corresponding preliminary parameters are marked as secondary parameters; if the deviation coefficient PC is greater than or equal to the deviation threshold PCmax, it is determined that the feature comparison of the preliminary parameters fails, and the corresponding preliminary parameters are marked as invalid parameters; during identity authentication, feature comparison analysis is performed, firstly, the feature parameters are preliminarily screened through the area comparison results, and then the preliminary parameters are further screened through the feature comparison results, so as to reduce the number of comparisons of the finger vein image, improve the authentication efficiency, and reduce the risk of leakage of the finger vein image when the system is attacked.

[0038] The image comparison module is used to perform image comparison and analysis when authenticating a user: retrieve the finger vein image corresponding to the secondary parameter through the storage module and mark it as the analysis image, and compare the authentication image with the analysis image one by one: enlarge the authentication image and the analysis image into pixel grid images and perform grayscale transformation, mark the pixel grid as an ordinary grid or a vein grid through the binary method, and then overlap the authentication image with the analysis image to obtain the marking status of the pixel grid at the same position in the authentication image and the analysis image: if the pixel grid at the same position is marked as an ordinary grid or a vein grid in both the authentication image and the analysis image, the pixel grid at the corresponding position is marked as a unified grid; otherwise, the pixel grid at the corresponding position is marked as a bifurcated grid; the ratio of the number of unified grids to the number of pixel grids in the analysis image is marked as a unified coefficient, and a unified threshold is obtained through the storage module, and the unified coefficient is compared with the unified threshold: if the unified coefficient is greater than or equal to the unified threshold, the corresponding analysis image is marked as a matching image; if the unified coefficient is less than the unified threshold, the The corresponding analysis image is marked as an invalid image; after all the analysis images are compared with the authentication image, the number of matching images is obtained: if the number of matching objects is one, the image comparison is determined to be successful, and the identity information of the corresponding matching object is matched with the authentication user, and an authentication success signal is generated and sent to the processor; if the number of matching objects is greater than one, the image comparison is determined to be successful, and the identity information of the matching object with the largest unified coefficient value is matched with the authentication user, and an authentication success signal is generated and sent to the processor; if the number of matching objects is zero, the image comparison is determined to be unsuccessful, and an authentication failure signal is generated and sent to the processor; during identity authentication, image comparison and analysis are performed, and the finger vein image is segmented in combination with image processing technology, and then the feature parameters of successful authentication are extracted through the proportion of overlapping pixel grids in the finger vein image, and after completing the initial screening and secondary screening, the final authentication analysis is performed through image comparison to improve the safety of system operation.

[0039] Embodiment 2

[0040] like Figure 2 As shown, the finger vein recognition method includes the following steps:

[0041] Step 1: Obtain the user's finger vein image: When entering identity information, turn on the active light source. The light of the active light source passes through the filter to generate near-infrared light with a wavelength of 960nm. After the near-infrared light is absorbed by the finger vein, the finger vein image is collected through the image sensor, and the feature parameters are obtained by extracting the feature of the finger vein image.

[0042] Step 2: Perform feature comparison analysis during identity authentication: When the authenticating user performs identity authentication, the active light source is turned on and the user's finger vein image is obtained through the image sensor, the user's finger vein image is marked as the authentication image, the feature parameters are marked as invalid parameters or preliminary parameters through area comparison, and the authentication image is feature compared with the preliminary parameters and the preliminary parameters are marked as invalid parameters or secondary parameters;

[0043] Step 3: Perform image comparison and analysis during identity authentication: retrieve the finger vein image corresponding to the secondary parameter through the storage module and mark it as the analysis image, compare the authentication image with the analysis image one by one, and mark the analysis image as a matching image or an invalid image based on the comparison result, and determine whether the image comparison is successful based on the number of matching images.

[0044] The finger vein recognition method, device, module and medium are used for inputting identity information. When working, the active light source is turned on. The light of the active light source passes through the filter to generate near-infrared light with a wavelength of 960nm. After the near-infrared light is absorbed by the finger vein, the finger vein image is collected by the image sensor, and the feature parameters are extracted from the finger vein image. When the authenticated user performs identity authentication, the active light source is turned on and the finger vein image of the user is obtained by the image sensor, the finger vein image of the user is marked as an authentication image, the feature parameters are marked as invalid parameters or preliminary parameters by area comparison, the authentication image is compared with the preliminary parameters, and the preliminary parameters are marked as invalid parameters or secondary parameters. The finger vein image corresponding to the secondary parameters is retrieved by the storage module and marked as an analysis image, the authentication image and the analysis image are compared one by one, and the analysis image is marked as a matching image or an invalid image by the comparison result, and whether the image comparison is successful is determined by the number of matching images.

[0045] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0046] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula PC=α1*ZC+α2*FC+α3*JC; technicians in this field collect multiple groups of sample data and set corresponding deviation coefficients for each group of sample data; substitute the set deviation coefficients and the collected sample data into the formula, any three formulas constitute a three-variable linear equation group, screen the calculated coefficients and take the average, and obtain the values ​​of α1, α2 and α3 as 3.53, 2.82 and 2.49 respectively;

[0047] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the technical personnel in this field preliminarily set the corresponding deviation coefficient for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value, such as the deviation coefficient is proportional to the value of the main difference.

