CN109461155B - Raw silk quality detection method - Google Patents
Raw silk quality detection method Download PDFInfo
- Publication number
- CN109461155B CN109461155B CN201811391033.8A CN201811391033A CN109461155B CN 109461155 B CN109461155 B CN 109461155B CN 201811391033 A CN201811391033 A CN 201811391033A CN 109461155 B CN109461155 B CN 109461155B
- Authority
- CN
- China
- Prior art keywords
- raw silk
- image
- defect
- blackboard
- detection
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 230000007547 defect Effects 0.000 claims description 67
- 230000003749 cleanliness Effects 0.000 claims description 46
- 230000015572 biosynthetic process Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 9
- 230000001678 irradiating effect Effects 0.000 claims description 9
- 238000013519 translation Methods 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- 206010020112 Hirsutism Diseases 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 238000004804 winding Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims 1
- 230000000737 periodic effect Effects 0.000 claims 1
- 238000007689 inspection Methods 0.000 abstract description 14
- 230000007246 mechanism Effects 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 241000255789 Bombyx mori Species 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009323 psychological health Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000009941 weaving Methods 0.000 description 1
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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
Abstract
The invention discloses a raw silk quality detection method, which comprises the steps of dividing a raw silk detection blackboard into a plurality of areas and carrying out image shooting; the Fourier transform of the image is adopted to correct the errors of the images of the raw silk blackboard, so that the detection precision is improved; removing filoplume noise and isolated noise through image filtering; the image processing adopts parallel processing, so that the automation of raw silk blackboard detection can be realized, the accuracy of the detection result reaches the level of the current manual detection, the detection efficiency is improved, the errors caused by human factors are reduced, the detection pictures and data are filed, and a basis is provided for the raw silk reinspection; the method replaces completely manual blackboard inspection, replaces manual recording of inspection results and manual certificate delivery, improves the scientificity, objectivity and automation level of raw silk blackboard inspection, relieves the pressure on raw silk inspection and quarantine mechanisms due to the increase of labor cost, and has important practical significance on silk industries and inspection and quarantine mechanisms.
Description
Technical Field
The invention relates to a method for detecting textile raw materials, in particular to a method for detecting the quality of raw silk.
Background
At present, China is the biggest raw silk production and export country in the world, and the production and export amount of China accounts for more than 70% of the international market. The cocoon silk industry is a characteristic and dominant industry in Sichuan province, along with the deep implementation of the Dong-sang-Xishi shift engineering and a new round of western big development strategy in China, Sichuan is becoming the main transfer and accepting place of the silkworm silk industry in China, and the industry development potential is extremely high. Sichuan province, as one of the origins of cocoon silk in China and global silk industry bases, is not only a main production area for producing high-grade raw silk, but also a province for largely using raw silk (silk for silk weaving, twisting and the like). However, the traditional raw silk detection means is relatively backward, and especially, the centralized blackboard inspection (the inspection of cleanliness, cleanliness and evenness) is always carried out for a long time by adopting methods such as visual detection, manual counting and the like. Firstly, the labor intensity of inspectors is high, the raw silk blackboard inspection needs to be carried out in a dark room, the eyes of people are congested due to long-time detection, and the physical and psychological health of people is greatly influenced; secondly, the dependence of the eye detection result on people is very strong, and the eye detection result is greatly influenced by human factors.
