CN116626029B - Detection method for color difference of cobalt chloride test paper for diabetes - Google Patents
Detection method for color difference of cobalt chloride test paper for diabetes Download PDFInfo
- Publication number
- CN116626029B CN116626029B CN202310889567.8A CN202310889567A CN116626029B CN 116626029 B CN116626029 B CN 116626029B CN 202310889567 A CN202310889567 A CN 202310889567A CN 116626029 B CN116626029 B CN 116626029B
- Authority
- CN
- China
- Prior art keywords
- connected domain
- value
- pixel point
- gray
- test paper
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 141
- GVPFVAHMJGGAJG-UHFFFAOYSA-L cobalt dichloride Chemical compound [Cl-].[Cl-].[Co+2] GVPFVAHMJGGAJG-UHFFFAOYSA-L 0.000 title claims abstract description 66
- 206010012601 diabetes mellitus Diseases 0.000 title claims abstract description 43
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000004075 alteration Effects 0.000 claims description 3
- 239000003153 chemical reaction reagent Substances 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 2
- 239000007788 liquid Substances 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 20
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000009826 distribution Methods 0.000 description 19
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 12
- 210000004243 sweat Anatomy 0.000 description 11
- 208000024891 symptom Diseases 0.000 description 8
- 238000005259 measurement Methods 0.000 description 5
- 210000000106 sweat gland Anatomy 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 208000008960 Diabetic foot Diseases 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000028327 secretion Effects 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 230000036285 pathological change Effects 0.000 description 2
- 231100000915 pathological change Toxicity 0.000 description 2
- 208000025865 Ulcer Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- SAXCKUIOAKKRAS-UHFFFAOYSA-N cobalt;hydrate Chemical compound O.[Co] SAXCKUIOAKKRAS-UHFFFAOYSA-N 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003345 hyperglycaemic effect Effects 0.000 description 1
- 201000001421 hyperglycemia Diseases 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 201000001119 neuropathy Diseases 0.000 description 1
- 230000007823 neuropathy Effects 0.000 description 1
- 210000000578 peripheral nerve Anatomy 0.000 description 1
- 208000033808 peripheral neuropathy Diseases 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 231100000397 ulcer Toxicity 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/75—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated
- G01N21/77—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator
- G01N21/78—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator producing a change of colour
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/8483—Investigating reagent band
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Software Systems (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Plasma & Fusion (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of test paper color change analysis, in particular to a detection method for color difference of a cobalt chloride test paper for diabetes, which comprises the following steps: acquiring a connected domain in a surface gray scale image of the used diabetes cobalt chloride test paper; obtaining the region information richness of each connected domain according to the pixel fluctuation degree, texture information and gray difference conditions in the connected domain; determining gray weights according to the difference between each pixel point and the gray minimum value in the connected domain, and further obtaining a color coefficient representation value of each pixel point; and clustering the pixel points in the surface gray level image according to the color coefficient representation value of each pixel point to obtain two categories, and determining the color difference detection result of the cobalt chloride test paper according to the gray level value of the pixel points in the two categories, the number of the pixel points and the unused test paper image. The application ensures that the detection result of the color difference of the cobalt chloride test paper for diabetes is more accurate.
Description
Technical Field
The application relates to the technical field of test paper color change analysis, in particular to a detection method for color difference of a cobalt chloride test paper for diabetes.
Background
Diabetic foot is a common complication of diabetics who all have symptoms of hyperglycemia. The peripheral nerves of the patient can be damaged when the patient is in a hyperglycemic state for a long time, meanwhile, the blood circulation in the body can be reduced, the working capacity of sweat glands of feet of the diabetic patient is low, the sweat releasing function of the feet is blocked, and finally, the diabetic feet can be caused, and symptoms such as chapping and ulcers appear. The cobalt chloride test paper can detect moisture, and human sweat contains a large amount of moisture, so that the cobalt chloride test paper can be used for detecting the human sweat discharge. At present, cobalt chloride is often used as a raw material for early diagnosis test paper of diabetic foot neuropathy, sweat glands of feet of normal people are good in function, a large amount of sweat is generated, and color change from blue to complete pink can occur when the test paper is used. In the diabetic patient with the sweat gland function of the foot impaired, little sweat is generated, the test paper is used, the color change is not generated, or part of the test paper turns pink.
The color difference detection effect of the test paper used by normal people is better by using an image processing method, but for the test paper used by diabetics, the sweat gland function of the foot of the test paper used by diabetics is damaged, the test paper used by the test paper possibly presents a part of pink color, or almost does not have the pink color part, and the edge part of the pink color area has gradual change characteristics, so that the accuracy of extracting the areas corresponding to two color categories by collecting the surface images of the test paper is lower, and the accuracy of the detection result of the color difference of the diabetics cobalt chloride test paper is lower.
Disclosure of Invention
In order to solve the technical problem of lower accuracy of a detection result of the diabetic cobalt chloride test paper color difference, the application aims to provide a detection method for the diabetic cobalt chloride test paper color difference, and the adopted technical scheme is as follows:
collecting a surface gray level image of the used diabetes cobalt chloride test paper, and obtaining a connected domain in the surface gray level image;
obtaining the region information richness of each connected domain according to the pixel fluctuation degree in each connected domain, the texture information of the pixel points in the local range and the gray difference condition of the pixel points in the local range;
determining the gray weight of each pixel point in the connected domain according to the difference between each pixel point in each connected domain and the gray minimum value in the connected domain; obtaining a color coefficient representation value of each pixel point according to the gray weight of the pixel point and the region information richness of the connected region where the pixel point is positioned;
and clustering the pixel points in the surface gray level image according to the color coefficient representation value of each pixel point to obtain two categories, and determining the color difference detection result of the cobalt chloride test paper according to the gray level value of the pixel points in the two categories, the number of the pixel points and the unused test paper image.
