A near-infrared light intensity uniformity detection method, device and computer equipment

Abstract

The present invention relates to the field of biometrics, and specifically to a near-infrared light intensity uniformity detection method, device and computer equipment, wherein the near-infrared light intensity uniformity detection method comprises: obtaining an image to be processed, wherein the image to be processed is an image taken by a vein sensor of a reference surface within a capture range, and the reference surface is a white plane on a reference object that can cover the near-infrared light irradiation range of the vein sensor; converting the image to be processed into a grayscale image to obtain the grayscale value of each pixel; dividing the grayscale image into a plurality of blocks; calculating the grayscale average value of each block; comparing the grayscale average values ​​of different blocks to obtain a comparison result; and determining the uniformity of the near-infrared light intensity of the vein sensor according to the comparison result. The present invention can solve the problem of inaccurate detection results or high detection costs in the prior art for the near-infrared light uniformity detection method for vein recognition.

Description

Technical Field

[0001] The present invention relates to the field of biometrics, and in particular to a near-infrared light intensity uniformity detection method, device and computer equipment. Background Art

[0002] In vein recognition technology, people use vein sensors to capture blood vessel images by taking advantage of the fact that near-infrared light is easily absorbed by hemoglobin in human blood. In order to ensure the quality of the captured images, a group of near-infrared light sources are designed to focus on a specific area (such as a finger or palm), and the luminous intensity of the near-infrared light source is required to be moderate and the light intensity in the specified area is basically uniform.

[0003] In order to evaluate the uniformity of the intensity of near-infrared light irradiated into a specified area, people usually use various types of light intensity measuring devices. The existing light intensity measuring devices are mainly divided into two types: ordinary and professional. Among them, the ordinary type of light intensity measuring device has a wavelength measurement range limited to 0-720nm and cannot measure changes in a very small area. The professional near-infrared light radiation intensity measurement system is not only expensive, but also can only measure the angular distribution or radiation intensity of 850nm-940nm near-infrared light emitters.

[0004] In the prior art, when judging the uniformity of near-infrared light intensity, whether it is a common light intensity measuring device or a professional near-infrared light radiation intensity measurement system, equipment is required for detection. This detection method is affected by the performance of the equipment itself. On the one hand, there is a problem of inaccurate detection results, and on the other hand, it causes excessively high detection costs. Summary of the invention

[0005] Therefore, the present invention aims to solve the problem in the prior art that the detection results of the near-infrared light uniformity detection method for vein recognition are inaccurate or the detection cost is high, thereby providing a near-infrared light intensity uniformity detection method.

[0006] According to one aspect of the present invention, a near-infrared light intensity uniformity detection method is provided, comprising the following steps: acquiring an image to be processed, wherein the image to be processed is an image taken by a vein sensor of a reference surface within a capture range, and the reference surface is a white plane on a reference object that can cover the near-infrared light irradiation range of the vein sensor; converting the image to be processed into a grayscale image to obtain a grayscale value of each pixel; dividing the grayscale image into a plurality of blocks; calculating the grayscale average value of each block; comparing the grayscale average values ​​of different blocks to obtain a comparison result; and determining the uniformity of the near-infrared light intensity of the vein sensor according to the comparison result.

[0007] Optionally, dividing the grayscale image into a plurality of blocks includes: taking a central pixel point of the grayscale image as a circle center, dividing the grayscale image into a plurality of concentric circular areas with different radii, and taking each concentric circular area as a block.

[0008] Optionally, after dividing the grayscale image into several concentric circle areas with different radii, it also includes: dividing all concentric circle areas into several sector ring areas; wherein the method also includes: calculating the grayscale average value of each sector ring area, and comparing the grayscale average values ​​of different sector ring areas within the same concentric circle area.

[0009] Optionally, comparing the sizes of the grayscale average values ​​of different blocks includes: counting all grayscale values ​​of each block to form a grayscale histogram corresponding to each block; and comparing the sizes of the grayscale average values ​​of different blocks by comparing the grayscale histogram corresponding to each block.

[0010] Optionally, the calculating the grayscale average value of each block includes: summing up all grayscale values ​​in each block and dividing the sum by the number of pixels in the corresponding block to obtain the grayscale average value of the block.

