WO2021027155A1

WO2021027155A1 - Verification method and apparatus based on finger vein image, and storage medium and computer device

Info

Publication number: WO2021027155A1
Application number: PCT/CN2019/118088
Authority: WO
Inventors: 巢中迪; 庄伯金; 王少军
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-08-13
Filing date: 2019-11-13
Publication date: 2021-02-18
Also published as: CN110705341A

Abstract

Disclosed are a verification method and apparatus based on a finger vein image, and a storage medium and a computer device, relating to the technical field of artificial intelligence. The method comprises: collecting a finger vein image to obtain a finger vein image to be identified (S102); acquiring a feature parameter of a finger vein (S104); constructing a target convolution kernel according to the feature parameter (S106); performing, by using the target convolution kernel, filtering processing on the finger vein image to be identified (S108); respectively calculating the similarity between the finger vein image to be identified subjected to filtering processing and each preset finger vein image stored in a target database (S110); if the similarity between the finger vein image to be identified subjected to filtering processing and any preset finger vein image stored in the target database is less than a preset similarity threshold value, determining that verification fails (S112); and if the similarity between the finger vein image to be identified subjected to filtering processing and at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity threshold value, determining that the verification is successful (S114). The method and apparatus, and the storage medium and the computer device can solve the problem in the art of low accuracy of identity verification based on a finger vein image.

Description

Verification method, device, storage medium and computer equipment based on finger vein image

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on August 13, 2019, the application number is 201910743874.9, and the application title is "Verification Method, Device, and Storage Medium Based on Finger Vein Images", the entire content of which is incorporated by reference Incorporated in this application.

【Technical Field】

This application relates to the field of artificial intelligence technology, and in particular to a verification method, device, storage medium, and computer equipment based on finger vein images.

【Background technique】

Finger vein recognition technology uses the texture of finger veins for identity verification, which is harmless to the human body and is not easy to be stolen or forged. The identification technology can be widely used in access control systems in banking, finance, government, education and other fields.

At present, the problem of finger vein recognition technology is: because finger veins exist under the epidermis, the finger vein image matching process is easily disturbed by the texture of the epidermis, resulting in low accuracy of finger vein image matching, which in turn leads to identification verification based on finger vein images The accuracy is low.

【Content of Application】

In view of this, the embodiments of the present application provide a verification method, device, storage medium, and computer equipment based on finger vein images to solve the problem of low accuracy of identity verification based on finger vein images in the prior art.

On the one hand, an embodiment of the present application provides a verification method based on a finger vein image. The method includes: acquiring a finger vein image to obtain a finger vein image to be identified; acquiring characteristic parameters of the finger vein; and constructing a target based on the characteristic parameters Convolution kernel; using the target convolution kernel to filter the finger vein image to be identified; respectively calculate the filter process between the finger vein image to be identified and each preset finger vein image stored in the target database If the similarity between the filtered finger vein image to be identified and any one of the preset finger vein images stored in the target database is less than the preset similarity threshold, it is determined that the verification fails; if After the filtering process, the similarity between the finger vein image to be identified and at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity threshold, then it is determined that the verification is successful.

On the one hand, an embodiment of the present application provides a verification device based on a finger vein image. The device includes: an acquisition unit for acquiring a finger vein image to obtain a finger vein image to be identified; an acquisition unit for acquiring a finger vein image Feature parameters; a construction unit, configured to construct a target convolution kernel according to the feature parameters; a filtering unit, configured to use the target convolution kernel to filter the finger vein image to be identified; a calculation unit, configured to calculate filters separately The processed similarity between the finger vein image to be identified and each preset finger vein image stored in the target database; the first determining unit is configured to determine if the finger vein image to be identified after the filtering process is compared with the If the similarity between any one of the preset finger vein images stored in the target database is less than the preset similarity threshold, it is determined that the verification fails; the second determining unit is configured to filter the finger vein images to be identified if the If the similarity with at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity threshold, it is determined that the verification is successful.

On the one hand, an embodiment of the present application provides a storage medium that includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the above-mentioned verification method based on finger vein images.