Preferably, the obtaining the region information richness of each connected domain according to the pixel fluctuation degree in each connected domain, the texture information of the pixel point in the local range, and the gray scale difference condition of the pixel point in the local range specifically includes:
for any one connected domain, obtaining a first characteristic coefficient of the connected domain according to the fluctuation degree of the pixel values of all the pixel points in the connected domain; obtaining a second characteristic coefficient of the connected domain according to texture information of each pixel point in the connected domain in the neighborhood range; obtaining a third characteristic coefficient of the connected domain according to the gray difference condition of each pixel point in the connected domain in the neighborhood range;
obtaining the region information richness of the connected domain according to the first characteristic coefficient, the second characteristic coefficient and the third characteristic coefficient of the connected domain; and the first characteristic coefficient, the second characteristic coefficient and the third characteristic coefficient are in positive correlation with the region information richness.
Preferably, the obtaining the first characteristic coefficient of the connected domain according to the fluctuation degree of the pixel values of all the pixel points in the connected domain specifically includes:
performing corner detection on the surface gray level image to obtain the number of corner points in each connected domain;
calculating the variance of gray values of all pixels in the connected domain to obtain a first coefficient, calculating a second coefficient of the sum of the number of corner points in the connected domain and a first preset value, and taking the product of the first coefficient and the second coefficient as a first characteristic coefficient of the connected domain.
Preferably, the obtaining the second characteristic coefficient of the connected domain according to the texture information of each pixel point in the connected domain in the neighborhood range specifically includes:
marking any pixel point in the connected domain as a target pixel point, and constructing a gray level co-occurrence matrix corresponding to the target pixel point in a window with the target pixel point as a center and a preset size based on gray level values of all the pixel points in the window; taking the product of the contrast and entropy of the gray level co-occurrence matrix corresponding to the target pixel as a texture information complex factor of the target pixel; and taking the average value of the texture information complex factors of all the pixel points in the connected domain as a second characteristic coefficient of the connected domain.
Preferably, the obtaining the third characteristic coefficient of the connected domain according to the gray scale difference condition of each pixel point in the connected domain in the neighborhood range specifically includes:
marking any pixel point in the connected domain as a selected pixel point, respectively acquiring the average value of the gray values of each row of pixel points as a row characteristic value and respectively acquiring the average value of the gray values of each column of pixel points as a column characteristic value in a window with the selected pixel point as the center and the preset size; calculating the average value of the differences between the line characteristic values of every two lines to obtain a third coefficient; calculating the average value of the differences between the column characteristic values of every two columns to obtain a fourth coefficient; obtaining a local difference index of the selected pixel point according to the third coefficient and the fourth coefficient; the third coefficient and the fourth coefficient are in positive correlation with the local difference index;
and taking the average value of the local difference indexes of all the pixel points in the connected domain as a third characteristic coefficient of the connected domain.
Preferably, the obtaining the color coefficient representation value of each pixel point according to the gray weight of the pixel point and the region information richness of the connected domain where the pixel point is located specifically includes:
and taking the product of the gray weight of each pixel point and the region information richness of the connected region where the pixel point is positioned as a color coefficient representation value of each pixel point.
Preferably, the determining the color difference detection result of the cobalt chloride test paper according to the gray values and the number of the pixels in the two categories and the template test paper image specifically includes:
taking the ratio of the number of all the pixel points in each category to the total number of all the pixel points in the surface gray image as the corresponding number weight value of each category, and carrying out weighted summation on the characteristic mean value of each category by utilizing the number weight value of each category to obtain the characteristic color value of the surface gray image;
calculating the gray value average value of all pixel points in the unused test paper image and marking the gray value average value as the characteristic color value of the test paper image; taking a normalized value of the absolute value of the difference between the characteristic color value of the surface gray image and the characteristic color value of the test paper image as a color difference value;
when the color difference value is smaller than or equal to a preset first color threshold value, the color difference detection result of the cobalt chloride test paper is slight color difference; when the color difference value is larger than the first color threshold value and smaller than or equal to a preset second color threshold value, the color difference detection result of the cobalt chloride test paper is a moderate color difference; and when the color difference value is larger than the second color threshold value, the color difference detection result of the cobalt chloride test paper is the gravity color difference.
Preferably, the determining the gray weight of each pixel in the connected domain according to the difference between each pixel in the connected domain and the gray minimum in the connected domain specifically includes:
and regarding any pixel point in any connected domain, taking the negative correlation normalized value of the absolute value of the difference between the gray value of the pixel point and the minimum gray value of the pixel point in the connected domain as the gray weight of the pixel point.
Preferably, the components of the diabetic cobalt chloride test paper specifically comprise:
cobalt chloride test paper, PU film, PE release film and release paper; wherein, the cobalt chloride test paper adopts pH base paper, and the pH base paper is uniformly soaked by cobalt chloride reagent liquid with the pH value of 6-7.5 and the cobalt chloride content of more than or equal to 12 percent.
The embodiment of the application has at least the following beneficial effects:
according to the application, the connected domain in the surface gray level image of the used diabetes cobalt chloride test paper is firstly obtained, so that analysis is carried out based on gray level distribution conditions of different pixels in different connected domains, and more accurate color characteristic distribution of the test paper can be obtained. And then, analyzing the pixel fluctuation degree in each connected domain, the texture information of the pixel points in the local range and the gray level difference condition of the pixel points in the local range respectively to obtain the region information richness of each connected domain, namely, the feature distribution in the connected domain is reflected from three aspects of the pixel fluctuation degree, the texture information distribution condition and the gray level difference condition by using the region information richness. Further, a gray weight is given to each pixel point based on the difference between the gray minimum value of each pixel point and the gray minimum value of the connected domain where the pixel point is located, the classification measurement index is quantized to the pixel level, clustering is further carried out based on the color coefficient representation value of each pixel point, a more accurate clustering result can be obtained, and the cobalt chloride test paper color difference detection result is determined based on the classification result, so that the detection result of the diabetes cobalt chloride test paper color difference is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting the chromatic aberration of the cobalt chloride test paper for diabetes.