[0011] According to another aspect of the present invention, a near-infrared light intensity uniformity detection device is provided, comprising: an acquisition module, used to acquire an image to be processed, wherein the image to be processed is an image taken by a vein sensor of a reference surface within a capture range, and the reference surface is a white plane on a reference object that can cover the near-infrared light irradiation range of the vein sensor; a conversion module, used to convert the image to be processed into a grayscale image to obtain a grayscale value of each pixel; a division module, used to divide the grayscale image into multiple blocks; a calculation module, used to calculate the grayscale average value of each block; a comparison module, used to compare the grayscale average values ​​of different blocks to obtain a comparison result; and a determination module, used to determine the uniformity of the near-infrared light intensity of the vein sensor according to the comparison result.

[0012] A computer device comprises: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the near-infrared light intensity uniformity detection method by executing the computer instructions.

[0013] A computer-readable storage medium stores computer instructions, wherein the computer instructions are used to enable the computer to execute the near-infrared light intensity uniformity detection method.

[0014] The technical solution of the present invention has the following advantages:

[0015] A near-infrared light intensity uniformity detection method provided by the present invention comprises the following steps: obtaining an image to be processed, wherein the image to be processed is an image taken by a vein sensor of a reference surface within a capture range, and the reference surface is a white plane on a reference object that can cover the near-infrared light irradiation range of the vein sensor; converting the image to be processed into a grayscale image to obtain a grayscale value of each pixel; dividing the grayscale image into a plurality of blocks; calculating the grayscale average value of each block; comparing the grayscale average values ​​of different blocks to obtain a comparison result; and determining the uniformity of the near-infrared light intensity of the vein sensor according to the comparison result. When the operator needs to perform uniformity detection, the reference surface is placed within the capture range of the vein sensor, and the vein sensor is used to capture the image to be processed on the reference surface. The reference surface is a white plane that can evenly reflect near-infrared light, which helps to improve the quality of the image to be processed. The operator then converts the image to be processed into a grayscale image to obtain the grayscale value of each pixel, and then divides the grayscale image into multiple blocks, calculates the grayscale average of each block, compares the grayscale averages of each block, and determines the uniformity of the near-infrared light intensity of the vein sensor based on the comparison results. The above operation does not require the use of special equipment. The image to be processed captured by the vein sensor can be used for calculation and processing to accurately detect the uniformity of the near-infrared light intensity, so as to improve the design of the near-infrared light source of the vein sensor in a targeted manner.

[0016] 2. The present invention provides a method for detecting the uniformity of near-infrared light intensity, wherein the grayscale image is divided into a plurality of blocks, including: taking the central pixel point of the grayscale image as the center of the circle, dividing the grayscale image into a plurality of concentric circular ring areas of different radii, and taking each concentric circular ring area as a block. In the step of the operator dividing the grayscale image into a plurality of blocks, the reason for dividing the grayscale image into a plurality of concentric circular ring areas of different radii rather than other shapes is that the near-infrared light source of the vein sensor is distributed around the camera and is distributed in a circular pattern. Therefore, dividing the grayscale image into a plurality of concentric circular rings of different radii can more accurately detect the uniformity of the near-infrared light intensity.

[0017] 3. A near-infrared light intensity uniformity detection method provided by the present invention, after dividing the grayscale image into a number of concentric circle areas with different radii, further includes: dividing all concentric circle areas into a number of fan-ring areas; wherein the method also includes: calculating the grayscale average value of each fan-ring area, and comparing the grayscale average values ​​of different fan-ring areas in the same concentric circle area. In order to further analyze the changes in the near-infrared light intensity of different areas within the same concentric circle, the operator divides the grayscale image into a number of different concentric circle areas, and then divides the concentric circle area into a number of different fan-ring areas, calculates the grayscale average value of each fan-ring area, compares the grayscale average values ​​of different fan-ring areas in the same concentric circle area, and further analyzes the uniformity of the near-infrared light intensity of the vein sensor based on the comparison results.