On the one hand, an embodiment of the present application provides a computer device, including a memory and a processor, the memory is configured to store information including program instructions, the processor is configured to control the execution of the program instructions, and the program instructions are executed by the processor. When loaded and executed, the steps of the above-mentioned verification method based on finger vein images are realized.

In the embodiment of the present application, the target convolution kernel is constructed according to the characteristic parameters of the finger veins, and the target convolution kernel is used to filter the finger vein images to be identified, which effectively avoids skin texture interference and improves the accuracy of finger vein image matching. This solves the problem of low accuracy of identity verification based on finger vein images in the prior art, and achieves the effect of improving the accuracy of identity verification based on finger vein images.

【Explanation of drawings】

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative labor, other drawings can be obtained from these drawings.

Fig. 1 is a flowchart of an optional verification method based on finger vein images according to an embodiment of the present application;

2 is a schematic diagram of an optional verification device based on finger vein images according to an embodiment of the present application;

Fig. 3 is a schematic diagram of an optional computer device provided by an embodiment of the present application.

【detailed description】

In order to better understand the technical solutions of the present application, the following describes the embodiments of the present application in detail with reference to the accompanying drawings.

It should be clear that the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

It should be understood that the term "and/or" used in this article is only an association relationship describing related objects, indicating that there can be three types of relationships. For example, A and/or B can mean that there is A alone, and both A and A B, there are three cases of B alone. In addition, the character "/" in this text generally indicates that the associated objects before and after are in an "or" relationship.

Fig. 1 is a flowchart of an optional verification method based on finger vein images according to an embodiment of the present application. As shown in Fig. 1, the method includes:

Step S102: Collect a finger vein image to obtain a finger vein image to be identified.

Step S104, acquiring characteristic parameters of the finger veins.

Step S106, construct a target convolution kernel according to the characteristic parameters.

Step S108, using the target convolution kernel to perform filtering processing on the finger vein image to be identified.

Step S110: Calculate the similarity between the filtered finger vein image to be identified and each preset finger vein image stored in the target database.

Step S112: If the similarity between the filtered finger vein image to be identified and any preset finger vein image stored in the target database is less than the preset similarity threshold, it is determined that the verification fails.

Step S114: If the similarity between the filtered finger vein image to be identified and at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity threshold, it is determined that the verification is successful.

Finger veins refer to the veins in the fingers of the human body. Finger vein recognition uses the characteristics of the vascular structure to achieve identity authentication. Under visible light, finger veins are invisible and can only be obtained with a special collection device. It is medically proven that the vascular structure of human finger veins can penetrate bones and muscles under the irradiation of near-infrared light, and the hemoglobin flowing through the venous blood vessels can easily absorb the infrared light of this band to highlight the vein structure. Finger vein images can be captured by a special image acquisition device such as an infrared CCD camera, and then the finger vein images can be analyzed and processed to obtain the finger vein characteristics. The vein structure of different people is different, even the finger veins of twins are different, and the structure of adult finger veins does not change, that is, finger veins are unique, which provides a scientific basis for finger vein recognition.

Convolution kernel: In image processing, given an input image, each pixel in the output image is a weighted average of pixels in a small area in the input image, where the weight is defined by a function, which is called the convolution kernel. One property of the convolution kernel is locality. That is, it only focuses on local features, and the degree of locality depends on the size of the convolution kernel.

Optionally, the characteristic parameter includes a finger vein width parameter. The vein width parameter is a parameter used to indicate the width range of the finger vein. Constructing the target convolution kernel according to the characteristic parameters may specifically be: determining the size of the target convolution kernel according to the finger vein width parameter. Since the convolution kernel has the property of locality, the degree of locality depends on the size of the convolution kernel. Therefore, if there are more pixels that need attention in the finger vein image to be recognized, the size of the convolution kernel can be larger; Recognizing that there are fewer pixels that need attention in the finger vein image, the size of the convolution kernel can be smaller. For example, assuming that the vein width parameter indicates that the width of the finger vein covers m pixels, the size of the target convolution kernel can be m×m.