Detailed Description
In order to further illustrate the technical means and effects adopted by the application to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of a detection method for the color difference of the cobalt chloride test paper for diabetes according to the application, which is provided by the application, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
The specific scheme of the detection method for the color difference of the cobalt chloride test paper for diabetes is provided by the application with the following specific description of the accompanying drawings.
The specific scene aimed by the application is as follows: according to the application, color difference detection is carried out on the color change of the diabetic cobalt chloride test paper before and after use, a clustering algorithm is used for analyzing the surface image of the test paper after use, and a blue type part of the test paper which is not discolored and a pink type part of the test paper which is discolored can be obtained, so that the test paper color difference detection is carried out based on the areas corresponding to the two color types. However, when the conventional distance-based clustering algorithm is used for processing the image, misclassification may occur. Therefore, the application obtains the index capable of representing the color characteristic of each pixel point based on the gray level characteristic of the test paper surface image, and further obtains a more accurate color classification result.
Examples:
referring to fig. 1, a flowchart of a method for detecting chromatic aberration of a diabetic cobalt chloride test paper according to an embodiment of the application is shown, and the method includes the following steps:
step one, collecting a surface gray level image of the used diabetes cobalt chloride test paper, and obtaining a connected domain in the surface gray level image.
Firstly, it should be noted that the composition of the diabetic cobalt chloride test paper adopted in the application specifically comprises: cobalt chloride test paper, PU film, PE release film and release paper; wherein, the color development strip cobalt chloride test paper adopts pH base paper, and the pH base paper is uniformly soaked by cobalt chloride reagent solution which is regulated to reach the pH value of 6-7.5 and the cobalt chloride content of more than or equal to 12 percent. The test paper is stuck to the skin of the ball-shaped part under the foot of a diabetic patient for 10 minutes, then the used substance is placed on a camera table, and a fixed machine position is adopted to shoot the surface image of the diabetic cobalt chloride test paper, wherein the fixed machine position adopts a CMOS camera to carry out image acquisition, and the acquired surface image is converted into a gray image, so that the gray image of the diabetic cobalt chloride is obtained.
Because the images are obtained by shooting with a fixed camera, and the sizes of the test paper in production and the backgrounds in shooting are consistent, a fixed coordinate cutting method can be adopted in the embodiment to remove the background part in the gray level image, obtain the part only containing the diabetes cobalt chloride test paper, and record the image after removing the background as the surface gray level image of the diabetes cobalt chloride test paper. In other embodiments, the practitioner may also use semantic segmentation to remove background portions from the gray scale image.
When the surface of the diabetic cobalt chloride test paper does not react with water molecules, the test paper presents a deeper blue color, but once chemical reaction is generated between the test paper and the water molecules, the test paper which presents the blue color per se is turned into pink color. However, the reaction condition between cobalt chloride and water molecules is less limited, and cobalt chloride test paper can even generate chemical reaction with water molecules in the air, but the storage environment of the test paper cannot be ensured to be completely isolated from the air and the water. The blue test paper can chemically react with water molecules in the air, but because the water content in the air is less and the water molecules are dispersed on the test paper and do not concentrate in a certain area, partial areas of the test paper can change, and uneven color distribution is displayed, namely, the partial areas of the test paper are changed from deep blue to light blue.
In the surface gray scale image of the diabetes cobalt chloride test paper, there may be a part where moisture in the air reacts with the test paper to change blue, that is, a blue test paper part which does not react with sweat of a patient may have deep blue and light blue, and abundant texture information and gray scale change characteristics may be generated in the surface gray scale image. And the pink part reacts with sweat of the patient, the part fully reacts with sweat moisture of the foot of the patient, and presents more uniform pink, and the pink area presents outward diffusion characteristic due to the strong water absorption characteristic of the test paper, so that the pink part has little color change, small gray scale difference and no more abundant texture information.
In order to facilitate the subsequent analysis of the color feature distribution of the pixel points in each region and the texture information of each region, in this embodiment, a canny edge detection algorithm is used to process the surface gray level image to obtain an edge binary image, and a chain code method is used to determine the connected regions of the edge binary image, so that a plurality of connected regions in the surface gray level image can be obtained. The practitioner can also select other suitable methods to obtain the connected domain in the surface gray level image according to the specific implementation scene.
And step two, obtaining the region information richness of each connected domain according to the pixel fluctuation degree in each connected domain, the texture information of the pixel points in the local range and the gray difference condition of the pixel points in the local range.
The blue test paper part which does not react possibly reacts with fewer water molecules in the air, so that the color of the test paper is changed from deep blue to light blue, in a surface gray level image, the deep blue part is darker in color, the gray level value is smaller, the light blue part is lighter in color and the gray level value is larger, and therefore, the gray level value of the blue part in the surface gray level image is different, and further, the texture change exists. The pink part of the test paper has stronger water absorption and is soaked by water uniformly, so that the gray value difference of the pink part is smaller, and more texture information does not exist.
Based on this, if the connected domain belongs to the blue portion, there is a large difference in gray value of the connected domain, the distribution is uneven, and there are deep blue and light blue at the same time. If the connected domain belongs to the pink part, the gray value of the connected domain has smaller difference, the distribution is more uniform, and only one pink color exists.
Firstly, analyzing the gray value fluctuation condition of each pixel point in each connected domain, and further obtaining a first characteristic coefficient of the connected domain according to the fluctuation degree of the pixel values of all the pixel points in the connected domain because of the color fluctuation of the region where the blue part is located and certain gray fluctuation and richer texture information and corner information.
Specifically, corner detection is carried out on the surface gray level image, and the number of corner points in each connected domain is obtained. In this embodiment, the Harris corner detection algorithm is used to process the surface gray level image, and this algorithm is a well-known technique and will not be described here too much. Calculating the variance of gray values of all pixels in the connected domain to obtain a first coefficient, calculating a second coefficient of the sum of the number of corner points in the connected domain and a first preset value, and taking the product of the first coefficient and the second coefficient as a first characteristic coefficient of the connected domain.