[0018] 4. A near-infrared light intensity uniformity detection method provided by the present invention, wherein the size of the grayscale average values ​​of different blocks is compared, including: counting all grayscale values ​​of each block to form a grayscale histogram corresponding to each block; comparing the sizes of the grayscale average values ​​of different blocks by comparing the grayscale histogram corresponding to each block. When the operator needs to compare the sizes of the grayscale average values ​​of different blocks, all grayscale values ​​of each block are counted, and a grayscale histogram is formed according to the frequency of occurrence of different grayscale values, and then the sizes of the grayscale average values ​​of different blocks are compared by comparing the grayscale histogram corresponding to each block. The grayscale histogram can more intuitively show the difference between the grayscale average values ​​between different blocks, and more accurately detect the uniformity of near-infrared light intensity.

[0019] 5. A near-infrared light intensity uniformity detection method provided by the present invention, wherein the grayscale average value of each block is calculated, including: summing up all grayscale values ​​in each block and dividing by the number of pixels in the corresponding block to obtain the grayscale average value of the block. When the operator needs to calculate the grayscale average value of each block, the calculation method is as follows: summing up all grayscale values ​​in each block and dividing by the number of pixels in the corresponding block to obtain the grayscale average value of the block. The above method enables the operator to quickly and conveniently obtain the grayscale average value of each block.

[0020] 6. A near-infrared light intensity uniformity detection device provided by the present invention includes: an acquisition module, used to acquire an image to be processed, wherein the image to be processed is an image taken by a vein sensor of a reference surface within a capture range, and the reference surface is a white plane on a reference object that can cover the near-infrared light irradiation range of the vein sensor; a conversion module, used to convert the image to be processed into a grayscale image to obtain the grayscale value of each pixel; a division module, used to divide the grayscale image into multiple blocks; a calculation module, used to calculate the grayscale average value of each block; a comparison module, used to compare the grayscale average values ​​of different blocks to obtain a comparison result; a determination module, used to determine the uniformity of the near-infrared light intensity of the vein sensor based on the comparison result. When the operator needs to perform uniformity detection, the reference surface is placed within the capture range of the vein sensor, and the vein sensor is used to capture the image to be processed on the reference surface. The reference surface is a white plane that can completely reflect the near-infrared light, which helps to improve the quality of the image to be processed. The operator then converts the image to be processed into a grayscale image to obtain the grayscale value of each pixel, and then divides the grayscale image into multiple blocks, calculates the grayscale average of each block, compares the grayscale averages of each block, and determines the uniformity of the near-infrared light intensity of the vein sensor based on the comparison results. The above operation does not require the use of special equipment. The image to be processed captured by the vein sensor can be used for calculation and processing to accurately detect the uniformity of the near-infrared light intensity, so as to improve the design of the near-infrared light source of the vein sensor in a targeted manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 This is a flow chart of a near-infrared light intensity uniformity detection method in Example 1 of the present invention;

[0023] Figure 2 This is a flow chart of calculating the grayscale average value in Example 1 of the present invention;

[0024] Figure 3 This is a principle block diagram of a near-infrared light intensity uniformity detection device in Embodiment 2 of the present invention;

[0025] Figure 4 Schematic diagram of a computer device in Embodiment 3 of the present invention.

[0026] Explanation of the accompanying drawings: 301, acquisition module; 302, conversion module; 303, division module; 304, calculation module; 405, comparison module; 406, determination module; 3031, first submodule; 3032, second submodule; 3041, third submodule; 3042, fourth submodule; 3051, fifth submodule; 3052, sixth submodule; 401, processor; 402, memory; 403, bus. DETAILED DESCRIPTION

[0027] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0028] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0029] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, it can also be the internal connection of two components, it can be a wireless connection, or it can be a wired connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0031] Example 1

[0032] The present application provides a near-infrared light intensity uniformity detection method, which is mainly used for the near-infrared light intensity uniformity detection of a vein sensor. Specifically, it is necessary to use a reference object with a white plane to capture the near-infrared image irradiated on the white plane through the vein sensor, and then use a computer device to execute the detection method of the embodiment of the present invention to identify the uniformity of the near-infrared light intensity of the vein sensor through the image. Specifically, the detection method of the embodiment of the present invention is as follows Figure 1-2 As shown, the following steps are included:

[0033] S100, obtaining an image to be processed, wherein the image to be processed is an image captured by the vein sensor of a reference surface within a capture range, and the reference surface is a white plane on a reference object that can cover a near-infrared light irradiation range of the vein sensor.