The target convolution kernel is used to filter the finger vein image to be recognized, that is, the target convolution kernel is convolved with the finger vein image to be recognized, specifically, each pixel in the finger vein image to be recognized is used by the target convolution kernel Point to perform a series of operations, for example, for an m×m target convolution kernel, the target convolution kernel is an m×m matrix, and each element in the matrix has a preset weight value. When calculating the target convolution kernel, place the center of the target convolution kernel on the target pixel to be calculated in the finger vein image to be recognized, and calculate the weight value of each element in the target convolution kernel and the image pixels covered by it The product of the pixel values of, and the sum, the result is the new pixel value of the target pixel. For all the pixels in the finger vein image to be identified, the new pixel value is used to replace the original pixel value, and the filtered finger vein image to be identified is obtained. By using the target convolution kernel to filter the finger vein image to be recognized, the features of the finger vein image to be recognized can be extracted, and the enhancement effect of the finger vein image to be recognized can be achieved, effectively avoiding the interference of the epidermal texture.

Optionally, the process of calculating the similarity between the filtered finger vein image to be recognized and any one of the preset finger vein images stored in the target database is: extracting the filtered finger vein image to be recognized and the preset finger vein image The most similar area in the vein image is obtained, and the first image and the second image are obtained. The first image is the area in the finger vein image to be recognized after the filtering process, and the second image is the area in the preset finger vein image; calculate the first image The distance between the image and the second image; the similarity between the filtered finger vein image to be identified and the preset finger vein image is determined according to the distance between the first image and the second image.

First, extract the most similar area in the filtered finger vein image and the preset finger vein image, and determine the similarity between the finger vein image to be recognized and the preset finger vein image by calculating the distance of the most similar area. It overcomes the problem of unclear finger vein image boundaries, and improves the accuracy of finger vein image matching.

Optionally, calculating the distance between the first image and the second image includes: calculating the first image according to the formula Dist=(d/q)×(d/q)×0.5×(A+B-1)+d The distance from the second image, where Dist represents the distance between the first image and the second image, A represents the proportion of non-zero pixels in the first image, and B represents the proportion of non-zero pixels in the second image , D is the Hamming distance between the first image and the second image, 0<q<1. For example, when q=0.3, the above formula is: Dist=(d/0.3)×(d/0.3)×0.5×(A+B-1)+d; for another example, when q=0.32, the above formula is : Dist=(d/0.32)×(d/0.32)×0.5×(A+B-1)+d; for another example, when q=0.5, the above formula is: Dist=(d/0.5)×(d /0.5)×0.5×(A+B-1)+d.

The Hamming distance represents the number of different bits corresponding to two (same length) character strings. Perform an exclusive OR operation on the two character strings and count the number of results as 1, then this number is the Hamming distance.

In information theory, the Hamming distance between two strings of equal length is the number of different characters in the corresponding positions of the two strings. In other words, it is the number of characters that need to be replaced to transform one string into another. For example: the Hamming distance between "1011101" and "1001001" is 2. The Hamming distance between "2143896" and "2233796" is 3. The Hamming distance between "toned" and "roses" is 3.

The specific process of calculating the Hamming distance between the first image and the second image is as follows: respectively generate the fingerprint character string of the first image and the fingerprint character string of the second image; calculate the fingerprint character string of the first image and the fingerprint character string of the second image The Hamming distance between the fingerprint character strings; the Hamming distance between the fingerprint character string of the first image and the fingerprint character string of the second image is taken as the Hamming distance between the first image and the second image. The greater the Hamming distance, the greater the difference between the two images.

Among them, the process of generating a fingerprint string of an image is as follows:

The first step is to reduce the size.

For example, reduce the image to a size of 8×8, a total of 64 pixels. The function of this step is to remove the details of the image, only retain basic information such as structure, light and shade, and abandon the difference in images caused by different sizes.

The second step is to simplify the color.

Convert the reduced image to 64-level grayscale. In other words, there are only 64 colors for all pixels.

The third step is to calculate the average value.

Calculate the gray average of all 64 pixels.

The fourth step is to compare the gray levels of pixels.

Compare the gray scale of each pixel with the average value. Greater than or equal to the average value is recorded as 1; less than the average value is recorded as 0.

The fifth step is to calculate the hash value.

Combine the comparison results of the previous step to form a 64-bit integer, which is the fingerprint of this image. The order of combination is not important, as long as all images are in the same order.