Disclosure of Invention
In order to overcome the defects of the existing raw silk manual detection technology, the invention provides a raw silk quality detection method.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a method for detecting raw silk quality, which adopts a machine vision mode to collect and process images of a raw silk detection blackboard in a partition mode, comprises the following steps,
step 1, firstly, preparing a standard raw silk blackboard used as a reference; winding raw silk to be detected on the blackboard according to the standard to manufacture a raw silk detection blackboard; (the specification is national standard GB/T1798-
Step 2, dividing the standard raw silk blackboard into a plurality of areas, irradiating by using a light source, and performing area division translation shooting by using a CCD (charge coupled device) camera;
step 3, synthesizing the shot images of the subareas through a computer, removing boundaries and redundant parts between each image acquisition, and storing the synthesized images; carrying out image binarization processing by using Otsu method to prepare a standard sample photographic image; and the following indexes are counted according to the national standard GB/T1798-:
cleanliness: counting the defect type x, defect area A and defect length a and width b of the standard sample photograph image, and setting the length and width range m according to the national standard; establishing a data table of each defect;
cleanliness: counting the defect area A of the standard sample photograph images under the national standard scoring rule, and calculating the defect average area A1 of a sample photograph with the cleanliness of 100, the defect average area A2 of a sample photograph with the cleanliness of 80 and the defect average area A3 of a sample photograph with the cleanliness of 50;
uniformity: calculating the contrast value range of the image gray scale according to the rating requirements of the national standard of the standard sample image to determine the uniformity;
step 4, dividing the raw silk detection blackboard into a plurality of areas according to the method in the step 2, irradiating by using a light source, and carrying out area division translation shooting by using a CCD camera;
step 5, turning the raw silk detection blackboard to the back, similarly dividing the raw silk detection blackboard into a plurality of areas according to the method in the step 2, irradiating by using a light source, and carrying out area division translation shooting by using a CCD camera;
step 6, carrying out image synthesis on the images of the sub-regions shot in the step 4 and the step 5 through a computer, removing the boundary and redundant parts between each image acquisition, and storing the synthesized front image and back image; carrying out image binarization processing by using Otsu method to prepare front and back images;
step 7, carrying out image local mean filtering on the two-side images obtained in the step 6, and removing hairiness noise and isolated noise; carrying out binarization processing on the image by adopting Otsu method again;
step 8, correcting the image data by an image Fourier transform method to obtain to-be-detected images of two surfaces of the raw silk to be detected;
step 9, counting the shape parameters of the non-zero points of the to-be-detected images on the two sides of the raw silk to be detected: comparing the defect area A, the defect length a and the defect width b with the standard sample image obtained in the step 3 to obtain data of the defect area A, the defect length a and the defect width b, obtaining a cleanliness defect variety, and grading according to the cleanliness variety of national standards to obtain a cleanliness index of the measured raw silk;
step 10, calculating the defect areas of the to-be-detected images on the two sides of the raw silk to be detected, which are obtained in the step 8; calculating the number of pixels of each non-zero communicated region of the binary image by adopting an eight-neighborhood communicated region or four-neighborhood communicated region marking algorithm to obtain the cleanliness of the raw silk to be detected;
step 11, selecting the detected raw silk image of any surface obtained in the step 8, obtaining non-zero pixels in the image, recording the subscript of the non-zero pixels as coordinate values, and replacing the non-zero pixels with the non-zero area gray of the selected surface image obtained in the step 6 and stored before binarization to eliminate the influence of defects on uniformity; calculating the gray gradient of each column, and finding out the column with the maximum gray change; and (4) calculating the contrast ratio of the column with the maximum gray scale and the adjacent column, and comparing the contrast ratio with the uniformity index of the standard sample photo image obtained in the step (3) to obtain a contrast value, namely the uniformity of the raw silk to be detected.
Further, the area of the divided region of the blackboard in the step 2 is calculated according to the resolution of the CCD camera, the resolution of the object plane and the field of view parameters, and the calculation method is as follows: according to the fact that the resolution of an object plane is a, the size of a CCD camera pixel is b, and the magnification factor is k = b/a; the CCD resolution is c x d, then the length of the divided region is: c/k, width d/k. Under the condition of the same camera resolution, the division of the area can improve the resolution and the measurement precision of raw silk detection; the problem that the small bran in the cleanliness index is not enough in resolution to cause inaccurate detection results due to division of areas is avoided.
The image Fourier transform in the step 8 is to extract the period of the pixel point signals of the image on the same straight line, and by comparing the periods of the pixel points on the straight lines at different positions, when the straight line where the pixel point is located is parallel to the silk line position, the obtained period value is minimum, and according to the principle that the period value is minimum, the rotation angle can be determined, so that the raw silk in the image is adjusted to be in the completely vertical direction, and the width of the raw silk expansion part is calculated in the subsequent step.