[0034] Specifically, the reference surface is a white plane on a reference object that can cover the near-infrared light irradiation range of the vein sensor, and the reference surface should be placed within the capture range of the vein sensor. For the selection of the reference surface, the operator can use professional printed white paper, such as Colotech+, or a curtain or whiteboard. In actual use, interference from other external light sources should be avoided. The methods to avoid interference from other external light sources mainly include the following aspects: on the one hand, using the vein sensor to take pictures on the reference surface in a darker environment, and on the other hand, a shell made of light-blocking material is placed on the periphery of the vein sensor and the reference surface.

[0035] The reference surface should be placed in the optical path of the near-infrared light emitted by the vein sensor, and the near-infrared light should be able to completely illuminate the reference surface.

[0036] S200, converting the image to be processed into a grayscale image to obtain the grayscale value of each pixel.

[0037] Specifically, the resolution of the image to be processed and the grayscale image is M*N, and the coordinates of a pixel in the grayscale image are expressed as gray[y, x], where x∈{0, 1, 2…(M-1)}, y∈{0, 1, 2…(N-1)}.

[0038] Grayscale value refers to the color value of each pixel when converting grayscale image to RGB. The logarithmic relationship between white and black is divided into several levels, which is called "grayscale". In the computer field, grayscale image is an image with only one sampled color per pixel. Such images are usually displayed as grayscale from the darkest black to the brightest white. Grayscale image is different from black and white image. In the field of computer image, black and white image only has two colors, black and white, while grayscale image has many levels of color depth between black and white.

[0039] RGB is a color standard. R refers to red, G refers to green, and B refers to blue. These three colors can be superimposed in different proportions to obtain a variety of colors. Different proportions correspond to different grayscale values. The common grayscale value ∈ [0, 255], white is 255, and black is 0.

[0040] For example, the grayscale value of the pixel with coordinates [100, 100] in the grayscale image is 150, which can be expressed as gray[100, 100]=150.

[0041] S300, dividing the grayscale image into a plurality of blocks.

[0042] Specifically, the grayscale image is divided into a number of different blocks, and the division method is arbitrary division, for example, the grayscale image is divided into a grid shape or a strip shape.

[0043] It should be noted that the near-infrared light source of the vein sensor is distributed around the camera and is distributed in a circular manner. Therefore, in order to more accurately describe and detect the uniformity of the near-infrared light distributed in the circular manner, step S300 of the embodiment of the present invention may adopt an optional implementation method, which specifically includes:

[0044] S310 , taking the central pixel point of the grayscale image as the center of the circle, dividing the grayscale image into a plurality of concentric circular areas with different radii, and taking each concentric circular area as a block.

[0045] Specifically, the coordinates of the center pixel of the grayscale image are (X = (M-1) / 2, Y = (M-1) / 2), the outer radius of the concentric ring is R, and the inner radius is r, where 0 ≤ r <R≤0.5*[(M–1) 2 +(N–1) 2 ] 0.5 In theory, the grayscale image can be divided into countless concentric rings, but in actual operation, the grayscale image can be divided into a preset number of concentric rings. The more concentric rings are divided, the more accurate the detection of the uniformity of near-infrared light intensity is. It is worth noting that the inner circle radius r of the smallest concentric ring is 0, that is, the smallest concentric ring is a circle with a radius of R.

[0046] S320: Divide all concentric circle areas into a plurality of sector ring areas.

[0047] Specifically, step S320 is executed after step S310. Taking the central pixel point as the origin, several rays are drawn outwards. These several rays can divide the concentric circle region into several fan-shaped ring regions. In theory, the concentric circle region can be divided into an infinite number of fan-shaped ring regions, but in actual operation, the concentric circle region can be divided into a preset number of fan-shaped ring regions. Each fan-shaped ring region is regarded as a block. The more the number of divided fan-shaped ring regions, the more accurate the detection of the near-infrared light intensity uniformity. Among them, the preset number can be divided by angles. For example, taking 30° as the interval, taking the central pixel point as the origin, 12 rays are drawn outwards, and each concentric circle region is divided into 12 fan-shaped ring regions.