[0048] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0049] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A finger vein recognition device, characterized in that: It includes a base, an active light source, a processor and an image sensor are arranged on the surface of the base, a lens is fixedly mounted on the base through a fixing seat, and a filter is arranged in the lens; The processor is communicatively connected to an image acquisition module, a feature comparison module, an image comparison module and a storage module; The image acquisition module is used to acquire the finger vein image of the user: when entering identity information, the active light source is turned on, and the light of the active light source passes through the filter to generate near-infrared light with a wavelength of 960nm. After the near-infrared light is absorbed by the finger vein, the finger vein image is acquired through the image sensor, and the acquired finger vein image is feature extracted to obtain area data, trunk data, branch data and angle data. The area data, trunk data, branch data and angle data constitute feature parameters of the finger vein image, and the finger vein image is matched with the feature parameters and sent to the storage module through the processor for storage; The feature comparison module is used to perform feature comparison analysis when authenticating a user: when authenticating a user, the active light source is turned on and the finger vein image of the user is obtained through the image sensor, the finger vein image of the user is marked as an authentication image, and feature extraction is performed on the authentication image to obtain area data, trunk data, branch data and angle data, all feature parameters are retrieved through the storage module, and the authentication image and the feature parameters are compared in area; The image comparison module is used to perform image comparison analysis when authenticating a user; The specific process of performing area comparison between the authentication image and the feature parameter includes: marking the absolute value of the difference between the area data of the authentication image and the area data in the feature parameter as a face difference value, obtaining the face difference threshold through the storage module, and comparing the face difference value with the face difference threshold: if the face difference value is less than the face difference threshold, marking the corresponding feature parameter as a preliminary parameter; if the face difference value is greater than or equal to the face difference threshold, marking the corresponding feature parameter as an invalid parameter; performing feature comparison between the authentication image and the preliminary parameter; The specific process of feature comparison between the authentication image and the preliminary parameters includes: marking the absolute value of the difference between the trunk data of the authentication image and the trunk data of the preliminary parameters as the main difference ZC, marking the absolute value of the difference between the branch data of the authentication image and the branch data of the preliminary parameters as the branch difference FC, marking the absolute value of the difference between the angle data of the authentication image and the angle data of the preliminary parameters as the angle difference JC; obtaining the deviation coefficient PC of the preliminary parameters by numerically calculating the main difference ZC, the branch difference FC and the angle difference JC; marking the preliminary parameters as secondary parameters or invalid parameters by the deviation coefficient PC; The specific process of the image comparison and analysis performed by the image comparison module during identity authentication includes: calling the finger vein image corresponding to the secondary parameter through the storage module and marking it as the analysis image, and performing image comparison between the authentication image and the analysis image one by one: enlarging the authentication image and the analysis image into pixel grid images and performing grayscale transformation, marking the pixel grid as a common grid or a vein grid through a binary method, and then overlapping the authentication image and the analysis image to obtain the marking status of the pixel grid at the same position in the authentication image and the analysis image: if the pixel grid at the same position is marked as a common grid or a vein grid in both the authentication image and the analysis image, the pixel grid at the corresponding position is marked as a unified grid; otherwise, the pixel grid at the corresponding position is marked as a bifurcated grid; the ratio of the number of unified grids to the number of pixel grids in the analysis image is marked as a unified coefficient, and the analysis image is marked as a matching image or an invalid image through the unified coefficient. After all the analysis images are compared with the authentication image, the number of matching images is obtained and whether the image authentication is successful is determined by the number of matching images.

2. The finger vein recognition device according to claim 1, characterized in that: The area data is the area value of the finger vein in the finger vein image, the trunk data is the number value of the main vein in the finger vein image, the branch data is the number value of the branch vein in the finger vein image, and the angle data is the maximum angle between the branch vein and the trunk vein in the vein image.

3. The finger vein recognition device according to claim 2, characterized in that: The specific process of marking the analysis image as a matching image or an invalid image includes: obtaining a unified threshold through a storage module, and comparing a unified coefficient with the unified threshold: if the unified coefficient is greater than or equal to the unified threshold, the corresponding analysis image is marked as a matching image; if the unified coefficient is less than the unified threshold, the corresponding analysis image is marked as an invalid image.

4. The finger vein recognition device according to claim 3, characterized in that: The specific process of determining whether image authentication is successful includes: if the number of matching objects is one, the image comparison is determined to be successful, the identity information of the corresponding matching object is matched with the authenticated user, and an authentication success signal is generated and sent to the processor; if the number of matching objects is greater than one, the image comparison is determined to be successful, the identity information of the matching object with the largest unified coefficient value is matched with the authenticated user, and an authentication success signal is generated and sent to the processor; if the number of matching objects is zero, the image comparison is determined to be unsuccessful, an authentication failure signal is generated and sent to the processor.

Images