In the step 11, the contrast between the standard sample image and the adjacent column is calculated and then compared with the evenness index of the standard sample image obtained in the step 3, and the comparison process is as follows:
if the obtained contrast is consistent with the contrast in the standard sample photograph, the evenness is directly graded according to the standard, and if the contrast is not consistent with the contrast in the standard sample photograph, the following rule is adopted: the contrast exceeds that of the standard sample according to V0, and does not exceed that of V1, and the contrast is changed once; above V1 no more than V2 is a two degree change in formation, and above V2 is rated as a three degree change in formation. (the rating rule is the national standard GB/T1798-.
The invention has the beneficial effects that: and (3) carrying out subarea image acquisition processing on the raw silk detection blackboard by adopting a machine vision mode. The automatic detection device can realize the automation of raw silk blackboard detection, the accuracy of the detection result reaches the level of the current manual detection, the detection efficiency is improved, the errors caused by human factors are reduced, the complete manual blackboard detection is replaced, and the manual recording and manual certificate transmission of the detection result are replaced.
1. Dividing a raw silk detection blackboard into a plurality of areas for shooting; under the condition of the same CCD camera resolution, the division of the area can improve the resolution and the measurement precision of raw silk detection; the method avoids the defects that the resolution is insufficient for small bran in the cleanliness index and the accuracy of the detection result is insufficient when the shooting is not divided.
2. The images are subjected to binary imaging processing by adopting the Otsu method and are subjected to Fourier transform to correct the errors of the images on the raw silk blackboard, so that the detection precision is greatly improved; removing filoplume noise and isolated noise through image filtering; and the image processing adopts parallel processing, so that the efficiency is high.
3. Acquiring the coordinate value of the non-zero point of the to-be-detected image of the raw silk to be detected, and replacing the non-zero point area gray scale of the front image which is acquired in the step 6 and is not stored before binarization, so as to eliminate the influence of the defects on uniformity; calculating the column gray gradient and finding out the column with the maximum gray change; and (4) calculating the contrast of the raw silk and the adjacent columns, and then comparing the contrast with the evenness index of the standard sample photo image obtained in the step (3) to obtain a contrast value, namely the evenness of the raw silk to be detected. The method has the technical effect that the functional relation between the raw silk evenness and the image gray scale is established according to the corresponding relation between the raw silk evenness and the image gray scale. The evenness rating does not contain information of cleanliness and cleanliness, indexes influencing the cleanliness and the cleanliness are mainly embodied as defect data, defects generally appear as points with larger integral background gray scale on an image, and therefore, the elimination of the defects is beneficial to the accuracy of the evenness index rating, namely, the non-zero-point field gray scale of the image which is stored before binarization is adopted for replacement after the image synthesis, and the influence of the defects on the evenness is eliminated.
4. The method can simultaneously detect the cleanliness, cleanliness and evenness of the raw silk; the scientificity and objectivity of raw silk blackboard inspection are greatly improved, the pressure brought to a raw silk inspection and quarantine mechanism due to the improvement of labor cost is relieved, and the method has important practical value for silk industries and inspection and quarantine mechanisms.
Detailed Description
The present invention will be further described with reference to the following examples.
A method for detecting raw silk quality, which adopts a machine vision mode to collect and process images of a raw silk detection blackboard in a partition mode, comprises the following steps,
step 1, firstly, preparing a standard raw silk blackboard used as a reference; winding raw silk to be detected on the blackboard according to the standard to manufacture a raw silk detection blackboard; (the specification is national standard GB/T1798-
Step 2, dividing the standard raw silk blackboard into a plurality of areas, irradiating by using a light source, and performing area division translation shooting by using a CCD (charge coupled device) camera; the area of the divided region is calculated according to the resolution of the CCD camera, the resolution of an object plane and a view field, and the calculation method is as follows: according to the fact that the resolution of an object plane is a, the size of a CCD camera pixel is b, and the magnification factor is k = b/a; the CCD resolution is c x d, then the length of the divided region is: c/k, width d/k. Under the condition of the same CCD camera resolution, the division of the area can improve the resolution and the measurement precision of raw silk detection; the problem that the small bran in the cleanliness index is not enough in resolution to cause inaccurate detection results due to division of areas is avoided.
