CN115082465B - Wool and cashmere classification method based on scanning electron microscope image processing - Google Patents
Wool and cashmere classification method based on scanning electron microscope image processing Download PDFInfo
- Publication number
- CN115082465B CN115082465B CN202211002556.5A CN202211002556A CN115082465B CN 115082465 B CN115082465 B CN 115082465B CN 202211002556 A CN202211002556 A CN 202211002556A CN 115082465 B CN115082465 B CN 115082465B
- Authority
- CN
- China
- Prior art keywords
- gray
- texture
- scale
- cashmere
- calculating
- 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
- 210000000085 cashmere Anatomy 0.000 title claims abstract description 61
- 210000002268 wool Anatomy 0.000 title claims abstract description 58
- 238000001000 micrograph Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 title claims abstract description 21
- 239000000835 fiber Substances 0.000 claims abstract description 77
- 239000004753 textile Substances 0.000 claims abstract description 63
- 238000007637 random forest analysis Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 43
- 239000006185 dispersion Substances 0.000 claims description 17
- 150000001875 compounds Chemical class 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 7
- 238000001914 filtration Methods 0.000 description 5
- 230000009466 transformation Effects 0.000 description 3
- 230000000739 chaotic effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06V10/54—Extraction of image or video features relating to texture
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a wool and cashmere classification method based on scanning electron microscope image processing, which comprises the following steps: acquiring a binary image and a gray image corresponding to the electron microscope image of the textile fiber, and determining the contour texture and the scale texture of the textile fiber texture in the gray image; calculating the roughness of the contour texture; calculating the chaos degree of scale textures; calculating the texture definition of the textile fibers, calculating the uniformity of the texture thickness of the textile fibers, taking the roughness, the chaos, the texture definition and the uniformity of the texture thickness corresponding to the textile fibers as the input of a random forest classification model, taking the fiber types of the textile fibers as the output of the random forest classification model, training the random forest classification model, and classifying the textile fibers to be detected by utilizing the trained random forest classification model.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a wool and cashmere classification method based on scanning electron microscope image processing.
Background
Cashmere is a pure natural fiber, and because textiles made of the cashmere are comfortable to wear, good in elasticity and good in heat retention, the cashmere products are popular with people, more and more people begin to chase after with the development of economy.
At present, the detection and identification of textile fibers in the textile industry are generally carried out on-site identification in factories or farms, and the textile fibers are mainly detected and identified by a portable microscope, but the method is mainly used for classifying according to different edge profiles of cashmere and wool fibers, so that detection personnel are required to have strong judgment capability and identification experience, the detection results are influenced by human factors, and the detection results are inaccurate.
Therefore, it is necessary to provide a method for classifying wool and cashmere based on scanning electron microscope image processing to solve the above problems.
Disclosure of Invention
The invention provides a wool and cashmere classification method based on scanning electron microscope image processing, which aims to solve the existing problems.
The invention discloses a wool and cashmere classification method based on scanning electron microscope image processing, which adopts the following technical scheme: the method comprises the following steps:
acquiring a binary image and a gray image corresponding to an electron microscope image of the textile fiber, wherein the fiber type of the textile fiber is wool or cashmere;
acquiring edge pixel points in the gray level image, performing linear fitting on the edge pixel points to obtain a fitting straight line, and determining contour texture and scale texture of textile fiber texture in the gray level image according to the slope of the fitting straight line;
calculating the roughness of the contour texture according to a Tamura texture feature algorithm;
acquiring a gray level co-occurrence matrix of scale textures in a gray level image, and calculating the chaos degree of the scale textures according to the value of each element in the gray level co-occurrence matrix;
constructing a gray level difference matrix in a corresponding angle direction according to the absolute value of the gray level difference value of each pixel point in the gray level image and the adjacent pixel points in different angle directions, determining a total gray level difference matrix of the gray level image according to the gray level difference matrices in all angle directions, and calculating the texture definition of the textile fibers according to the total gray level difference matrix;
performing distance transformation on the binary image to obtain a target gray image, acquiring the maximum gray value in each row of pixels in the target gray image, constructing a gray sequence according to the maximum gray value corresponding to each row of pixels, calculating the dispersion of the gray sequence according to each maximum gray value in the gray sequence, and taking the dispersion as the uniformity of the texture thickness of the textile fibers;
and constructing a random forest classification model, taking the roughness, the chaos, the texture definition and the uniformity of the texture thickness corresponding to the textile fibers as the input of the random forest classification model, taking the fiber types of the textile fibers as the output of the random forest classification model, training the random forest classification model, and determining the fiber types corresponding to the electron microscope images of the textile fibers to be detected by using the trained random forest classification model.