[0048] S400, calculate the average gray value of each block.

[0049] Specifically, sum up all the gray values in each block and divide by the number of pixel points in the corresponding block to obtain the average gray value of the block.

[0050] Among them, step S400 includes sub-steps S410 and S420:

[0051] S410, calculate the average gray value of each concentric circle region.

[0052] Specifically, the coordinates of a certain pixel point are (x, y), and the distance of this pixel point from the coordinates of the central pixel point is d, where d = [(x – (M - 1) / 2) 2 +(y – (N – 1)) 2 0.5 , when r ≤ d < R, this pixel point is located in the concentric circle region with the outer circle radius of R and the inner circle radius of r. Among them, the specific calculation method is as follows (taking a grayscale image with a resolution of 640 * 480 as an example):

[0053]

[0054] The average value of the gray level in this region: s = sum / i

[0055] The operator sequentially substitutes the outer circle radius R and the inner circle radius r of different concentric circle regions, so as to calculate the average gray value of each concentric circle region.

[0056] It should be noted that this step s410 corresponds to step s310, and s410 is executed after s310.

[0057] S420, calculate the average gray value of each fan-shaped ring region.

[0058] Specifically, sum up the gray values of all pixel points in each fan-shaped ring region and divide by the number of pixel points in the corresponding fan-shaped ring region, so as to obtain the average gray value in each fan-shaped ring region.​

[0059] S500, comparing the grayscale average values ​​of different blocks to obtain a comparison result.

[0060] Specifically, for the grayscale average values ​​of different blocks, they are compared in pairs to obtain multiple comparison sub-results. For example, the divided blocks include Q1, Q2, and Q3. When making comparisons, Q1 is compared with Q2 to obtain comparison sub-result B1; Q1 is compared with Q3 to obtain comparison sub-result B2; Q2 is compared with Q3 to obtain comparison sub-result B3. The comparison sub-results are aggregated to form a set to obtain a comparison result. The comparison sub-results described above can be the difference or division of the two, and correspondingly, the comparison sub-results are the difference or ratio.

[0061] Of course, in an embodiment of the present invention, the grayscale average values ​​of different blocks can also be used for overall judgment, for example, a corresponding grayscale histogram is generated for each block, or the variance of the grayscale average values ​​of all blocks is calculated, so as to make an overall judgment on the uniformity of near-infrared light intensity between different blocks.

[0062] In an optional implementation manner, step S500 includes:

[0063] S510, counting all grayscale values ​​of each block to form a grayscale histogram corresponding to each block;

[0064] The grayscale average values ​​of different blocks are compared by comparing the grayscale histograms corresponding to each block.

[0065] Specifically, the grayscale histogram corresponding to each block can be obtained according to the frequency of occurrence of the same grayscale value in the block. It should be noted that when comparing the grayscale histograms corresponding to different blocks, on the one hand, the comparison is made between different concentric circle areas, and on the other hand, the comparison is made between different sector ring areas in the same concentric circle area.

[0066] The above comparison method has the advantage of being intuitive. Through the grayscale histogram, the operator can easily and quickly compare the grayscale average values ​​of different blocks. The disadvantage is that there is no accurate data to support it.

[0067] The above step S500 may further include:

[0068] S520, calculating the variance of the grayscale mean value of the grayscale image.

[0069] Specifically, the grayscale average values ​​of all sector ring areas in the grayscale image are taken as calculation objects, and the variance of the grayscale average value of the grayscale image is calculated according to the variance calculation formula, and the variance is recorded as the uniformity parameter A.

[0070] The advantage of the above comparison method is accuracy. Through the uniformity parameter A, the operator can accurately determine whether the near-infrared light intensity distribution is uniform. The disadvantage is that it is not intuitive enough.

[0071] Therefore, both step S510 and step S520 should be performed, so as to more accurately and intuitively compare the grayscale average values ​​of different blocks and obtain a comparison result, which is recorded as the uniformity parameter A.

[0072] S600: Determine the uniformity of the near-infrared light intensity of the vein sensor according to the comparison result.