Step 3, synthesizing the shot images of the subareas through a computer, removing boundaries and redundant parts between each image acquisition, and storing the synthesized images; carrying out image binarization processing by using Otsu method to prepare a standard sample photographic image; and the following indexes are counted according to the national standard GB/T1798-:
cleanliness: counting the defect type x, defect area A and defect length a and width b of the standard sample photograph image, and setting the length and width range m according to the national standard; establishing a data table of each defect;
cleanliness: counting the defect area A of the standard sample photograph images under the national standard scoring rule, and calculating the defect average area A1 of a sample photograph with the cleanliness of 100, the defect average area A2 of a sample photograph with the cleanliness of 80 and the defect average area A3 of a sample photograph with the cleanliness of 50;
uniformity: calculating the contrast value range of the image gray scale according to the rating requirements of the national standard of the standard sample image to determine the uniformity;
the specific implementation process comprises the following steps: and (3) classifying the defects in the image according to the cleanliness standard sample photograph, calculating the length a (pixel value), the width b (pixel value) and the shape x of each defect in the image, and establishing 11 types of standard defect data of the standard sample photograph. Calculating the area s (pixel value) and the quantity c of each defect in each scoring standard according to cleanliness standard sample pictures, and establishing 8 standard cleanliness scoring data; according to the evenness standard sample photograph image, the contrast of the corresponding image gray scale under each level of evenness is calculated, and 3 standard evenness data are established.
Step 4, dividing the raw silk detection blackboard into a plurality of areas according to the method in the step 2, irradiating by using a light source, and carrying out area division translation shooting by using a CCD camera;
step 5, turning the raw silk detection blackboard to the back, similarly dividing the raw silk detection blackboard into a plurality of areas according to the method in the step 2, irradiating by using a light source, and carrying out area division translation shooting by using a CCD camera;
step 6, carrying out image synthesis on the images of the sub-regions shot in the step 4 and the step 5 through a computer, removing the boundary and redundant parts between each image acquisition, and storing the synthesized front image and back image; carrying out image binarization processing by using Otsu method to prepare front and back images;
step 7, carrying out image local mean filtering on the two-side images obtained in the step 6, and removing hairiness noise and isolated noise; carrying out binarization processing on the image by adopting Otsu method again;
step 8, correcting the image data by an image Fourier transform method to obtain to-be-detected images of two surfaces of the raw silk to be detected; the image Fourier transform method is to extract the period of the pixel point signal of the same straight line of the image, and by comparing the periods of the pixel points on the straight lines at different positions, when the straight line where the pixel point is positioned is parallel to the silk line position, the obtained period value is the minimum, and the principle is that the rotation angle can be determined according to the principle of the minimum period value, so that the raw silk in the image is adjusted to be in the completely vertical direction, and the width of the raw silk expansion position can be calculated later.