Preferably, the step of determining the contour texture and the scale texture of the textile fiber texture in the gray-scale image according to the slope of the fitted straight line comprises the following steps:
setting wool or cashmere in the collected electronic microscope image of the textile fiber to be in the horizontal direction;
the edge pixel points corresponding to the fitting straight line with the small slope are contour texture pixel points of wool or cashmere, wherein the edge pixel points form contour textures of textile fiber textures in the gray level image;
the edge pixel points corresponding to the fitting straight line with the large slope are scale texture pixel points of wool or cashmere, wherein the scale texture pixel points form scale textures of textile fiber textures in the gray level image.
Preferably, the step of calculating the roughness of the contour texture according to the Tamura texture feature algorithm comprises:
acquiring a plurality of sliding windows in a gray scale image;
calculating the gray average value in each sliding window;
respectively calculating the average gray level difference between sliding windows of which the pixels of the contour texture do not intersect in the horizontal direction and the vertical direction according to the gray level average value in each sliding window;
determining the optimal size of the sliding window according to the average gray difference;
and calculating the roughness of the contour texture according to the optimal size of the sliding window where each pixel point is located and the size of the gray level image.
Preferably, the formula for calculating the chaos of the scale texture is as follows:
in the formula (I), the compound is shown in the specification,representing scale linesDegree of disorder of the theory;
Preferably, the formula for determining the total gray level difference matrix of the gray image is:
in the formula (I), the compound is shown in the specification,a total gray level difference matrix representing a gray image;
Preferably, the formula for calculating the texture sharpness of the textile fiber:
in the formula (I), the compound is shown in the specification,representing calculating the texture definition of the textile fiber;
Preferably, the step of calculating the dispersion of the gray scale sequence according to each maximum gray scale value in the gray scale sequence includes:
calculating the average gray value of all the maximum gray values in the gray sequence;
and calculating the dispersion of the gray sequence according to the average gray value of all the maximum gray values in the gray sequence, each maximum gray value and the number of the maximum gray values.
Preferably, a dispersion formula of the gray sequence is calculated:
in the formula (I), the compound is shown in the specification,representing the dispersion of the gray sequence;
l represents the number of maximum gray values in the gray sequence;
The beneficial effects of the invention are: the wool and cashmere classifying method based on scanning electron microscope image processing collects images of wool or cashmere fibers through a scanning electron microscope, extracts texture features such as roughness, chaos, texture definition and uniformity of texture thickness of the wool and the cashmere through the image processing method, then takes the texture features as input, takes fiber types of textile fibers corresponding to the features as output, trains in a random forest classification model, and determines the fiber types corresponding to the electron microscope images of the textile fibers to be detected through the trained random forest classification model, so that the wool or cashmere textiles are accurately classified, and the accuracy of detection results is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of the general steps of an embodiment of a wool and cashmere classification method based on scanning electron microscope image processing.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the embodiment of the method for classifying wool and cashmere based on scanning electron microscope image processing of the present invention, it should be noted that, in this embodiment, only textiles made of cashmere fibers or wool fibers are classified, specifically, as shown in fig. 1, the method includes:
s1, obtaining a binary image and a gray image corresponding to an electron microscope image of the textile fiber, wherein the fiber type of the textile fiber is wool or cashmere.