In this embodiment, taking the ith connected domain in the surface gray scale image as an example for explanation, the calculation formula of the first characteristic coefficient of the ith connected domain may be expressed as:
wherein ,first characteristic coefficient representing the ith connected domain,/->Represents the number of corner points contained in the i-th connected domain,/->Represents the total number of pixel points contained in the ith connected domain, +.>Gray value representing the nth pixel point in the ith connected domain, < >>And representing the average value of the gray values of all the pixel points in the ith connected domain.
In this embodiment, the first preset value is 1, so as to prevent the number of corner points included in the connected domain from being 0, affecting the accuracy of the final data, and the implementer may set according to the specific implementation scenario. The larger the value of the second coefficient is, the more intense the gray level change in the connected domain is, the more the information of the connected domain is rich, and the larger the value of the corresponding first characteristic coefficient is.
The first coefficient reflects the fluctuation condition of the gray value of the pixel point in the connected domain, and the larger the value of the first coefficient is, the larger the whole fluctuation degree of the gray value of the pixel point in the connected domain is, and further the stronger the gray change in the connected domain is, the larger the value of the corresponding first characteristic coefficient is. The first characteristic coefficient of the connected domain reflects the gray scale variation condition and gray scale fluctuation degree of the whole connected domain.
And then, respectively analyzing the distribution condition of texture information in the local range of each pixel point of each connected domain, namely obtaining a second characteristic coefficient of the connected domain according to the texture information of each pixel point in the neighborhood range in the connected domain. Specifically, marking any pixel point in the connected domain as a target pixel point, and constructing a gray level co-occurrence matrix corresponding to the target pixel point in a window with the target pixel point as a center and a preset size based on gray level values of all the pixel points in the window; taking the product of the contrast and entropy of the gray level co-occurrence matrix corresponding to the target pixel as a texture information complex factor of the target pixel; and taking the average value of the texture information complex factors of all the pixel points in the connected domain as a second characteristic coefficient of the connected domain.
In this embodiment, the neighborhood range of the pixel point is set to be 5*5, that is, the preset size is 5*5, and the practitioner can set according to the specific implementation scenario. And constructing a gray level co-occurrence matrix with the step length of 1 and 0 degree in a window taking the target pixel point as the center, and marking the gray level co-occurrence matrix as a gray level co-occurrence matrix corresponding to the target pixel point. The method for acquiring the gray level co-occurrence matrix is a well-known technology, and will not be described in detail here, and the practitioner can set the acquiring conditions according to the specific implementation scene.
The entropy of the gray level co-occurrence matrix corresponding to the target pixel point reflects the complexity of gray level distribution in the neighborhood range of the target pixel point, the contrast of the gray level co-occurrence matrix corresponding to the target pixel point reflects the depth of texture distribution in the neighborhood range of the target pixel point, namely, the greater the entropy is, the greater the contrast is, the greater the complexity of gray level distribution in the neighborhood of the pixel point in the connected domain is, the deeper the grooves of the texture distribution are, the clearer the effect is, the greater the corresponding texture information complexity factor is, and the greater the value of the second characteristic coefficient is. The second characteristic coefficient of the connected domain reflects the equilibrium condition of the distribution condition of texture information in the neighborhood range of each pixel point.
Further, the blue part in the surface gray level image has dark blue and light blue, the position distribution of the two colors is not random, and the distribution range is random, so that larger difference between gray values in the neighborhood range of each pixel point may exist, and smaller difference between gray values in the neighborhood range of the pixel point of the region where the pink part is located may exist. Based on the third characteristic coefficient of the connected domain is obtained according to the gray difference condition of each pixel point in the connected domain in the neighborhood range.
Specifically, marking any pixel point in the connected domain as a selected pixel point, respectively acquiring the average value of the gray values of each row of pixel points as a row characteristic value and respectively acquiring the average value of the gray values of each column of pixel points as a column characteristic value in a window with the selected pixel point as the center and the preset size; calculating the average value of the differences between the line characteristic values of every two lines to obtain a third coefficient; calculating the average value of the differences between the column characteristic values of every two columns to obtain a fourth coefficient; obtaining a local difference index of the selected pixel point according to the third coefficient and the fourth coefficient; the third coefficient and the fourth coefficient are in positive correlation with the local difference index; and taking the average value of the local difference indexes of all the pixel points in the connected domain as a third characteristic coefficient of the connected domain.
In this embodiment, taking the ith connected domain in the surface gray scale image as an example, and taking the mth pixel point in the ith connected domain as the selected pixel point, the calculation formula of the local difference index of the selected pixel point can be expressed as:
wherein ,local difference index representing the mth pixel point in the ith connected domain,/for>Representing the total number of absolute values of differences between the row characteristic values of every two rows of the window corresponding to the mth pixel point or representing the total number of absolute values of differences between the column characteristic values of every two columns in the window corresponding to the mth pixel point,/>Representing the line characteristic value of the ith line in the window corresponding to the mth pixel point, +.>Representing the row characteristic value of the v th row in the window corresponding to the m-th pixel point, wherein x represents the index as the row characteristic value,/for>Representing a set formed by all rows contained in a window corresponding to the mth pixel point;column characteristic value of a column a in a window corresponding to the mth pixel point is represented by +.>Column characteristic value of the b-th column in the window corresponding to the m-th pixel point is represented, y represents that the index is the column characteristic value,/the index is represented by the column characteristic value>Representation ofAnd the m-th pixel point corresponds to a set formed by all columns contained in the window.
As a result of the third coefficient being the value of,and the fourth coefficient is used for reflecting the gray level difference condition of the selected pixel points between the rows in the corresponding window, the fourth coefficient is used for reflecting the gray level difference condition of the selected pixel points between the columns in the corresponding window, and the larger the third coefficient is, the larger the fourth coefficient is, which means that the larger the gray level difference of the pixel points in the window is, the larger the corresponding local difference index is, and the more the selected pixel points corresponding to the window are likely to be positioned in the blue part.