Optionally, after acquiring the finger vein image to obtain the finger vein image to be identified, the method further includes: performing size normalization processing on the finger vein image to be identified. Optionally, after performing size normalization processing on the finger vein image to be recognized, the method further includes: performing gray-scale normalization processing on the finger vein image after the size normalization processing.

When finger vein images are collected, due to different conditions such as light intensity, finger thickness, blood temperature, finger inclination, etc., finger vein images collected at different times have large differences in grayscale distribution, which will affect future image processing and Matching increases the difficulty. Therefore, after the finger vein image is collected, normalization is required, including size normalization and gray normalization.

The benefits of size normalization are: 1. For different fingers, different sizes have no effect on the matching results of veins, that is, it will not cause misunderstanding; but if it is the same finger, if the size is different, it is easy to cause misunderstanding , That is, I cannot recognize my own situation. 2. If the actually collected image is too large, it will take a long time to process the image, and the normalized size is reduced to a certain pixel size, for example, without affecting the recognition result, which can further shorten the matching time and improve the matching efficiency .

Image size normalization is essentially a geometric transformation of an image, which is generally achieved by mapping from the opposite direction of the target image. Reverse mapping is to scan each pixel of the target image and determine the original pixel corresponding to the target pixel according to a given transformation formula. Using this method to calculate the target image can ensure that the entire target image has no empty pixels, that is, each pixel of the target image obtained has a corresponding gray value.

Gray normalization is mainly to increase the brightness of the image, make the details of the image clearer, and reduce the influence of light and light intensity.

An embodiment of the application provides a verification device based on a finger vein image, and the device is used to execute the above verification method based on a finger vein image. FIG. 2 is an optional verification device based on a finger vein image according to an embodiment of the application. As shown in FIG. 2, the device includes: an acquisition unit 10, an acquisition unit 20, a construction unit 30, a filter unit 40, a calculation unit 50, a first determination unit 60, and a second determination unit 70.

The acquisition unit 10 is used to acquire a finger vein image to obtain a finger vein image to be identified.

The acquiring unit 20 is used to acquire characteristic parameters of finger veins.

The construction unit 30 is used to construct the target convolution kernel according to the characteristic parameters.

The filtering unit 40 is configured to use the target convolution kernel to perform filtering processing on the finger vein image to be identified.

The calculating unit 50 is configured to calculate the similarity between the finger vein image to be identified after the filtering process and each preset finger vein image stored in the target database.

The first determining unit 60 is configured to determine that the verification fails if the similarity between the filtered finger vein image to be identified and any one of the preset finger vein images stored in the target database is less than the preset similarity threshold.

The second determining unit 70 is configured to determine that the verification is successful if the similarity between the filtered finger vein image to be identified and at least one preset finger vein image stored in the target database is greater than or equal to a preset similarity threshold.

Finger veins refer to the veins in the fingers of the human body. Finger vein recognition uses the characteristics of the vascular structure to achieve identity authentication. Under visible light, finger veins are invisible and can only be obtained with a special collection device. It is medically proven that the vascular structure of human finger veins can penetrate bones and muscles under the irradiation of near-infrared light, and the hemoglobin flowing through the venous blood vessels can easily absorb the infrared light of this band to highlight the vein structure. Finger vein images can be captured by a special image acquisition device such as an infrared CCD camera, and then the finger vein images can be analyzed and processed to obtain the finger vein characteristics. The vein structure of different people is different, even the finger veins of twins are different, and the finger vein structure of adults does not change, that is, finger veins are unique, which provides a scientific basis for finger vein recognition.

The target convolution kernel is used to filter the finger vein image to be recognized, that is, the target convolution kernel and the finger vein image to be recognized are convolved. Specifically, the target convolution kernel is used to perform the filtering process on each pixel in the finger vein image. A series of operations, for example, for an m×m target convolution kernel, the target convolution kernel is an m×m matrix, and each element in the matrix has a preset weight value. When using the target volume When the product kernel is calculated, place the center of the target convolution kernel on the target pixel to be calculated, and calculate the product of the weight value of each element in the target convolution kernel and the pixel value of the image pixel it covers. Sum, the result obtained is the new pixel value of the target pixel. For all the pixels in the finger vein image to be identified, the new pixel value is used to replace the original pixel value, and the filtered finger vein image to be identified is obtained. By using the target convolution kernel to filter the finger vein image to be recognized, the features of the finger vein image to be recognized can be extracted, and the enhancement effect of the finger vein image to be recognized can be achieved, effectively avoiding the interference of the epidermal texture.

