Image digitization discrimination detection method

Abstract

The invention belongs to the field of in-vitro diagnostic instruments, and discloses an image digitization discrimination detection method, which comprises the following steps: step 1, fixing the positions of a camera and test paper, and carrying out light supplement to shoot an image of the test paper; 2, selecting a rectangular image of a CT line area of the test paper, wherein the image covers a CT line and a peripheral blank; and step 3, according to the rectangular image selected in the step 2, calculating gray values of all pixels, firstly calculating a mean value of the gray values of all the pixels, then calculating a standard deviation, and finally calculating a variable coefficient of the image. The color depth of the target area is judged through the CV method, the color judgment accuracy is improved, and then the result judgment accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of in vitro diagnostic instruments, and particularly to an image digital discrimination detection method. Background Art

[0002] With the development and utilization of technology, colloidal gold detection and drug sensitivity tests have been widely applied, which are simple to operate and highly practical. However, most current detections rely on visual observation and recording, requiring a large amount of manpower. Objective error factors are easily introduced during the use process, leading to misjudgment of the detection results. In this application, digital image acquisition and program interpretation are used to improve stability, efficiency, and accuracy. Summary of the Invention

[0003] The purpose of the present invention is to provide an image digital discrimination detection method to solve the problems raised in the above background art.

[0004] To achieve the above purpose, the present invention provides the following technical solutions:

[0005] An image digital discrimination detection method includes the following steps:

[0006] Step 1, fix the positions of the camera and the test strip, and take a supplementary light image of the test strip.

[0007] Step 2, select a rectangular image of the CT line area of the test strip, where the image covers the CT line and the surrounding blank.

[0008] Step 3, according to the rectangular image selected in Step 2, calculate the gray values of all pixels within the rectangular image. First, calculate the mean μ of all pixel gray values, and then calculate the standard deviation where X i is the gray value of the i-th pixel, σ is the standard deviation of the pixel gray values, n is the number of pixels, and finally calculate the coefficient of variation C of the image v :

[0009] The present invention also provides an image digital discrimination detection method, which is characterized by including the following steps:

[0010] Step 1, fix the camera and the drug sensitivity plate, and take a supplementary light image of the drug sensitivity plate.

[0011] Step 2, for each well of the drug sensitivity plate in Step 1, select a central circular image, where the central circular image covers the central bacterial colony aggregation area of the drug sensitivity plate image and the surrounding blank.

[0012] Step 3, according to the central circular image in Step 2, calculate the gray values of all pixels within the central circular image. First, calculate the mean μ of all pixel gray values, and then calculate the standard deviation where X iis the gray value of the i-th pixel, σ is the standard deviation of the pixel gray values, n is the number of pixels, and finally the coefficient of variation C of the image is calculated. v :

[0013] Further, the drug sensitivity plate is a 96-well drug sensitivity plate.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: By using the CV method to interpret the depth of color in the target area, the present invention improves the accuracy of color interpretation, and further improves the accuracy of result determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is the test strip image taken in Example 1.

[0016] Figure 2 is the operation schematic diagram of selecting a rectangular image on the test strip image in Example 1.

[0017] Figure 3 is the operation schematic diagram of selecting a rectangular image on the test strip image in Example 2.

[0018] Figure 4 is the corresponding C value obtained by selecting rectangular images at different positions on the test strip image of the present invention. v value result schematic diagram.

[0019] Figure 5 is the well position diagram taken on the 96-well drug sensitivity plate in Example 3.

[0020] Figure 6 is the operation schematic diagram of selecting a central circular image on the well position diagram in Example 3.

[0021] Figure 7 is the operation schematic diagram of selecting a central circular image on the well position diagram in Example 4. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] Example 1

[0024] Please refer to Figure 1 - Figure 2 , an image digital discrimination detection method for colloidal gold photographing and interpretation, comprising the following steps:

[0025] Step 1, fix the positions of the camera and the test strip, and take a picture of the test strip with supplementary light.