According to a calculation formula of the local difference index, the local difference index of each pixel point in the connected domain can be obtained, the average value of the local difference indexes of all the pixel points in the connected domain is used as a third characteristic coefficient of the connected domain, and the third characteristic coefficient of the connected domain reflects the gray scale difference condition of each pixel point in the connected domain in a corresponding window.
Finally, a deep blue part and a light blue part exist in the blue part area at the same time, so that the gray level change of the area where the blue part is positioned is larger, the gray level fluctuation degree is larger, the texture information is more complex, and the gray level value difference of the pixel point is larger. The color distribution in the region of the pink part is more uniform, so that the gray value of the region of the pink part has smaller change, the gray fluctuation degree is smaller, less texture information exists, and the gray value difference of the pixel points is smaller.
Meanwhile, the first characteristic coefficient of the connected domain reflects the whole gray level change condition and gray level fluctuation degree of the connected domain, the second characteristic coefficient of the connected domain reflects the balance condition of the texture information distribution condition in the neighborhood range of each pixel point, the third characteristic coefficient of the connected domain reflects the gray level difference condition of each pixel point in the corresponding window in the connected domain, and further the region information richness of each connected domain is obtained by combining three characteristic aspects, and the first characteristic coefficient, the second characteristic coefficient and the third characteristic coefficient are in positive correlation with the region information richness. In the present embodiment, the product of the first characteristic coefficient, the second characteristic coefficient, and the third characteristic coefficient is taken as the region information richness of the connected domain.
Determining the gray weight of each pixel point in the communication domain according to the difference between each pixel point in each communication domain and the gray minimum value in the communication domain; and obtaining the color coefficient representation value of each pixel point according to the gray weight of the pixel point and the region information richness of the connected region where the pixel point is positioned.
Since the characteristic index of each pixel point needs to be clustered later, and the region information richness reflects the gray level fluctuation degree, the texture information distribution condition and the gray level difference condition in each connected domain, the gray level value information of each pixel point needs to be analyzed respectively. The darker the color at a certain location on the test paper, the smaller the gray value of the pixel at its corresponding location, the more likely the pixel is at the original color of the test paper for the blue portion and the more likely the sweat-wetted location for the pink portion.
Based on this, the gray weight of each pixel point in the connected domain is determined according to the difference between each pixel point in each connected domain and the gray minimum value in the connected domain. And regarding any pixel point in any connected domain, taking the negative correlation normalized value of the absolute value of the difference between the gray value of the pixel point and the minimum gray value of the pixel point in the connected domain as the gray weight of the pixel point.
In this embodiment, taking the selected pixel point as an example for explanation, the calculation formula of the gray weight of the selected pixel point may be expressed as follows:
wherein ,representing the ith connected domainGray weight of mth pixel in the inner, < ->Gray value representing the mth pixel point in the ith connected domain, < >>Representing the minimum of the gray values of all pixel points in the i-th connected domain, exp () represents an exponential function based on a natural constant e.
The gray level difference between the pixel point and the deepest color point in the communication domain where the pixel point is positioned is reflected, the smaller the difference is, the closer the pixel point is to the deepest color point, the deeper the color depth of the pixel point is further, the larger the corresponding gray level weight is, and the larger the color richness of the region where the pixel point is positioned is endowed.
Specifically, the product of the gray weight of each pixel point and the region information richness of the connected region where the pixel point is located is used as the color coefficient representation value of each pixel point. The larger the gray weight value of the pixel point is, the larger the value of the region information richness of the connected region where the pixel point is located is, and the greater the possibility that the corresponding pixel point belongs to the blue part is. The smaller the gray weight value of the pixel point is, the smaller the value of the region information richness of the connected region where the pixel point is located is, and the greater the possibility that the corresponding pixel point belongs to a pink part is.
And step four, clustering the pixel points in the surface gray level image according to the color coefficient representation value of each pixel point to obtain two categories, and determining the color difference detection result of the cobalt chloride test paper according to the gray level value of the pixel points in the two categories, the number of the pixel points and the unused test paper image.
In the traditional K-means clustering algorithm, clustering is only performed based on distance measurement among pixel points, dark blue and light blue gradual changes exist in a region where a blue part is located in a surface gray level image, gradual changes exist at a junction between the blue part and a pink part, and the situation that boundary color change situations cannot be distinguished by the distance-based clustering algorithm and misclassification possibly occurs is caused, so that the embodiment can obtain the vividness degree of color of each pixel point respectively by analyzing gray level fluctuation situations, information richness and gray level difference situations in the range of each connected region in the surface gray level image, and further clustering processing is performed on each pixel point based on the index, so that a more accurate classification result can be obtained.
Specifically, the color coefficient representation value of each pixel point is used as a classification measurement index of each pixel point, the Euclidean distance is adopted in the measurement mode, namely, the Euclidean distance between the classification measurement indexes of two pixel points is calculated in the clustering process, in the embodiment, the K-means clustering algorithm is adopted for carrying out the in-out processing, the value of K is 2, and namely, all the pixel points in the surface gray level image are divided into two categories.
The two categories correspond to the category of the blue part and the category of the pink part respectively, and further, the color difference detection result of the cobalt chloride test paper can be determined according to the gray value and the number of the pixel points in the two categories and the unused test paper image. Specifically, the gray value average value of all the pixel points of each category is calculated and recorded as the characteristic average value of each category, the ratio of the number of all the pixel points in each category to the total number of all the pixel points in the surface gray image is used as the number weight corresponding to each category, and the characteristic average value of each category is weighted and summed by using the number weight of each category to obtain the characteristic color value of the surface gray image.
The corresponding number weight value of each category reflects the ratio of the number of pixel points in each category, and the larger the number ratio is, the larger the corresponding gray value weight is, and the characteristic color value obtained based on the calculation can reflect the surface color characteristics of the surface gray image.