Step 9, counting the shapes of all non-zero points of the to-be-detected images on the two sides of the raw silk to be detected, comparing the non-zero points with the data obtained by the image of the standard sample image obtained in the step 3, specifically, matching the non-zero points (the defect area A, the defect length a and the width b are raw silk defect data) with the 11 types of standard defect data (the defect area A, the defect length a and the width b) obtained in the step 3, finding out the types of the defects to obtain the types of cleanliness defects, and grading according to the types of cleanliness of national standards (the grading standard is the national standard GB/T1798-;
step 10, calculating the defect areas of the to-be-detected images on the two sides of the raw silk to be detected, which are obtained in the step 8; calculating Euler numbers of the binary non-zero regions, namely the number of pixel points, by adopting an eight-neighborhood connected region or four-neighborhood connected region marking algorithm, and calculating the number of the pixel points of each non-zero connected region of the binary image to obtain the cleanliness of the raw silk to be detected;
step 11, selecting the detected raw silk image of any surface obtained in the step 8, obtaining non-zero pixels in the image, recording the subscript of the non-zero pixels as coordinate values, and replacing the non-zero pixels with the non-zero area gray of the selected surface image obtained in the step 6 and stored before binarization to eliminate the influence of defects on uniformity; calculating the gray gradient of each column, and finding out the column with the maximum gray change; and (4) calculating the contrast ratio of the column with the maximum gray scale and the adjacent column, and comparing the contrast ratio with the uniformity index of the standard sample photo image obtained in the step (3) to obtain a contrast value, namely the uniformity of the raw silk to be detected.
If the obtained contrast is consistent with the contrast in the standard sample photograph, the evenness is directly graded according to the standard (the grading rule is the national standard GB/T1798-: the contrast exceeds that of the standard sample according to V0, and does not exceed that of V1, and the contrast is changed once; above V1 no more than V2 is a two degree change in formation, and above V2 is rated as a three degree change in formation.
The method has the technical effect that the functional relation between the raw silk evenness and the image gray scale is established according to the corresponding relation between the raw silk evenness and the image gray scale. The evenness rating does not contain information of cleanliness and cleanliness, and indexes influencing the cleanliness and the cleanliness are mainly represented as defect data, and defects are generally represented as points with larger integral background gray scale on images, so that the elimination of the defects is beneficial to accurate grading of the evenness index. Namely, the non-zero area gray scale of the image which is not stored before binarization is adopted for replacement after image synthesis, thereby eliminating the influence of defects on uniformity.
The invention adopts a machine vision mode to collect and process the partitioned images of the raw silk detection blackboard. The automatic detection device can realize the automation of raw silk blackboard detection, the accuracy of the detection result reaches the level of the current manual detection, the detection efficiency is improved, the errors caused by human factors are reduced, the complete manual blackboard detection is replaced, and the manual recording and manual certificate transmission of the detection result are replaced.
The method can simultaneously detect the cleanliness, cleanliness and evenness of the raw silk; the scientificity and objectivity of raw silk blackboard inspection are greatly improved, the pressure brought to a raw silk inspection and quarantine mechanism due to the improvement of labor cost is relieved, and the method has important practical value for silk industries and inspection and quarantine mechanisms.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (4)
1. A raw silk quality detection method is characterized in that a machine vision mode is adopted, and a method for collecting and processing images of a raw silk detection blackboard in a partition mode comprises the following steps,
step 1, firstly, preparing a standard raw silk blackboard used as a reference; winding raw silk to be detected on the blackboard according to the standard to manufacture a raw silk detection blackboard;
step 2, dividing the standard raw silk blackboard into a plurality of areas, irradiating by using a light source, and performing area division translation shooting by using a CCD (charge coupled device) camera;