[0026] Refer to Figure 1 , the photographed picture is the whole or multiple test strips.

[0027] Step 2, select a rectangular image of the CT line area of the test strip, and the image covers the CT line and the surrounding blank area.

[0028] Refer to Figure 2 , select a rectangular image with a width of 30 pixels and a height of 10 pixels of the first CT line in the example test strip.

[0029] Step 3, according to the rectangular image selected in Step 2, calculate the gray values of all pixels in the rectangular image. Refer to Table 1 for all pixel gray values. Calculate all gray values. First, calculate the average value of all pixel gray values as μ, and then calculate the standard deviation where, X i is the gray value of the i-th pixel, σ is the standard deviation of the pixel gray values, n is the number of pixels, and finally calculate the coefficient of variation C v : According to Table 1, C V The result value is 0.25.

[0030] 167 165 163 164 163 160 156 150 136 125 117 109 102 92 86 80 72 72 83 106 136 154 162 165 166 166 165 166 165 164 165 166 163 166 163 163 161 159 152 137 125 119 110 103 94 84 78 74 74 84 105 136 153 161 167 167 165 165 167 166 166 166 167 164 166 163 165 162 159 149 138 127 117 109 101 93 84 79 73 72 83 107 134 154 163 164 167 167 166 166 167 165 167 165 167 165 166 163 163 156 147 139 126 118 111 101 92 85 79 74 71 83 108 138 154 164 162 166 165 165 165 164 165 167 166 168 164 167 165 162 157 148 138 128 116 110 101 93 85 77 72 73 84 107 138 157 162 163 164 165 165 166 163 165 165 165 164 164 164 164 161 160 151 140 128 115 110 101 93 84 77 70 70 83 108 138 155 162 164 164 166 167 167 164 165 165 164 164 168 164 164 164 159 150 140 128 118 110 101 92 86 76 72 70 83 108 136 154 161 164 166 167 166 167 165 167 168 166 164 164 165 162 163 160 149 138 129 118 109 102 92 85 77 72 71 82 106 136 155 160 166 167 167 167 167 166 169 168 165 164 166 167 163 162 161 149 138 129 118 108 101 93 84 77 70 69 80 106 136 153 160 165 166 165 167 166 166 169 167 166 163 166 166 166 165 160 150 138 127 118 108 101 92 84 76 69 69 79 105 134 153 161 165 165 162 164 167 168 168 166 165 164 165 165 165 164 160 151 136 125 118 109 101 92 82 74 69 68 77 103 135 155 162 164 165 164 165 166 166 167 165

[0031] Table 1

[0032] Example 2

[0033] The difference between this example and Example 1 is that the rectangular image selected in Step 2 is Figure 3 at the position shown, then all pixel gray values are shown in Table 2, and the obtained C V The result is 0.013.

[0034] 166 166 166 165 165 164 164 165 165 164 164 161 161 158 161 162 163 164 166 163 162 167 164 165 164 166 166 166 168 167 169 166 163 164 164 163 165 165 165 164 164 167 161 161 162 163 163 161 157 161 161 162 166 164 162 165 167 168 167 164 167 166 163 163 164 166 162 164 168 164 164 163 162 160 164 162 163 161 160 163 165 165 163 164 168 165 165 163 165 167 166 167 168 164 163 164 166 163 165 165 163 166 166 165 162 160 161 161 159 160 161 163 165 166 163 164 166 163 164 165 165 168 168 165 164 161 164 164 164 162 161 164 166 165 163 164 160 159 159 160 164 161 163 165 165 162 164 163 162 166 164 163 164 164 165 158 162 165 162 165 163 162 163 164 165 163 160 161 162 159 163 165 165 160 164 165 164 164 162 161 165 165 165 164 166 162 164 165 163 163 164 163 164 166 166 164 164 162 161 159 160 161 164 165 164 163 164 164 165 164 162 166 165 165 166 167 167 166 164 165 166 167 164 163 166 165 163 163 162 161 159 159 159 163 163 164 165 163 163 166 165 163 166 164 168 164 164 167 166 164 165 165 165 166 165 164 166 165 163 161 162 163 159 161 163 163 163 165 166 164 165 165 162 165 164 167 164 164 165 165 165 166 167 165 165 165 166 166 164 162 164 163 162 159 163 165 164 164 164 165 165 165 165 163 165 166 163 165 164 163 165 163 167 166 165 166 166 167 165 164 161 164 162 161 160 165 163 163 163 165 167 166 164 167 165 167 166 164 163 163 165