Specifically, because the wool fibers have the characteristics of small width and thinness, for example, the diameter of high-quality fine wool fibers is basically below 25 micrometers, the requirement on acquisition equipment is high, in order to control the cost and not influence the quality of subsequent detection, a scanning electron microscope is selected to acquire an electron microscope image of the fibers of the textile, namely, the electron microscope image of wool or cashmere, then the electron microscope image is subjected to threshold-based binarization processing to obtain a binary image, the threshold is empirically set to be 100, the area containing the cashmere or wool is set to be 1, the background is set to be 0, the processed image is multiplied by the original electron microscope image, the wool or cashmere area in the electron microscope image is extracted to obtain a gray level image of the cashmere or wool, wherein in order to ensure that the edge information of the image completely removes noise in the gray level image at the same time, the gray level image is processed by adopting a method combining median filtering and wiener filtering, the fusion filter combines the advantages of the two filtering, so that the integrity of the edge information can be protected, and the background noise can be well removed.
S2, obtaining edge pixel points in the gray level image, performing linear fitting on the edge pixel points to obtain a fitting straight line, and determining the contour texture and the scale texture of the textile fiber texture in the gray level image according to the slope of the fitting straight line.
Specifically, edge detection is carried out on a gray scale image of the textile fibers by using a canny operator to obtain edge pixel points of the textile fibers, the size of a Gaussian filter is 3 x 3, so that a fuzzy effect generated by filtering is less, fine lines with small and obvious changes can be detected, wool or cashmere edges in each textile fiber are analyzed to obtain edge pixel points of each cashmere or wool, then linear fitting is carried out on the edge pixel points to obtain a fitting straight line formula y = ax + b, a represents a slope, b represents a constant, and the wool or cashmere in an acquired electron microscope image of the textile fibers is set to be in the horizontal direction; the edge pixel points corresponding to the fitting straight line with the small slope are edge pixel points of wool or cashmere, wherein the contour texture pixel points form contour textures of the wool or the cashmere; the edge pixel points corresponding to the fitting straight line with the large slope are scale texture pixel points of wool or cashmere, wherein the scale texture pixel points form scale textures of the wool or the cashmere.
And S3, calculating the roughness of the contour texture according to a Tamura texture feature algorithm.
Specifically, in the embodiment, the roughness of the contour texture is calculated by adopting a method for calculating the roughness in plate classification research based on Gabor filtering and Tamura texture features, and a plurality of sizes of the contour texture are obtained from a gray-scale imageThe sliding window of (2); formula for calculating the mean value of the gray levels in each sliding window:
in the formula (I), the compound is shown in the specification,the size of the sliding window is shown, and k is 0,1,2,3,4,5;
to representThe average value of the gray scale of the sliding window, and the sliding windowA sliding window with a coordinate point as a center;
respectively calculating the average gray difference between the sliding windows of each pixel of the contour texture which are not crossed in the horizontal and vertical directions according to the gray average value in each sliding window, and calculating the formula:
wherein the content of the first and second substances,represents an average gray difference in the horizontal direction;
the optimal size of the sliding window is determined based on the average gray difference, wherein,+= E, when the E reaches the maximum value, the size of the sliding window corresponding to the k value at the moment is the optimal size of the sliding window; calculating the roughness of the contour texture according to the optimal size of the sliding window where each pixel point is located and the size of the gray level image, wherein a roughness formula for calculating the contour texture is as follows:
in the formula, C represents the roughness of the contour texture of the textile raw material, C represents the difference of the gray values on the gray level graph, and the larger the C is, the larger the gray level difference is, the rougher the contour texture of cashmere or wool representing the textile raw material is;
to express the second in a gray scale imageThe optimal size of the sliding window where each pixel point is located.