step 3, synthesizing the shot images of the subareas through a computer, removing boundaries and redundant parts between each image acquisition, and storing the synthesized images; carrying out image binarization processing by using Otsu method to prepare a standard sample photographic image; and the following indexes are counted according to the national standard GB/T1798-:
cleanliness: counting the defect type x, defect area A and defect length a and width b of the standard sample photograph image, and setting the length and width range m according to the national standard; establishing a data table of each defect;
cleanliness: counting the defect area A of the standard sample photograph images under the national standard scoring rule, and calculating the defect average area A1 of a sample photograph with the cleanliness of 100, the defect average area A2 of a sample photograph with the cleanliness of 80 and the defect average area A3 of a sample photograph with the cleanliness of 50;
uniformity: calculating the contrast value range of the image gray scale according to the rating requirements of the national standard of the standard sample image to determine the uniformity;
step 4, dividing the raw silk detection blackboard into a plurality of areas according to the method in the step 2, irradiating by using a light source, and carrying out area division translation shooting by using a CCD camera;
step 5, turning the raw silk detection blackboard to the back, similarly dividing the raw silk detection blackboard into a plurality of areas according to the method in the step 2, irradiating by using a light source, and carrying out area division translation shooting by using a CCD camera;
step 6, carrying out image synthesis on the images of the sub-regions shot in the step 4 and the step 5 through a computer, removing the boundary and redundant parts between each image acquisition, and storing the synthesized front image and back image; carrying out image binarization processing by using Otsu method to prepare front and back images;
step 7, carrying out image local mean filtering on the two-side images obtained in the step 6, and removing hairiness noise and isolated noise; carrying out binarization processing on the image by adopting Otsu method again;
step 8, correcting the image data by an image Fourier transform method to obtain to-be-detected images of two surfaces of the raw silk to be detected;
step 9, counting the shape parameters of the non-zero points of the to-be-detected images on the two sides of the raw silk to be detected: comparing the defect area A, the defect length a and the defect width b with the standard sample image obtained in the step 3 to obtain data of the defect area A, the defect length a and the defect width b, obtaining a cleanliness defect variety, and grading according to the cleanliness variety of national standards to obtain a cleanliness index of the measured raw silk;
step 10, calculating the defect areas of the to-be-detected images on the two sides of the raw silk to be detected, which are obtained in the step 8; calculating the number of pixels of each non-zero communicated region of the binary image by adopting an eight-neighborhood communicated region or four-neighborhood communicated region marking algorithm to obtain the cleanliness of the raw silk to be detected;
step 11, selecting the detected raw silk image of any surface obtained in the step 8, obtaining non-zero pixels in the image, recording the subscript of the non-zero pixels as coordinate values, and replacing the non-zero pixels with the non-zero area gray of the selected surface image obtained in the step 6 and stored before binarization to eliminate the influence of defects on uniformity; calculating the gray gradient of each column, and finding out the column with the maximum gray change; and (4) calculating the contrast ratio of the column with the maximum gray scale and the adjacent column, and comparing the contrast ratio with the uniformity index of the standard sample photo image obtained in the step (3) to obtain a contrast value, namely the uniformity of the raw silk to be detected.
2. The raw silk quality detection method of claim 1, wherein the area of the divided region of the blackboard in the step 2 is calculated according to the resolution of the CCD camera, the resolution of the object plane and the field of view parameters by the following calculation method: according to the fact that the resolution of an object plane is a, the size of a CCD camera pixel is b, and the magnification factor is k = b/a; the CCD resolution is c x d, then the length of the divided region is: c/k, width d/k.
3. The raw silk quality detection method of claim 1, wherein the image fourier transform in step 8 is a periodic extraction of pixel point signals of the image located in the same straight line, and by comparing the periods of the pixel points on the straight lines at different positions, when the straight line where the pixel points are located is parallel to the silk position, the obtained period value is minimum, and according to the principle that the period value is minimum, the rotation angle can be determined, so that the raw silk in the image is adjusted to be in a completely vertical direction.