Optionally, the calculation unit 50 includes: an extraction subunit, a calculation subunit, and a determination subunit.

The extraction subunit is used to extract the most similar area in the finger vein image to be identified after the filtering process and the preset finger vein image to obtain the first image and the second image, where the first image is the finger vein image to be identified after the filtering process The area in the vein image, and the second image is the area in the preset finger vein image.

The calculation subunit is used to calculate the distance between the first image and the second image.

The determining subunit is configured to determine the similarity between the finger vein image to be identified after the filtering process and the preset finger vein image according to the distance between the first image and the second image.

Optionally, the calculation subunit is used to calculate the distance between the first image and the second image according to the formula Dist=(d/q)×(d/q)×0.5×(A+B-1)+d, Among them, Dist represents the distance between the first image and the second image, A represents the proportion of non-zero pixels in the first image, B represents the proportion of non-zero pixels in the second image, and d is the first image and the second image. The Hamming distance between images, 0<q<1.

Optionally, the characteristic parameter includes a finger vein width parameter.

Optionally, the device further includes: a size normalization unit. The size normalization unit is used to perform size normalization processing on the finger vein image to be identified after the finger vein image is collected by the acquisition unit 10 to obtain the finger vein image to be identified.

Optionally, the device further includes: a gray-scale normalization unit. The gray-scale normalization unit is used to perform the gray-scale normalization process on the finger vein image to be recognized after the size normalization process after the size normalization unit performs the size normalization process on the finger vein image to be recognized.

On the one hand, an embodiment of the present application provides a storage medium, the storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to perform the following steps: acquiring a finger vein image to obtain a finger vein image to be identified; Vein characteristic parameters; construct the target convolution kernel according to the characteristic parameters; use the target convolution kernel to filter the image of the finger vein to be identified; calculate the filtered finger vein image to be identified and each preset finger stored in the target database separately The similarity between vein images; if the similarity between the filtered finger vein image to be identified and any one of the preset finger vein images stored in the target database is less than the preset similarity threshold, the verification is determined to fail; if The similarity between the filtered finger vein image to be identified and at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity threshold, then it is determined that the verification is successful.

Optionally, when the program is running, the device where the storage medium is controlled further executes the following steps: extract the most similar area in the finger vein image to be identified after the filtering process and the preset finger vein image to obtain the first image and the second image, where , The first image is the area in the finger vein image to be recognized after the filtering process, the second image is the area in the preset finger vein image; calculate the distance between the first image and the second image; according to the first image and the first image The distance between the two images determines the similarity between the filtered finger vein image to be identified and the preset finger vein image.

Optionally, when the program is running, the device where the storage medium is controlled further executes the following steps: calculate the first image and the value according to the formula Dist=(d/q)×(d/q)×0.5×(A+B-1)+d The distance between the second image, where Dist represents the distance between the first image and the second image, A represents the proportion of non-zero pixels in the first image, and B represents the proportion of non-zero pixels in the second image, d is the Hamming distance between the first image and the second image, 0<q<1.

Optionally, when the program is running, the device where the storage medium is located is controlled to perform the following steps: after the finger vein image is collected and the finger vein image to be identified is obtained, the size normalization process is performed on the finger vein image to be identified.

Optionally, when the program is running, the device where the storage medium is controlled further executes the following steps: after performing size normalization processing on the finger vein image to be recognized, perform gray level normalization on the finger vein image to be recognized after the size normalization process化处理.