[0035] Table 2

[0036] Comparing Example 1 and Example 2, it can be seen that the larger the C V value, the darker the corresponding CT line color.

[0037] The present invention also selects rectangular images at more different positions of the test strip to obtain result values of different CT line color depths. The results are as Figure 4 shown, further indicating that the larger the C V value, the darker the corresponding CT line color, which can prove the accuracy of the present invention.

[0038] Example 3

[0039] Please refer to Figure 5 - Figure 7 , an image digitization discrimination detection method for drug sensitivity test photographing and interpretation, including the following steps:

[0040] Step 1: Fix the camera and the 96-well drug sensitivity plate, and supplement light to take pictures of the drug sensitivity plate.

[0041] As Figure 5 shown, the captured image is the image of each well.

[0042] Step 2: For the image of each well in Step 1, select the central circular image. The central circular image covers the central bacterial aggregation area and the surrounding blank area of the drug sensitivity plate in the image.

[0043] Refer to Figure 6 , and select a circle with a radius of 35 pixels at the center of the well of the exemplary drug sensitivity plate.

[0044] Step 3: According to the central circular image in Step 2, calculate the gray values of all pixels within the central circular image. First, calculate the average value of all pixel gray values as μ, and then calculate the standard deviation where, X i is the gray value of the i-th pixel, σ is the standard deviation of the pixel gray values, n is the number of pixels, and finally calculate the coefficient of variation C v : The obtained CV result value is 0.414.

[0045] Example 4

[0046] The difference between this example and Example 3 is that in Step 2, select the Figure 7 image of the well position shown, and the obtained result is 0.019.

[0047] Comparing Example 3 and Example 4, it can be seen that the larger the C V value, the darker the color of the bacterial aggregation in the corresponding well.

[0048] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting and distinguishing digital images, characterized in that: The following steps are involved: Step 1, fix the position of the camera and the test paper, and shoot the image of the test paper with fill light; Step 2, select a rectangular image of the CT line area of ​​the test paper, the image covers the CT line and the surrounding blank; Step 3: Calculate the grayscale values ​​of all pixels in the rectangular image according to the rectangular image selected in step 2. First calculate the mean μ of the grayscale values ​​of all pixels, and then calculate the standard deviation Among them, X i is the gray value of the i-th pixel, σ is the standard deviation of the pixel gray value, n is the number of pixels, and finally the coefficient of variation C of the image is calculated v :

2. A method for detecting and distinguishing digital images, characterized in that: The following steps are involved: Step 1, fix the camera and the drug sensitivity plate, and take an image of the drug sensitivity plate with fill light; Step 2, for each well of the drug-sensitive plate in step 1, a central circular image is selected, where the central circular image covers the central bacterial colony cluster area of ​​the drug-sensitive plate and the surrounding blank area; Step 3: Calculate the grayscale values ​​of all pixels in the central circular image according to the central circular image in step 2. First calculate the mean μ of the grayscale values ​​of all pixels, and then calculate the standard deviation Among them, X i is the gray value of the i-th pixel, σ is the standard deviation of the pixel gray value, n is the number of pixels, and finally the coefficient of variation C of the image is calculated v :

3. The method for detecting and distinguishing digital images according to claim 2, characterized in that: The drug sensitivity plate is a 96-well drug sensitivity plate.

Images