4. The raw silk quality detection method of claim 1, wherein in the step 11, the contrast between the raw silk and the adjacent column is calculated and compared with the evenness index of the standard sample image obtained in the step 3, and the comparison process is as follows:
if the obtained contrast is consistent with the contrast in the standard sample photograph, the evenness is directly graded according to the standard, and if the contrast is not consistent with the contrast in the standard sample photograph, the following rule is adopted: the contrast exceeds that of the standard sample according to V0, and does not exceed that of V1, and the contrast is changed once; and if the average value exceeds V1 and does not exceed V2, the average degree is changed for two degrees, and if the average value exceeds V2, the average value is evaluated according to the average degree change for three degrees, wherein the rating rule is national standard GB/T1798-.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811391033.8A CN109461155B (en) | 2018-11-21 | 2018-11-21 | Raw silk quality detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811391033.8A CN109461155B (en) | 2018-11-21 | 2018-11-21 | Raw silk quality detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109461155A CN109461155A (en) | 2019-03-12 |
CN109461155B true CN109461155B (en) | 2021-06-22 |
Family
ID=65611127
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811391033.8A Active CN109461155B (en) | 2018-11-21 | 2018-11-21 | Raw silk quality detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109461155B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111260717A (en) * | 2020-01-10 | 2020-06-09 | 西南大学 | Cocoon silk fineness direct measuring method without reeling silk and application thereof |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102221559A (en) * | 2011-03-05 | 2011-10-19 | 河海大学常州校区 | Online automatic detection method of fabric defects based on machine vision and device thereof |
CN102520028A (en) * | 2011-12-16 | 2012-06-27 | 浙江丝绸科技有限公司 | Method for digitally processing raw silk defects |
WO2013192624A1 (en) * | 2012-06-22 | 2013-12-27 | Northeastern University | Fiber orientation image processing methods and systems |
-
2018
- 2018-11-21 CN CN201811391033.8A patent/CN109461155B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102221559A (en) * | 2011-03-05 | 2011-10-19 | 河海大学常州校区 | Online automatic detection method of fabric defects based on machine vision and device thereof |
CN102520028A (en) * | 2011-12-16 | 2012-06-27 | 浙江丝绸科技有限公司 | Method for digitally processing raw silk defects |
WO2013192624A1 (en) * | 2012-06-22 | 2013-12-27 | Northeastern University | Fiber orientation image processing methods and systems |
Non-Patent Citations (2)
Title |
---|
INFLUENCE OF SLUG CATCHER ON QUALITY OF TASAR SILK YARN;Kiran B Malali 等;《3rd International Conference on Natural Fibers: Advanced Materials for a Greener World, ICNF》;20170623;第33-38页 * |
基于图像分析技术的纱线黑板条干检测;章国红 等;《棉纺织技术》;20161231;第19-24页 * |
Also Published As
Publication number | Publication date |
---|---|
CN109461155A (en) | 2019-03-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109141232B (en) | Online detection method for disc castings based on machine vision | |
CN109856156A (en) | A kind of display panel tiny flaw determination method and device based on AOI | |
CN108921819B (en) | Cloth inspecting device and method based on machine vision | |
CN105021628A (en) | Detection method for surface defects of optical fiber image inverter | |
CN115100206A (en) | Printing defect identification method for textile with periodic pattern | |
CN108088381B (en) | Non-contact type micro gap width measuring method based on image processing | |
CN109406527B (en) | System and method for detecting fine appearance defects of micro camera module lens | |
CN111047586B (en) | Pixel equivalent measuring method based on machine vision | |
CN111062961A (en) | Contact lens edge defect detection method based on deep learning | |
CN111415349B (en) | Polyester filament yarn detection method based on image processing technology | |
CN110458809B (en) | Yarn evenness detection method based on sub-pixel edge detection | |
Fu et al. | Medicine glass bottle defect detection based on machine vision | |
CN109461155B (en) | Raw silk quality detection method | |
CN109297979B (en) | Raw silk quality detection device and detection method | |
CN106501278B (en) | Surface of the light tube defect classification method and system based on invariable rotary textural characteristics | |
CN114688969A (en) | Optical lens size detection device and method | |
CN116880353A (en) | Machine tool setting method based on two-point gap | |
CN106530248A (en) | Method for intelligently detecting scene video noise of transformer station | |
CN106504251B (en) | A kind of electric aluminum foil cubic texture detection method of content based on picture processing | |
CN104165696A (en) | Material surface color feature on-line automatic detection method | |
CN112037233B (en) | Image binarization method based on Otsu method and K-means clustering algorithm combined optimization | |
CN108230285A (en) | Baffle ring quality determining method based on machine vision | |
CN109211937A (en) | A kind of detection system and its detection method of underwear elastic woven tape curved strip defect | |
CN108871224B (en) | Groove depth detection method for LED glass lamp cup | |
CN113962921A (en) | Grid line detection method for photovoltaic cell |
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 |