S4, because cashmere scale texture and wool scale texture also have the difference, cashmere scale texture looks more chaotic, and the degree of torsion is bigger, and the connection between the texture is more random, and cashmere scale texture is compared with wool scale texture, and the randomness of cashmere scale texture is bigger promptly more chaotic, so with the chaos degree of scale texture as the characteristic of distinguishing cashmere and wool, at first, obtain the grey level co-occurrence matrix of scale texture in the grey level image, according to every element' S value calculates the chaos degree of scale texture in the grey level co-occurrence matrix, specific, the formula of the chaos degree of calculation scale texture:
in the formula (I), the compound is shown in the specification,the disorder degree of scale textures is shown, the larger the disorder degree is, the stronger the randomness of cashmere scale textures or wool scale textures is, and the more disordered the scale textures are;
S5, the definition of the cashmere or wool textures is different, wherein the cashmere or wool textures comprise: the method comprises the steps of firstly constructing a gray level difference matrix in a corresponding angle direction according to the absolute value of the gray level difference value of each pixel point in a gray level image and adjacent pixel points in different angle directions, determining a total gray level difference matrix of the gray level image according to the gray level difference matrix in all the angle directions, calculating the texture definition of textile fibers according to the total gray level difference matrix, directly reflecting the difference of gray levels, better reflecting the texture definition of the texture on each wool or cashmere, and reflecting the contrast condition of the brightness of a certain pixel value and the pixel value in the field of the texture definition.
Specifically, an arbitrary pixel point on a gray scale image is taken, the gray scale value of the pixel point is g1 (x, y), and the gray scale value of the pixel point in the theta degree direction is g2 (x, y), an absolute value of the gray scale difference value between the gray scale value of the pixel point and the gray scale value of the adjacent pixel point is calculated, then a gray scale difference matrix in the theta degree direction is constructed according to the absolute value of the gray scale difference value between each pixel point and the pixel point in the theta degree direction, and then a total gray scale difference matrix of the gray scale image is determined according to the gray scale difference matrices in all the angle directions, wherein a formula for determining the total gray scale difference matrix of the gray scale image is as follows:
in the formula (I), the compound is shown in the specification,a total gray level difference matrix representing a gray image;
representing the total number of angles, wherein 4 is taken as the total number of the angles and respectively represents a gray level difference matrix in the horizontal direction, the vertical direction and the diagonal direction;
wherein, the formula for calculating the texture definition of the textile fiber is as follows:
in the formula (I), the compound is shown in the specification,representing calculating the texture definition of the textile fiber;
S6, because the thickness of the cashmere texture is smaller than that of the wool texture, the uniformity of the texture thickness is used as a characteristic for distinguishing wool from cashmere, the distance transformation is carried out on the binary image to obtain a target gray level image, the maximum gray level value in each row of pixels in the target gray level image is obtained, a gray level sequence is constructed according to the maximum gray level value corresponding to each row of pixels, the dispersion of the gray level sequence is calculated according to each maximum gray level value in the gray level sequence, and the dispersion is used as the uniformity of the texture thickness of the textile fibers.
Specifically, the distance transformation of the binary image to obtain the target gray level image is the prior art, and this embodiment does not excessively describe the target gray level image, and calculates the average gray level value of all the maximum gray levels in the gray level sequence; calculating the dispersion of the gray sequence according to the average gray value of all the maximum gray values in the gray sequence, each maximum gray value and the number of the maximum gray values, and calculating the dispersion formula of the gray sequence:
in the formula (I), the compound is shown in the specification,representing the dispersion of the gray sequence;
l represents the number of maximum gray values in the gray sequence;
S7, constructing a random forest classification model, taking the roughness, the chaos, the texture definition and the texture thickness uniformity corresponding to the textile fibers as the input of the random forest classification model and the fiber type corresponding to each textile fiber as the output of the random forest classification model, training the random forest classification model, and determining the fiber type corresponding to the electron microscope image of the textile fiber to be detected by using the trained random forest classification model.