On the one hand, an embodiment of the present application provides a computer device, including a memory and a processor, the memory is used to store information including program instructions, the processor is used to control the execution of the program instructions, and the program instructions are loaded and executed by the processor to achieve the following Steps: Collect finger vein images to obtain the finger vein image to be identified; obtain the characteristic parameters of the finger vein; construct the target convolution kernel according to the characteristic parameters; use the target convolution kernel to filter the finger vein image to be identified; calculate the filtered and processed images separately The degree of similarity between the finger vein image to be identified and each preset finger vein image stored in the target database; if the filter process is between the finger vein image to be identified and any preset finger vein image stored in the target database If the similarity is less than the preset similarity threshold, it is determined that the verification fails; if the similarity between the filtered finger vein image to be identified and at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity Threshold, it is determined that the verification is successful.

Optionally, when the program instructions are loaded and executed by the processor, the following steps are also implemented: extract the most similar area in the finger vein image to be identified after the filtering process and the preset finger vein image to obtain the first image and the second image, where , The first image is the area in the finger vein image to be recognized after the filtering process, the second image is the area in the preset finger vein image; calculate the distance between the first image and the second image; according to the first image and the first image The distance between the two images determines the similarity between the filtered finger vein image to be identified and the preset finger vein image.

Optionally, when the program instructions are loaded and executed by the processor, the following steps are also implemented: according to the formula Dist=(d/q)×(d/q)×0.5×(A+B-1)+d calculate the first image and The distance between the second image, where Dist represents the distance between the first image and the second image, A represents the proportion of non-zero pixels in the first image, and B represents the proportion of non-zero pixels in the second image, d is the Hamming distance between the first image and the second image, 0<q<1.

Optionally, when the program instructions are loaded and executed by the processor, the following steps are further implemented: after the finger vein image is collected and the finger vein image to be identified is obtained, the size normalization process is performed on the finger vein image to be identified.

Optionally, when the program instructions are loaded and executed by the processor, the following steps are also implemented: after the size normalization process is performed on the finger vein image to be recognized, the gray scale normalization process is performed on the finger vein image to be recognized after the size normalization process.化处理.

Fig. 3 is a schematic diagram of a computer device provided by an embodiment of the present application. As shown in FIG. 3, the computer device 50 of this embodiment includes: a processor 51, a memory 52, and a computer program 53 stored in the memory 52 and running on the processor 51. When the computer program 53 is executed by the processor 51, To implement the verification method based on the finger vein image in the embodiment, in order to avoid repetition, it will not be repeated here. Alternatively, when the computer program is executed by the processor 51, the function of each model/unit in the verification device based on the finger vein image in the embodiment is realized. In order to avoid repetition, it will not be repeated here.

The computer device 50 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The computer device may include, but is not limited to, a processor 51 and a memory 52. Those skilled in the art can understand that FIG. 3 is only an example of the computer device 50, and does not constitute a limitation on the computer device 50. It may include more or less components than those shown in the figure, or a combination of certain components, or different components. For example, computer equipment may also include input and output devices, network access devices, buses, and so on.

The so-called processor 51 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.

The memory 52 may be an internal storage unit of the computer device 50, such as a hard disk or memory of the computer device 50. The memory 52 may also be an external storage device of the computer device 50, such as a plug-in hard disk equipped on the computer device 50, a smart memory card (Smart Media Card, SMC), a Secure Digital (SD) card, and a flash memory card (Flash). Card) and so on. Further, the memory 52 may also include both an internal storage unit of the computer device 50 and an external storage device. The memory 52 is used to store computer programs and other programs and data required by the computer equipment. The memory 52 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that, for the convenience and conciseness of description, the specific working process of the above-described system, device, and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed system, device, and method may be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined Or it can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in each embodiment of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional units.

The above-mentioned integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (Processor) execute the method described in each embodiment of the present application Part of the steps. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

The above are only the preferred embodiments of this application and are not intended to limit this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in this application Within the scope of protection.