[0073] Specifically, the uniformity parameter A is compared with a preset threshold value C. When A is less than C, the near-infrared light intensity distribution is determined to be uniform, and when A is greater than or equal to C, the near-infrared light intensity distribution is determined to be uneven. When the near-infrared light intensity distribution is uneven, the operator adjusts the intensity of the near-infrared light or modifies the light guide structure to make the near-infrared light intensity distribution uniform.

[0074] The embodiment of the present application provides a method for detecting uniformity of near-infrared light intensity, and its principle is as follows: when the operator needs to perform uniformity detection, the reference surface is placed within the capture range of the vein sensor, and the vein sensor is used to take a picture of the image to be processed on the reference surface. The reference surface is a white plane that can evenly reflect the near-infrared light, thereby helping to improve the quality of the image to be processed. The operator then converts the image to be processed into a grayscale image, thereby obtaining the grayscale value of each pixel point, and then divides the grayscale image into multiple blocks, calculates the grayscale average value of each block, compares the grayscale average values ​​of each block, and determines the uniformity of the near-infrared light intensity of the vein sensor based on the comparison result. The above operation does not require the use of special equipment. The image to be processed taken by the vein sensor is used for calculation and processing, which can accurately detect the uniformity of the near-infrared light intensity and improve the design of the near-infrared light source of the vein sensor.

[0075] Example 2

[0076] The embodiment of the present application provides a near-infrared light intensity uniformity detection device, which can be used to perform embodiment 1 ( Figure 1 ), specifically, as Figure 3 As shown, including:

[0077] An acquisition module 301 is used to acquire an image to be processed, wherein the image to be processed is an image captured by the vein sensor of a reference surface within a capture range, and the reference surface is a white plane on a reference object that can cover the near-infrared light irradiation range of the vein sensor;

[0078] A conversion module 302 is used to convert the image to be processed into a grayscale image to obtain the grayscale value of each pixel;

[0079] A division module 303, used for dividing the grayscale image into a plurality of blocks;

[0080] Specifically, the division module includes a first submodule 3031 and a second submodule 3032:

[0081] The first submodule 3031 is used to divide the grayscale image into a plurality of concentric circle areas, wherein the centers of all the concentric circles are the central pixel points of the grayscale image;

[0082] The second submodule 3032 is used to divide the concentric circle area into a plurality of sector ring areas;

[0083] A calculation module 304 is used to calculate the grayscale average value of each block;

[0084] Specifically, the calculation module includes a third submodule 3041 and a fourth submodule 3042:

[0085] The third submodule 3041 is used to calculate the grayscale average value of each concentric circle area;

[0086] The fourth submodule 3042 is used to calculate the grayscale average value of each sector ring area;

[0087] A comparison module 305 is used to compare the grayscale average values ​​of different blocks to obtain a comparison result;

[0088] Specifically, the comparison module includes a fifth submodule 3051 and a sixth submodule 3052:

[0089] The fifth submodule 3051 is used to count all gray values ​​of each block to form a gray histogram corresponding to each block;

[0090] The sixth submodule 3052 is used to calculate the variance of the grayscale mean value of the grayscale image.

[0091] The determination module 306 is used to determine the uniformity of the near-infrared light intensity of the vein sensor according to the comparison result.

[0092] For a detailed description, please refer to the above method embodiment, which will not be repeated here.

[0093] The embodiment of the present application provides a near-infrared light intensity uniformity detection device, and its principle is as follows: when the operator needs to perform uniformity detection, the reference surface is placed within the capture range of the vein sensor, and the vein sensor is used to take a picture of the image to be processed on the reference surface. The reference surface is a white plane that can make the near-infrared light evenly reflected, which helps to improve the quality of the image to be processed. Then the operator converts the image to be processed into a grayscale image, thereby obtaining the grayscale value of each pixel point, and then divides the grayscale image into multiple blocks, calculates the grayscale average value of each block, compares the grayscale average values ​​of each block, and determines the uniformity of the near-infrared light intensity of the vein sensor based on the comparison result. The above operation does not require the use of special equipment. The image to be processed taken by the vein sensor is used for calculation and processing, and the uniformity of the near-infrared light intensity can be accurately detected, so as to improve the design of the near-infrared light source of the vein sensor in a targeted manner.