In summary, the invention provides a wool and cashmere classification method based on scanning electron microscope image processing, which includes collecting images of wool or cashmere fibers through a scanning electron microscope, extracting texture features such as roughness, chaos, texture definition and uniformity of texture thickness of the wool and the cashmere by using the image processing method, then using the texture features as input, using fiber types of textile fibers corresponding to the features as output, training a random forest classification model, and determining the fiber types corresponding to the electron microscope images of the textile fibers to be detected by using the trained random forest classification model, thereby realizing accurate classification of wool or cashmere textiles and improving accuracy of detection results.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (7)
1. A wool and cashmere classification method based on scanning electron microscope image processing is characterized by comprising the following steps:
acquiring a binary image and a gray image corresponding to an electron microscope image of the textile fiber, wherein the textile fiber is wool or cashmere;
acquiring edge pixel points in the gray level image, performing linear fitting on the edge pixel points to obtain a fitting straight line, and determining contour texture and scale texture of textile fiber texture in the gray level image according to the slope of the fitting straight line; the steps of determining the contour texture and the scale texture of the textile fiber texture in the gray level image according to the slope of the fitting straight line comprise: setting wool or cashmere in the collected electronic microscope image of the textile fiber to be in the horizontal direction; the edge pixel points corresponding to the fitting straight line with the small slope are contour texture pixel points of wool or cashmere, wherein the edge pixel points form contour textures of textile fiber textures in the gray level image; edge pixel points corresponding to the fitting straight line with the large slope are scale texture pixel points of wool or cashmere, wherein the scale texture pixel points form scale textures of textile fiber textures in the gray level image;
calculating the roughness of the contour texture according to a Tamura texture feature algorithm;
acquiring a gray level co-occurrence matrix of scale textures in a gray level image, and calculating the chaos of the scale textures according to the value of each element in the gray level co-occurrence matrix;
constructing a gray level difference matrix in the corresponding angle direction according to the absolute value of the gray level difference value of each pixel point in the gray level image and the adjacent pixel points in different angle directions, determining a total gray level difference matrix of the gray level image according to the gray level difference matrices in all the angle directions, and calculating the texture definition of the textile fibers according to the total gray level difference matrix;
performing distance conversion on the binary image to obtain a target gray image, acquiring the maximum gray value in each row of pixels in the target gray image, constructing a gray sequence according to the maximum gray value corresponding to each row of pixels, calculating the dispersion of the gray sequence according to each maximum gray value in the gray sequence, and taking the dispersion as the uniformity of the texture thickness of the textile fibers;
and constructing a random forest classification model, taking the roughness, the chaos, the texture definition and the uniformity of the texture thickness corresponding to the textile fibers as the input of the random forest classification model, taking the fiber type of the textile fibers as the output of the random forest classification model, training the random forest classification model, and determining the fiber type corresponding to the electron microscope image of the textile fibers to be detected by using the trained random forest classification model.
2. The wool and cashmere classification method based on scanning electron microscope image processing according to claim 1, wherein the step of calculating the roughness of the contour texture according to Tamura texture feature algorithm comprises:
acquiring a plurality of sliding windows in a gray scale image;
calculating the gray average value in each sliding window;
respectively calculating the average gray level difference between sliding windows of which the pixels of the contour texture do not intersect in the horizontal direction and the vertical direction according to the gray level average value in each sliding window;
determining the optimal size of the sliding window according to the average gray difference;
and calculating the roughness of the contour texture according to the optimal size of the sliding window where each pixel point is located and the size of the gray level image.
3. The method for classifying wool and cashmere based on scanning electron microscope image processing according to claim 1, wherein a formula for calculating the degree of disorder of scale texture is:
in the formula (I), the compound is shown in the specification,representing the chaos of scale texture;
4. The method for classifying wool and cashmere based on scanning electron microscope image processing according to claim 1, characterized in that the formula for determining the total gray level difference matrix of the gray level image is:
in the formula (I), the compound is shown in the specification,a total gray level difference matrix representing a gray image;
5. A method for classifying wool and cashmere based on sem image processing according to claim 1, characterized in that the formula for calculating the texture sharpness of the textile fibers is:
in the formula (I), the compound is shown in the specification,representing calculating the texture definition of the textile fiber;
6. A method for classifying wool and cashmere based on sem image processing according to claim 1, wherein the step of calculating the dispersion of the gray scale sequence according to each maximum gray scale value in the gray scale sequence includes:
calculating the average gray value of all the maximum gray values in the gray sequence;
and calculating the dispersion of the gray sequence according to the average gray value of all the maximum gray values in the gray sequence, each maximum gray value and the number of the maximum gray values.
7. The method for classifying the wool and cashmere based on the scanning electron microscope image processing as claimed in claim 1, wherein the formula of the dispersion of the gray level sequence is calculated as follows:
in the formula (I), the compound is shown in the specification,representing the dispersion of the gray sequence;
l represents the number of maximum gray values in the gray sequence;
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211002556.5A CN115082465B (en) | 2022-08-22 | 2022-08-22 | Wool and cashmere classification method based on scanning electron microscope image processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211002556.5A CN115082465B (en) | 2022-08-22 | 2022-08-22 | Wool and cashmere classification method based on scanning electron microscope image processing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115082465A CN115082465A (en) | 2022-09-20 |
CN115082465B true CN115082465B (en) | 2022-11-11 |
Family
ID=83244688
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211002556.5A Active CN115082465B (en) | 2022-08-22 | 2022-08-22 | Wool and cashmere classification method based on scanning electron microscope image processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115082465B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115861310B (en) * | 2023-02-23 | 2023-05-16 | 深圳市富安娜艺术家居有限公司 | Method for detecting textile defects on surface of bed sheet |
CN117934461B (en) * | 2024-03-21 | 2024-06-07 | 广州航海学院 | Method, system and equipment for analyzing polishing surface roughness of side polishing optical fiber |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105760877B (en) * | 2016-02-19 | 2019-03-05 | 天纺标检测认证股份有限公司 | A kind of woollen and cashmere recognizer based on gray level co-occurrence matrixes model |
KR101824691B1 (en) * | 2017-01-05 | 2018-02-02 | 서울여자대학교 산학협력단 | Method for differentiation of fat-poor angiomyolipoma from clear cell renal cell carcinoma in contrast-enhanced mdct images using quantitative feature classification |
CN113792648A (en) * | 2021-09-13 | 2021-12-14 | 杨凌龙翔数字科技有限公司 | Satellite remote sensing orchard classification method based on multiple time phases |
-
2022
- 2022-08-22 CN CN202211002556.5A patent/CN115082465B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN115082465A (en) | 2022-09-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115082465B (en) | Wool and cashmere classification method based on scanning electron microscope image processing | |
CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
CN115082467B (en) | Building material welding surface defect detection method based on computer vision | |
US8358846B2 (en) | Scanning images for pornography | |
CN116188462B (en) | Noble metal quality detection method and system based on visual identification | |
CN111862194B (en) | Deep learning plant growth model analysis method and system based on computer vision | |
EP1259931B1 (en) | Method for analysing fingerprint images | |
CN116664559B (en) | Machine vision-based memory bank damage rapid detection method | |
CN107038416B (en) | Pedestrian detection method based on binary image improved HOG characteristics | |
CN116611748B (en) | Titanium alloy furniture production quality monitoring system | |
CN116205919A (en) | Hardware part production quality detection method and system based on artificial intelligence | |
JP4000380B2 (en) | Texture image classification device | |
CN106326834B (en) | method and device for automatically identifying sex of human body | |
CN115311507B (en) | Building board classification method based on data processing | |
CN109215010A (en) | A kind of method and robot face identification system of picture quality judgement | |
CN105095907B (en) | A kind of heterogeneous fibre identification method of cotton based on RBF neural | |
CN114549492B (en) | Quality evaluation method based on multi-granularity image information content | |
CN114219794A (en) | Method and system for evaluating surface quality of shaving board based on machine vision | |
CN106529543A (en) | Method and system for dynamically calculating multi-color-grade binary adaptive threshold | |
CN111753794A (en) | Fruit quality classification method and device, electronic equipment and readable storage medium | |
CN114881960A (en) | Feature enhancement-based cloth linear defect detection method and system | |
CN117635609B (en) | Visual inspection method for production quality of plastic products | |
CN115731493A (en) | Rainfall micro physical characteristic parameter extraction and analysis method based on video image recognition | |
CN114882010A (en) | Surface defect detection method based on picture recognition | |
CN116757972B (en) | Fabric defect detection method capable of resisting influence of shadow noise |
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 |