Claims

A verification method based on finger vein images, characterized in that the method includes:

Collect finger vein images to obtain the finger vein images to be identified;

Obtain characteristic parameters of finger veins;

Constructing a target convolution kernel according to the characteristic parameters;

Filtering the finger vein image to be identified by using the target convolution kernel;

Respectively calculating the similarity between the finger vein image to be identified after the filtering process and each preset finger vein image stored in the target database;

If the similarity between the filtered finger vein image to be identified and any one of the preset finger vein images stored in the target database is less than the preset similarity threshold, it is determined that the verification fails;

If the similarity between the filtered finger vein image to be identified and at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity threshold, it is determined that the verification is successful.
The method according to claim 1, wherein the calculating the similarity between the filtered finger vein image to be identified and the preset finger vein image stored in the target database respectively comprises:

The most similar area in the finger vein image to be identified after the filtering process and the preset finger vein image is extracted to obtain a first image and a second image, wherein the first image is the filtered finger vein image. Identifying an area in a finger vein image, where the second image is an area in the preset finger vein image;

Calculating the distance between the first image and the second image;

The similarity between the filtered finger vein image and the preset finger vein image is determined according to the distance between the first image and the second image.
The method according to claim 2, wherein the calculating the distance between the first image and the second image comprises:

Calculate the distance between the first image and the second image according to the formula Dist=(d/q)×(d/q)×0.5×(A+B-1)+d, where Dist represents the The distance between the first image and the second image, A represents the proportion of non-zero pixels in the first image, B represents the proportion of non-zero pixels in the second image, and d is the first image The Hamming distance between the image and the second image is 0<q<1.
The method according to claim 1, wherein the characteristic parameter includes a finger vein width parameter.
The method according to any one of claims 1 to 4, characterized in that, after the finger vein image is acquired to obtain the finger vein image to be identified, the method further comprises:

Perform size normalization processing on the finger vein image to be recognized.
The method according to claim 5, characterized in that, after the size normalization processing is performed on the finger vein image to be identified, the method further comprises:

Perform gray-scale normalization processing on the finger vein image to be identified after size normalization processing.
A verification device based on finger vein images, characterized in that the device comprises:

The acquisition unit is used to acquire the finger vein image to obtain the finger vein image to be identified;

An acquiring unit for acquiring characteristic parameters of finger veins;

A construction unit, configured to construct a target convolution kernel according to the characteristic parameters;

A filtering unit, configured to use the target convolution kernel to perform filtering processing on the finger vein image to be identified;

A calculation unit, configured to calculate the similarity between the finger vein image to be identified after the filtering process and each preset finger vein image stored in the target database;

The first determining unit is configured to determine and verify if the similarity between the filtered finger vein image to be identified and any one of the preset finger vein images stored in the target database is less than a preset similarity threshold failure;

The second determining unit is configured to, if the similarity between the filtered finger vein image to be identified and at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity threshold, It is determined that the verification is successful.
The device according to claim 7, wherein the calculation unit comprises:

The extraction subunit is used to extract the most similar area in the finger vein image to be identified after the filtering process and the preset finger vein image to obtain a first image and a second image, wherein the first image is filtered The processed area in the finger vein image to be identified, where the second image is the area in the preset finger vein image;

A calculation subunit for calculating the distance between the first image and the second image;

The determining subunit is configured to determine the similarity between the finger vein image to be identified after filtering processing and the preset finger vein image according to the distance between the first image and the second image.
The device according to claim 8, wherein the calculation subunit is used to calculate the first calculation according to the formula Dist=(d/q)×(d/q)×0.5×(A+B-1)+d The distance between an image and the second image, where Dist represents the distance between the first image and the second image, A represents the proportion of non-zero pixels in the first image, and B represents the non-zero pixels in the second image The proportion, d is the Hamming distance between the first image and the second image, 0<q<1.
The device according to any one of claims 7-9, wherein the device further comprises:

The size normalization unit is configured to perform size normalization processing on the finger vein image to be identified after the finger vein image is collected by the acquisition unit to obtain the finger vein image to be identified.
A storage medium, the storage medium including a stored program, wherein the device where the storage medium is located is controlled to perform the following steps when the program is running:

Collect finger vein images to obtain the finger vein images to be identified;

Obtain characteristic parameters of finger veins;

Constructing a target convolution kernel according to the characteristic parameters;

Filtering the finger vein image to be identified by using the target convolution kernel;

Respectively calculating the similarity between the finger vein image to be identified after the filtering process and each preset finger vein image stored in the target database;

If the similarity between the filtered finger vein image to be identified and any one of the preset finger vein images stored in the target database is less than the preset similarity threshold, it is determined that the verification fails;

If the similarity between the filtered finger vein image to be identified and at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity threshold, it is determined that the verification is successful.
The storage medium according to claim 11, wherein when the program is running, the device where the storage medium is located is controlled to execute the respective calculation and filtering processing, the finger vein image to be identified and the target database are stored The steps of presetting the similarity between finger vein images include:

The most similar area in the finger vein image to be identified after the filtering process and the preset finger vein image is extracted to obtain a first image and a second image, wherein the first image is the filtered finger vein image. Identifying an area in a finger vein image, where the second image is an area in the preset finger vein image;

Calculating the distance between the first image and the second image;

The similarity between the filtered finger vein image and the preset finger vein image is determined according to the distance between the first image and the second image.
The storage medium according to claim 12, wherein, when the program is running, controlling the device where the storage medium is located to execute the step of calculating the distance between the first image and the second image comprises :

Calculate the distance between the first image and the second image according to the formula Dist=(d/q)×(d/q)×0.5×(A+B-1)+d, where Dist represents the The distance between the first image and the second image, A represents the proportion of non-zero pixels in the first image, B represents the proportion of non-zero pixels in the second image, and d is the first image The Hamming distance between the image and the second image is 0<q<1.
The storage medium according to any one of claims 11 to 13, wherein when the program is running, the device where the storage medium is located is controlled to perform the acquisition of the finger vein image to obtain the finger vein image to be identified, and then Perform the following steps:

Perform size normalization processing on the finger vein image to be recognized.
The storage medium according to claim 14, wherein, when the program is running, the device where the storage medium is located is controlled to perform the following after performing the size normalization processing on the finger vein image to be recognized step:

Perform gray-scale normalization processing on the finger vein image to be identified after size normalization processing.
A computer device, comprising a memory and a processor, the memory is used to store information including program instructions, the processor is used to control the execution of the program instructions, characterized in that the program instructions are loaded by the processor and execute the following steps :

Collect finger vein images to obtain the finger vein images to be identified;

Obtain characteristic parameters of finger veins;

Constructing a target convolution kernel according to the characteristic parameters;

Filtering the finger vein image to be identified by using the target convolution kernel;

Respectively calculating the similarity between the finger vein image to be identified after the filtering process and each preset finger vein image stored in the target database;

If the similarity between the filtered finger vein image to be identified and any one of the preset finger vein images stored in the target database is less than the preset similarity threshold, it is determined that the verification fails;

If the similarity between the filtered finger vein image to be identified and at least one preset finger vein image stored in the target database is greater than or equal to the preset similarity threshold, it is determined that the verification is successful.
The computer device according to claim 16, wherein the program instructions are loaded by a processor and execute the respective calculation and filtering of the finger vein image to be identified and the preset finger stored in the target database. The steps of similarity between vein images include:

The most similar area in the finger vein image to be identified after the filtering process and the preset finger vein image is extracted to obtain a first image and a second image, wherein the first image is the filtered finger vein image. Identifying an area in a finger vein image, where the second image is an area in the preset finger vein image;

Calculating the distance between the first image and the second image;

The similarity between the filtered finger vein image and the preset finger vein image is determined according to the distance between the first image and the second image.
18. The computer device according to claim 17, wherein the program instructions are loaded by a processor to execute the step of calculating the distance between the first image and the second image, comprising:

Calculate the distance between the first image and the second image according to the formula Dist=(d/q)×(d/q)×0.5×(A+B-1)+d, where Dist represents the The distance between the first image and the second image, A represents the proportion of non-zero pixels in the first image, B represents the proportion of non-zero pixels in the second image, and d is the first image The Hamming distance between the image and the second image is 0<q<1.
The computer device according to any one of claims 16 to 18, wherein the program instructions are loaded by a processor and after executing the collecting finger vein image to obtain the finger vein image to be identified, the following steps are further executed:

Perform size normalization processing on the finger vein image to be recognized.
20. The computer device according to claim 19, wherein the program instructions are loaded by a processor and after performing the size normalization processing on the finger vein image to be recognized, the following steps are further executed:

Perform gray-scale normalization processing on the finger vein image to be identified after size normalization processing.