Meanwhile, before the test paper is used for detecting sweat glands of feet, an unused surface image of the test paper needs to be collected and converted into a gray level image, the gray level image is recorded as an unused test paper image, and the gray level value average value of all pixel points in the unused test paper image is calculated and recorded as the characteristic color value of the test paper image; and taking the normalized value of the absolute value of the difference between the characteristic color value of the surface gray image and the characteristic color value of the test paper image as the color difference value. The color difference detection result of the current test paper after use can be obtained by comparing the difference conditions between the color characteristics in the corresponding images before and after the test paper is used. The larger the color difference before and after the test paper is used, the larger the color change, which indicates that the more the color-changing part of the test paper is, the more the sweat secretion of the foot is, the lower the degree of foot pathological changes is, and the lower the possibility of diabetes is.
Specifically, when the color difference value is smaller than or equal to a preset first color threshold value, the color difference detection result of the cobalt chloride test paper is a slight color difference, which indicates that the color difference between the test paper after use and the test paper before use is smaller at the moment, and further indicates that the symptom of the diabetic patient is serious at the moment and needs to seek medical advice in time. When the color difference value is larger than the first color threshold value and smaller than or equal to the preset second color threshold value, the color difference detection result of the cobalt chloride test paper is a moderate color difference, which indicates that a certain difference exists between the test paper after use and the test paper before use at the moment, and further indicates that a diabetic patient shows a certain diabetes symptom at the moment. When the color difference value is larger than the second color threshold value, the color difference detection result of the cobalt chloride test paper is a heavy color difference, which indicates that the color difference between the test paper used at the moment and the test paper used for money is larger, and further indicates that the symptoms of diabetics are slight or do not exist at the moment. In this embodiment, the value of the first color threshold is 0.3, the value of the second color threshold is 0.7, and the practitioner can set according to the specific implementation scenario.
It should be noted that, in the early test paper detection of diabetics, if the patients have mild diabetes symptoms, the color change of the surface of the test paper may be mild when the test paper is used for detection, and a larger part of blue color and a smaller part of pink color may exist in the surface gray level image. If a patient has severe diabetes symptoms, the test strip may have severe surface color changes when tested with the test strip, and a large portion of pink and a small portion of blue may be present in the surface gray scale image. That is, in the method of this example, test paper is tested for the presence of certain symptoms of diabetes. The test paper can be detected according to the method in two special cases, namely, the test paper has no change before and after use and the test paper turns to pink completely after use.
In other embodiments, the analysis may also be performed for both of these special cases. Specifically, a gray level image of the whole test paper which is completely turned into pink is obtained and is marked as a characteristic test paper image, the average value of gray level values of all pixels in the characteristic test paper image is calculated and is marked as the characteristic color value of the characteristic test paper image, and for the surface gray level image of the untreated diabetes cobalt chloride test paper, the average value of gray level values of all pixels in the surface gray level image is calculated and is marked as the characteristic average value of the surface gray level image.
When the absolute value of the difference between the characteristic mean value of the surface gray level image and the characteristic color value of the characteristic test paper image is smaller than or equal to a preset threshold value, the fact that the gray level between the surface gray level image and the characteristic test paper image is relatively close at the moment can be indicated, the test paper can be completely changed into pink at the moment, and further the fact that the foot sweat secretion is high, the foot pathological change degree is low and the possibility of suffering from diabetes is low is indicated.
When the absolute value of the difference between the characteristic mean value of the surface gray level image and the characteristic color value of the test paper image is smaller than or equal to a preset threshold value, the fact that the gray level between the surface gray level image and the test paper image is relatively close at the moment can be indicated, the fact that the test paper is unchanged at the moment can be indicated, and further the fact that foot sweat secretion is small, foot lesion degree is high and possibility of diabetes is high is indicated.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application and are intended to be included within the scope of the application.
Claims (3)
1. The method for detecting the color difference of the cobalt chloride test paper for diabetes is characterized by comprising the following steps of:
collecting a surface gray level image of the used diabetes cobalt chloride test paper, and obtaining a connected domain in the surface gray level image;
obtaining the region information richness of each connected domain according to the pixel fluctuation degree in each connected domain, the texture information of the pixel points in the local range and the gray difference condition of the pixel points in the local range;
determining the gray weight of each pixel point in the connected domain according to the difference between each pixel point in each connected domain and the gray minimum value in the connected domain; obtaining a color coefficient representation value of each pixel point according to the gray weight of the pixel point and the region information richness of the connected region where the pixel point is positioned;
clustering pixel points in the surface gray level image according to the color coefficient representation value of each pixel point to obtain two categories, and determining a cobalt chloride test paper color difference detection result according to the gray level value of the pixel point and the number of the pixel points in the two categories and the unused test paper image;
obtaining the region information richness of each connected domain according to the pixel fluctuation degree in each connected domain, the texture information of the pixel points in the local range and the gray difference condition of the pixel points in the local range, wherein the method specifically comprises the following steps:
for any one connected domain, obtaining a first characteristic coefficient of the connected domain according to the fluctuation degree of the pixel values of all the pixel points in the connected domain; obtaining a second characteristic coefficient of the connected domain according to texture information of each pixel point in the connected domain in the neighborhood range; obtaining a third characteristic coefficient of the connected domain according to the gray difference condition of each pixel point in the connected domain in the neighborhood range;
obtaining the region information richness of the connected domain according to the first characteristic coefficient, the second characteristic coefficient and the third characteristic coefficient of the connected domain; the first characteristic coefficient, the second characteristic coefficient and the third characteristic coefficient are in positive correlation with the region information richness;
the first characteristic coefficient for obtaining the connected domain according to the fluctuation degree of the pixel values of all the pixel points in the connected domain is specifically:
performing corner detection on the surface gray level image to obtain the number of corner points in each connected domain;
calculating the variance of gray values of all pixel points in the connected domain to obtain a first coefficient, calculating a second coefficient of the sum value of the number of corner points in the connected domain and a first preset value, and taking the product of the first coefficient and the second coefficient as a first characteristic coefficient of the connected domain;
the second characteristic coefficient of the connected domain obtained according to the texture information of each pixel point in the connected domain in the neighborhood range is specifically:
marking any pixel point in the connected domain as a target pixel point, and constructing a gray level co-occurrence matrix corresponding to the target pixel point in a window with the target pixel point as a center and a preset size based on gray level values of all the pixel points in the window; taking the product of the contrast and entropy of the gray level co-occurrence matrix corresponding to the target pixel as a texture information complex factor of the target pixel; taking the average value of texture information complex factors of all pixel points in the connected domain as a second characteristic coefficient of the connected domain;
the third characteristic coefficient of the connected domain obtained according to the gray scale difference condition of each pixel point in the connected domain in the neighborhood range is specifically:
marking any pixel point in the connected domain as a selected pixel point, respectively acquiring the average value of the gray values of each row of pixel points as a row characteristic value and respectively acquiring the average value of the gray values of each column of pixel points as a column characteristic value in a window with the selected pixel point as the center and the preset size; calculating the average value of the differences between the line characteristic values of every two lines to obtain a third coefficient; calculating the average value of the differences between the column characteristic values of every two columns to obtain a fourth coefficient; obtaining a local difference index of the selected pixel point according to the third coefficient and the fourth coefficient; the third coefficient and the fourth coefficient are in positive correlation with the local difference index;
taking the average value of the local difference indexes of all the pixel points in the connected domain as a third characteristic coefficient of the connected domain;
the method for obtaining the color coefficient representation value of each pixel point according to the gray weight of the pixel point and the region information richness of the connected region of the pixel point comprises the following steps:
taking the product of the gray weight of each pixel point and the region information richness of the connected region where the pixel point is positioned as a color coefficient representation value of each pixel point;
the determining the gray weight of each pixel point in the connected domain according to the difference between each pixel point in the connected domain and the gray minimum value in the connected domain specifically comprises the following steps:
for any pixel point in any connected domain, taking the negative correlation normalized value of the absolute value of the difference between the gray value of the pixel point and the minimum gray value of the pixel point in the connected domain as the gray weight of the pixel point;
the calculation formula of the gray weight is expressed as:
wherein ,gray scale weight representing the mth pixel point in the ith connected domain,/for each pixel point>Gray value representing the mth pixel point in the ith connected domain, < >>Representing the minimum of the gray values of all pixel points in the i-th connected domain, exp () represents an exponential function based on a natural constant e.
2. The method for detecting the color difference of the cobalt chloride test paper for diabetes according to claim 1, wherein the determining the color difference detection result of the cobalt chloride test paper according to the gray values of the pixels in the two categories, the number of the pixels and the template test paper image specifically comprises:
taking the ratio of the number of all the pixel points in each category to the total number of all the pixel points in the surface gray image as the corresponding number weight value of each category, and carrying out weighted summation on the characteristic mean value of each category by utilizing the number weight value of each category to obtain the characteristic color value of the surface gray image;
calculating the gray value average value of all pixel points in the unused test paper image and marking the gray value average value as the characteristic color value of the test paper image; taking a normalized value of the absolute value of the difference between the characteristic color value of the surface gray image and the characteristic color value of the test paper image as a color difference value;
when the color difference value is smaller than or equal to a preset first color threshold value, the color difference detection result of the cobalt chloride test paper is slight color difference; when the color difference value is larger than the first color threshold value and smaller than or equal to a preset second color threshold value, the color difference detection result of the cobalt chloride test paper is a moderate color difference; and when the color difference value is larger than the second color threshold value, the color difference detection result of the cobalt chloride test paper is the gravity color difference.
3. The method for detecting the chromatic aberration of the diabetic cobalt chloride test paper according to claim 1, wherein the components of the diabetic cobalt chloride test paper specifically comprise:
cobalt chloride test paper, PU film, PE release film and release paper; wherein, the cobalt chloride test paper adopts pH base paper, and the pH base paper is uniformly soaked by cobalt chloride reagent liquid with the pH value of 6-7.5 and the cobalt chloride content of more than or equal to 12 percent.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310889567.8A CN116626029B (en) | 2023-07-20 | 2023-07-20 | Detection method for color difference of cobalt chloride test paper for diabetes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310889567.8A CN116626029B (en) | 2023-07-20 | 2023-07-20 | Detection method for color difference of cobalt chloride test paper for diabetes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116626029A CN116626029A (en) | 2023-08-22 |