[0094] Example 3

[0095] The embodiment of the present invention also provides a computer device, such as Figure 4 As shown, the device includes a processor 401 and a memory 402, wherein the processor 401 and the memory 402 may be connected via a bus 403 or other means. Figure 4 The connection via bus 403 is taken as an example.

[0096] The processor 401 may be a central processing unit (CPU). The processor 401 may also be other general-purpose processors, digital signal processors (DSP), graphics processors (GPU), embedded neural network processors (NPU), or other dedicated deep learning coprocessors, application specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0097] The memory 402, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs and modules. The processor 401 executes various functional applications and data processing of the processor 401 by running the non-transitory software programs, instructions and modules stored in the memory, that is, implements the near-infrared light intensity uniformity detection method in the above method embodiment.

[0098] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 402 may optionally include a memory 402 remotely arranged relative to the processor, and these remote memories 402 may be connected to the processor 401 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0099] For details of the above computer equipment, please refer to Figures 1 to 3 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.

[0100] The embodiment of the present invention also provides a non-transitory computer storage medium, which stores computer executable instructions, and the computer executable instructions can execute the advertising delivery method in any of the above method embodiments. The storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0101] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A near-infrared light intensity uniformity detection method, characterized in that: The steps include: Acquire an image to be processed, wherein the image to be processed is an image captured by the vein sensor of a reference surface within a capture range, the reference surface being a white plane on a reference object that can cover the near-infrared light irradiation range of the vein sensor; the near-infrared light sources of the vein sensor are distributed around the camera and are distributed in a circular pattern; Convert the image to be processed into a grayscale image to obtain the grayscale value of each pixel; Dividing the grayscale image into a plurality of blocks; Calculate the grayscale average of each block; Compare the grayscale average values ​​of different blocks to obtain the comparison results; determining the uniformity of the near-infrared light intensity of the vein sensor according to the comparison result; The step of dividing the grayscale image into a plurality of blocks comprises: Taking the central pixel point of the grayscale image as the center of the circle, the grayscale image is divided into a number of concentric circular areas with different radii, and each concentric circular area is regarded as a block.

2. A near-infrared light intensity uniformity detection method according to claim 1, characterized in that: After dividing the grayscale image into a plurality of concentric circular areas with different radii, the method further includes: Divide all concentric circle areas into several sector ring areas; The method further comprises: calculating the grayscale average value of each sector ring area, and comparing the grayscale average values ​​of different sector ring areas within the same concentric circle area.

3. A near-infrared light intensity uniformity detection method according to any one of claims 1-2, characterized in that: The comparing the grayscale average values ​​of different blocks includes: Count all grayscale values ​​of each block to form a grayscale histogram corresponding to each block; The grayscale average values ​​of different blocks are compared by comparing the grayscale histograms corresponding to each block.

4. A near-infrared light intensity uniformity detection method according to any one of claims 1-2, characterized in that: The step of calculating the grayscale average value of each block includes: Sum all grayscale values ​​in each block and divide it by the number of pixels in the corresponding block to obtain the grayscale average value of the block.

5. A near-infrared light intensity uniformity detection device, characterized in that: include: An acquisition module (301) is used to acquire an image to be processed, wherein the image to be processed is an image captured by the vein sensor of a reference surface within a capture range, the reference surface being a white plane on a reference object that can cover the near-infrared light irradiation range of the vein sensor; the near-infrared light source of the vein sensor is distributed around the camera and is distributed in a circular pattern; A conversion module (302) is used to convert the image to be processed into a grayscale image to obtain the grayscale value of each pixel; A division module (303), the division module (303), is used to divide the grayscale image into a plurality of blocks; The dividing the grayscale image into a plurality of blocks includes: taking the central pixel point of the grayscale image as the center, dividing the grayscale image into concentric circular areas with different radii, and taking each concentric circular area as a block; A calculation module (304), used for calculating the grayscale average value of each block; A comparison module (305) is used to compare the grayscale average values ​​of different blocks to obtain a comparison result; A determination module (306) is used to determine the uniformity of the near-infrared light intensity of the vein sensor according to the comparison result.

6. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the near-infrared light intensity uniformity detection method according to any one of claims 1 to 4 by executing the computer instructions.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the near-infrared light intensity uniformity detection method according to any one of claims 1 to 4.

Images