| CN116626029B true CN116626029B (en) | 2023-09-22 |
Family
ID=87617387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310889567.8A Active CN116626029B (en) | 2023-07-20 | 2023-07-20 | Detection method for color difference of cobalt chloride test paper for diabetes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116626029B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116883395B (en) * | 2023-09-06 | 2023-11-21 | 山东荣信集团有限公司 | Image processing-based ammonium sulfate production color detection method and system |
| CN117934355B (en) * | 2024-01-23 | 2024-09-17 | 苏州世航智能科技有限公司 | Visual positioning method for underwater robot |
| CN117974633B (en) * | 2024-03-28 | 2024-06-07 | 潍坊科技学院 | Intelligent tomato pest detection method based on image processing |
| CN118072254B (en) * | 2024-04-18 | 2024-09-03 | 辽宁通安消防安全技术工程有限公司 | Intelligent detection method and system for instantaneous explosion open fire |
| CN118379300B (en) * | 2024-06-27 | 2024-10-15 | 青岛领军智能建造新材料科技有限公司 | Coated plate defect detection method for image processing |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107230210A (en) * | 2017-06-19 | 2017-10-03 | 长光卫星技术有限公司 | A kind of fast partition method of remote sensing images harbour waterborne target |
| CN108830858A (en) * | 2018-06-20 | 2018-11-16 | 天津大学 | It is a kind of based on infrared and optical image double-mode imaging information living body method for counting colonies |
| CN109800777A (en) * | 2018-09-21 | 2019-05-24 | 上海营阅企业管理服务中心(有限合伙) | A kind of urine test paper physical signs automatic identifying method |
| CN110717935A (en) * | 2019-08-26 | 2020-01-21 | 北京中科慧眼科技有限公司 | Image matching method, device and system based on image characteristic information |
| WO2020221177A1 (en) * | 2019-04-30 | 2020-11-05 | 深圳数字生命研究院 | Method and device for recognizing image, storage medium and electronic device |
| CN113496490A (en) * | 2021-09-06 | 2021-10-12 | 南通弈驰新型建材科技有限公司 | Wood board surface defect detection method and system based on computer vision |
| CN113963042A (en) * | 2021-12-21 | 2022-01-21 | 派立锐汽车零部件(武汉)有限公司 | Metal part defect degree evaluation method based on image processing |
| CN115311466A (en) * | 2021-04-21 | 2022-11-08 | 中移(成都)信息通信科技有限公司 | Image recognition method, electronic device, and storage medium |
| CN116168027A (en) * | 2023-04-24 | 2023-05-26 | 山东交通学院 | Intelligent woodworking machine cutting method based on visual positioning |
| CN116246174A (en) * | 2023-04-26 | 2023-06-09 | 山东金诺种业有限公司 | Sweet potato variety identification method based on image processing |
-
2023
- 2023-07-20 CN CN202310889567.8A patent/CN116626029B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107230210A (en) * | 2017-06-19 | 2017-10-03 | 长光卫星技术有限公司 | A kind of fast partition method of remote sensing images harbour waterborne target |
| CN108830858A (en) * | 2018-06-20 | 2018-11-16 | 天津大学 | It is a kind of based on infrared and optical image double-mode imaging information living body method for counting colonies |
| CN109800777A (en) * | 2018-09-21 | 2019-05-24 | 上海营阅企业管理服务中心(有限合伙) | A kind of urine test paper physical signs automatic identifying method |
| WO2020221177A1 (en) * | 2019-04-30 | 2020-11-05 | 深圳数字生命研究院 | Method and device for recognizing image, storage medium and electronic device |
| CN110717935A (en) * | 2019-08-26 | 2020-01-21 | 北京中科慧眼科技有限公司 | Image matching method, device and system based on image characteristic information |
| CN115311466A (en) * | 2021-04-21 | 2022-11-08 | 中移(成都)信息通信科技有限公司 | Image recognition method, electronic device, and storage medium |
| CN113496490A (en) * | 2021-09-06 | 2021-10-12 | 南通弈驰新型建材科技有限公司 | Wood board surface defect detection method and system based on computer vision |
| CN113963042A (en) * | 2021-12-21 | 2022-01-21 | 派立锐汽车零部件(武汉)有限公司 | Metal part defect degree evaluation method based on image processing |
| CN116168027A (en) * | 2023-04-24 | 2023-05-26 | 山东交通学院 | Intelligent woodworking machine cutting method based on visual positioning |
| CN116246174A (en) * | 2023-04-26 | 2023-06-09 | 山东金诺种业有限公司 | Sweet potato variety identification method based on image processing |
Non-Patent Citations (4)
| Title |
|---|
| A feasible image-based colorimetric assay using a smartphone RGB camera for point-of-care monitoring of diabetes;T.-T. Wang, et al.;《Talanta》;第1-5页 * |
| Portable and Intelligent Urine Glucose Analyzer Based on a CdTe QDs@GOx Aerogel Circular Array Sensor;Tao Hu et al.;《ACS Omega 》;第32655−32662页 * |
| 基于 HSV 色彩空间提取糖尿病变色试纸;翟善发，方中纯;《信息技术与信息化》;第35-38页 * |
| 复杂背景下基于 Vibe 和改进 LBP 的运动目标检测算法;陈玮琳等;《激光与光电子学进展》;第第60卷卷(第第4期期);第0410012-1-8页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116626029A (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116626029B (en) | Detection method for color difference of cobalt chloride test paper for diabetes | |
| Rubegni et al. | Automated diagnosis of pigmented skin lesions | |
| US20180226154A1 (en) | System and method for segmentation and automated measurement of chronic wound images | |
| Zhang et al. | Detection of microaneurysms using multi-scale correlation coefficients | |
| Jaworek-Korjakowska | Computer‐aided diagnosis of micro‐malignant melanoma lesions applying support vector machines | |
| CN113256641A (en) | Skin lesion image segmentation method based on deep learning | |
| Binder et al. | Computer-aided epiluminescence microscopy of pigmented skin lesions: the value of clinical data for the classification process | |
| Rubegni et al. | Differentiation between pigmented Spitz naevus and melanoma by digital dermoscopy and stepwise logistic discriminant analysis | |
| Waheed et al. | Hybrid features and mediods classification based robust segmentation of blood vessels | |
| Barbosa et al. | Towards automatic quantification of the epicardial fat in non-contrasted CT images | |
| Chen et al. | Colour analysis of skin lesion regions for melanoma discrimination in clinical images | |
| CN112071418B (en) | Gastric cancer peritoneal metastasis prediction system and method based on enhanced CT image histology | |
| Boubakar Khalifa Albargathe et al. | Blood vessel segmentation and extraction using H-minima method based on image processing techniques | |
| CN115526834A (en) | Immunofluorescence image detection method and device, equipment and storage medium | |
| CN113657449A (en) | Traditional Chinese medicine tongue picture greasy classification method containing noise labeling data | |
| CN115760858A (en) | Kidney pathological section cell identification method and system based on deep learning | |
| CN117252893A (en) | Segmentation processing method for breast cancer pathological image | |
| Vajravelu et al. | Machine learning techniques to detect bleeding frame and area in wireless capsule endoscopy video | |
| CN115797246A (en) | Pathological image quality evaluation and adjustment method and system, electronic device and medium | |
| Bochko et al. | Lower extremity ulcer image segmentation of visual and near‐infrared imagery | |
| CN116664563B (en) | New adjuvant chemotherapy curative effect evaluation system, equipment and medium | |
| Fauzi et al. | Segmentation and management of chronic wound images: A computer-based approach | |
| CN117078697A (en) | Fundus disease seed detection method based on cascade model fusion | |
| CN116883341A (en) | Liver tumor CT image automatic segmentation method based on deep learning | |
| Yahata et al. | Gastric cancer detection by two-step learning in near-infrared hyperspectral imaging |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |