CN114998227A - Cloth printing and dyeing defect detection method and system based on image processing - Google Patents
Cloth printing and dyeing defect detection method and system based on image processing Download PDFInfo
- Publication number
- CN114998227A CN114998227A CN202210555003.6A CN202210555003A CN114998227A CN 114998227 A CN114998227 A CN 114998227A CN 202210555003 A CN202210555003 A CN 202210555003A CN 114998227 A CN114998227 A CN 114998227A
- Authority
- CN
- China
- Prior art keywords
- texture
- suspected
- saturation
- stain area
- 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.)
- Pending
Links
- 239000004744 fabric Substances 0.000 title claims abstract description 51
- 238000004043 dyeing Methods 0.000 title claims abstract description 35
- 230000007547 defect Effects 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 title claims description 18
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 2
- 239000004753 textile Substances 0.000 abstract description 3
- 230000011218 segmentation Effects 0.000 description 4
- 238000009999 singeing Methods 0.000 description 2
- 239000011324 bead Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004061 bleaching Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- 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
- G06T7/40—Analysis of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention relates to the technical field of textile dyeing, in particular to a method and a system for detecting dyeing defects of cloth based on image processing.
Description
Technical Field
The invention relates to the technical field of textile dyeing, in particular to a method and a system for detecting cloth printing and dyeing defects based on image processing.
Background
Textiles can leave visual defects in the appearance of fabrics during the printing and dyeing process due to problems with dyeing processes and operations, such as: the dyeing process comprises the following steps of dyeing, bleaching, punching and the like, wherein oil drop-shaped dyeing spots are mostly generated on an E/R blended fabric, the dyed fabric has the oil drop-shaped spots, the color of the dyed fabric is slightly darker than that of a normal part, when the dyed fabric is observed by a magnifier, the tip of the pile of the fabric is in a tiny bead shape, the pile of the fabric is more than that of the normal part, the reason is that the pile of the dyed spot and the color of the fabric is not fully burnt due to uneven singeing, the pile of the dyed spot and the color of the fabric is in a fused mass at the tip, and the color absorbing performance is strong.
At present, the identification of stain defects of fabrics usually collects fabric surface images, and detects the stain defects by performing threshold segmentation on the fabric surface images, but the threshold of the threshold segmentation is set based on human experience, so the method can reduce the accuracy of the defect detection result.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a method and a system for detecting defects in printing and dyeing of cloth based on image processing, wherein the technical scheme adopted is as follows:
the embodiment of the invention provides a method for detecting cloth printing and dyeing defects based on image processing, which comprises the following steps:
collecting RGB images on the surface of the cloth, dividing the RGB images into a plurality of sub-regions according to equal areas, obtaining the color saturation of each sub-region, and confirming a suspected stain area in each sub-region according to the saturation value of each pixel point in each sub-region;
carrying out edge extraction on the current suspected stain area to obtain an edge contour, and respectively calculating a direction angle difference value between each edge point on the edge contour and a normal texture direction to obtain an overall texture direction difference value of the current suspected stain area; quantifying the direction angle difference value of each edge point to construct an edge histogram of the direction angle difference value, calculating the entropy of the edge histogram to serve as a texture complex index of the current suspected stain area, and calculating a texture uniformity index according to the length of a texture element in the current suspected stain area, wherein the length of the texture element represents the maximum pixel point set formed by continuous pixels of a constant level on a straight line texture; combining the integral texture direction difference value, the texture complex index, the texture uniform index and the corresponding color saturation to obtain a texture change parameter of the current suspected stain area;
respectively calculating the spacing distance between any two pixel points under each saturation in the current suspected stain area to obtain the frequency of each type of spacing distance under each saturation, and taking the product of each frequency and the texture change parameter as the characteristic value of the corresponding spacing distance under the corresponding saturation; calculating a related characteristic value between pixel points in the current suspected stain area by combining the interval distance under each saturation degree and the corresponding characteristic value, and confirming the stain area by the related characteristic value; and confirming the dyeing spot area in each sub-area to finish the cloth printing and dyeing defect detection.
Further, the method for calculating the direction angle difference between each edge point on the edge contour and the normal texture direction comprises:
establishing a rectangular coordinate system according to the direction of the normal dyeing texture in the sub-region, wherein the origin of the rectangular coordinate system is the boundary junction between the normal pixel point of the sub-region and the pixel point of the suspected stain region, the suspected stain region is divided into an upper part and a lower part by the X axis of the rectangular coordinate system, and the longitudinal coordinate distance of each part is equal;
and respectively acquiring an included angle between each edge point and the X axis of the rectangular coordinate system according to the positions of the edge points and the original point, and referring the included angle as a direction angle difference value between the corresponding edge point and the normal texture direction.
Further, the method for obtaining the overall texture direction difference value includes:
and calculating an average direction angle difference value according to the direction angle difference value of each edge point on the edge contour, and taking the average direction angle difference value as the overall texture direction difference value of the suspected stain area.
Further, the method for calculating the texture uniformity index according to the length of the texture primitive in the current suspected stain area comprises the following steps:
respectively acquiring the primitive length number of the length of the texture primitive corresponding to each gray level according to the lengths of the texture primitives corresponding to different gray levels in the suspected stain area on the basis of the gray level image of the sub-area where the suspected stain area is located, and calculating the total primitive length number according to the primitive length number of the length of the texture primitive corresponding to each gray level;
calculating the length sum of the texture primitive of the current gray level according to the length of the texture primitive of the current gray level and the corresponding length number of the primitive, and accumulating the length sum of the texture primitive of each gray level to obtain the length sum of the whole texture primitive; and calculating the ratio of the total length sum of the texture primitives to the total length of the texture primitives, and taking the ratio as a texture uniformity index.
Further, the calculating formula for obtaining the texture change parameter of the current suspected stain area by combining the overall texture direction difference value, the texture complex index, the texture uniformity index and the corresponding color saturation includes:
wherein gamma is a texture change parameter of a suspected stain area; delta is the difference value of the overall texture direction of the suspected stain area; beta is a texture complex index of a suspected stain area; alpha is the texture uniformity index of the suspected stain area; and S is the color saturation of the sub-area where the suspected stain area is located.
Further, the method for calculating the correlation characteristic value between the pixel points in the current suspected stain area by combining the interval distance under each saturation degree and the corresponding characteristic value comprises the following steps:
calculating the mean value and standard deviation of the feature values of all the spacing distances under the current saturation according to the feature values of the spacing distances, and calculating a first correlation value between the pixel points corresponding to the current saturation by combining the feature values of each type of spacing distance under the current saturation, the mean value of the feature values and the standard deviation of the feature values;
respectively calculating a first correlation value corresponding to each saturation in the suspected stain area, and taking the addition result of all the first correlation values as a correlation characteristic value between pixel points in the suspected stain area;
wherein, the calculation formula of the first correlation value is as follows:
wherein, w b A first correlation value, P, corresponding to the saturation b j b Frequency of separation distance of class j under saturation b, epsilon b Is the mean value of the characteristic values at the saturation b, σ b Is the standard deviation of the eigenvalues at saturation b.
Further, the embodiment of the invention also provides an image processing-based cloth printing defect detection system, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to realize the steps of any one of the image processing-based cloth printing defect detection methods.
The embodiment of the invention at least has the following beneficial effects: dividing the surface image of the cloth into a plurality of sub-areas, confirming a suspected stain area in each sub-area, analyzing related characteristic values among pixel points in the suspected stain area according to a plurality of texture characteristic differences of the suspected stain area and the color of the sub-area, and determining the stain area according to the related characteristic values, so that the stain defect detection result is more accurate, and the detection error of threshold segmentation is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart illustrating steps of a method for detecting defects in printing and dyeing of a piece of cloth based on image processing according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to a method and a system for detecting defects in printing and dyeing of cloth based on image processing according to the present invention, with reference to the accompanying drawings and preferred embodiments. In the following description, the different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
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 invention belongs.
The following describes a specific scheme of a method and a system for detecting printing and dyeing defects of cloth based on image processing in detail with reference to the accompanying drawings.
The specific scenes of the embodiment of the invention are as follows: and identifying the printing and dyeing defects aiming at the single-color printing and dyeing result of the cloth.
Referring to fig. 1, a flowchart illustrating steps of a method for detecting printing defects of a piece of cloth based on image processing according to an embodiment of the present invention is shown, where the method includes the following steps:
and S001, collecting an RGB image on the surface of the cloth, dividing the RGB image into a plurality of sub-regions according to equal areas, acquiring the color saturation of each sub-region, and confirming the suspected stain area in each sub-region according to the saturation value of each pixel point in the sub-region.
Specifically, RGB images on the surface of the cloth are collected through an industrial camera arranged, the RGB images are converted into HSV color space, corresponding HSV images are obtained, and the HSV images are divided into a plurality of sub-regions according to the equal area; because the dye color used by single printed and dyed cloth is the same, and the saturation value S can represent the dyeing depth information of each pixel point position, the color saturation of each subarea is calculated according to the saturation value of each pixel point, and the calculation method comprises the following steps: and acquiring a maximum saturation value and a minimum saturation value in the current sub-region according to the saturation values of the pixel points, calculating a saturation difference value between the maximum saturation value and the minimum saturation value, and taking the ratio of the saturation difference value to the maximum saturation value as the color saturation of the current sub-region.
Further, since the color of the stain area is darker than that of the normal area, and the saturation value of the pixel points in the corresponding stain area is smaller, the suspected stain area in each sub-area is roughly detected according to the saturation value of each pixel point, specifically: and calculating an average saturation value according to the saturation value of each pixel point in the current sub-region, acquiring pixel points with saturation values smaller than the average saturation value, and connecting a plurality of continuous pixel points into a suspected stain area of the current sub-region.
Step S002, performing edge extraction on the current suspected stain area to obtain an edge contour, and respectively calculating a direction angle difference value between each edge point on the edge contour and a normal texture direction to obtain an overall texture direction difference value of the current suspected stain area; quantifying the direction angle difference value of each edge point to construct an edge histogram of the direction angle difference value, calculating the entropy of the edge histogram to be used as a texture complex index of the current suspected stain area, calculating a texture uniformity index according to the length of a texture element in the current suspected stain area, wherein the length of the texture element represents the maximum pixel point set formed by continuous pixels with constant level on a straight line texture; and obtaining the texture change parameters of the current suspected stain area by combining the integral texture direction difference value, the texture complex index, the texture uniformity index and the corresponding color saturation.
Specifically, the texture on the surface of the cloth is regularly arranged and extends in a gradient manner in a certain direction, but if the tip of the cloth forms a fused mass shape due to uneven singeing, and therefore when a stain appears, the texture rule on the surface of the cloth changes, and the gradient direction of the texture also changes, so that the texture direction characteristics of a suspected stain area are analyzed based on the normal texture direction, specifically: performing edge extraction on the suspected stain area to obtain an edge profile; the method comprises the steps of establishing a rectangular coordinate system according to the direction of normal dyeing textures in a sub-area, enabling the origin of the rectangular coordinate system to be the boundary junction of normal pixel points of the sub-area and pixel points of a suspected stain area, enabling the X-axis of the rectangular coordinate system to divide the suspected stain area into an upper portion and a lower portion, enabling the longitudinal coordinate distance of each portion to be equal, respectively calculating the angle between each edge point on the edge contour of the suspected stain area and the origin of the rectangular coordinate system, enabling the angle to be called the direction angle difference value between the corresponding edge point and the normal texture direction, calculating the average direction angle difference value according to the direction angle difference value of each edge point on the edge contour, and enabling the average direction angle difference value to serve as the overall texture direction difference value delta of the suspected stain area.
As an example, since the suspected stain area is located in the first quadrant and the fourth quadrant of the rectangular coordinate system, the calculation formula of the direction angle difference value is as follows: the calculation formula corresponding to the first quadrant is
Wherein theta is i Is the direction angle difference of the ith edge point, i.e. the included angle between the edge point and the transverse axis, x i Is the abscissa value, y, of the ith edge point i The ordinate value of the ith edge point; the fourth quadrant corresponds to the calculation formula
Further, the direction angle difference of each edge point on the edge contour of the suspected stain area is quantified to measure the initial direction angle difference range [0, 180 °]Quantized to [0,36 ° ]]And further constructing an edge histogram of the direction angle difference value according to the quantized direction angle difference value, wherein the quantization formula is
And the quantized direction angle difference value of the ith edge point. And then calculating the entropy value of the edge histogram, and taking the entropy value as the texture complexity index beta of the suspected stain area.
It should be noted that the gray histogram reflects the frequency of occurrence of each gray level in the gray image, and the edge histogram reflects the frequency of occurrence of the angle difference between the edge point in the suspected stain area and the normal texture direction through the category inference.
Further, a large number of adjacent pixel points with the same gray level can reflect roughness of textures, a single pixel point reflects details of textures, the length of a texture primitive in different directions can be used as texture description, the length of the texture primitive is represented by a maximum pixel point set formed by continuous pixel points with constant levels on a straight line texture, and then texture uniformity indexes are analyzed according to the length of the texture primitive in a suspected stain area and the corresponding gray level, specifically: obtaining a gray image of a sub-area where a suspected stain area is located, and respectively obtaining the primitive length number of the length of the texture primitive corresponding to each gray level according to the lengths of the texture primitives corresponding to different gray levels in the suspected stain area, namely the length l of the texture primitive corresponding to the gray level a a Has a primitive length number of B (a, l) a ) Calculating the total number of primitive lengths according to the primitive length number of the texture primitive length corresponding to each gray level; calculating the length sum of the texture elements corresponding to the gray levels according to the length of the texture elements of each gray level and the length number of the corresponding elements, accumulating the length sum of the texture elements of each gray level to obtain the length sum of the whole texture elements, calculating the ratio of the length sum of the whole texture elements to the length sum of the elements, and taking the ratio as the texture uniformity index of the suspected stain area.
The surface texture of the cloth without flaw is regular, when stains appear on the surface of the cloth, the texture of a stain area is different from the normal texture, and the color of a sub-area where the stain area is located is different from the color of the normal area, so that the texture change parameter of the suspected stain area is calculated by combining the overall texture direction difference value, the texture complexity index, the texture uniformity index and the color saturation degree of the sub-area where the suspected stain area is located, and the calculation formula of the texture change parameter is as follows:
wherein gamma is a texture change parameter of the suspected stain area; delta is the difference value of the overall texture direction of the suspected stain area; beta is a texture complex index of a suspected stain area; alpha is the texture uniformity index of the suspected stain area; and S is the color saturation of the sub-area where the suspected stain area is located.
It should be noted that, the darker the stain color is, the larger the saturation value is, the larger the color saturation of the corresponding sub-region is, and the more likely the suspected stain region is the stain region; similarly, the larger the difference value of the whole texture direction, the larger the texture complex index and the larger the texture uniformity index, the more likely the suspected stain area is to be the stain area.
Step S003, respectively calculating the spacing distance between any two pixel points under each saturation in the current suspected stain area to obtain the frequency of each type of spacing distance under each saturation, and taking the product of each frequency and a texture change parameter as a characteristic value of the corresponding spacing distance under the corresponding saturation; calculating a related characteristic value between pixel points in the current suspected stain area by combining the interval distance under each saturation degree and the corresponding characteristic value, and confirming the stain area by the related characteristic value; and confirming the dyeing spot area in each sub-area to finish the cloth printing and dyeing defect detection.
Specifically, taking saturation b as an example, the interval distance between any two of the pixels corresponding to saturation b in the suspected stain area is respectively calculated, and the frequency of each type of interval distance is respectively calculated according to all the interval distances under saturation b, that is, the frequency is
Wherein P is i Frequency of the i-th class spacing, M is the total number of spacing distances, M i The number of the i-th class spacing distances; by analogy, the frequency of each type of interval distance under each saturation in the suspected stain area is obtained; and then, respectively calculating the product of the frequency of each type of spacing distance under each saturation and the texture change parameter of the corresponding suspected stain area, and taking the product as the characteristic value of the corresponding spacing distance under the corresponding saturation.
Further, based on each type of spacing distance at each saturation in the suspected stain areaAnd (3) calculating the correlation characteristic value between the pixel points in the suspected stain area according to the separated characteristic value, wherein the method comprises the following steps: calculating the mean value and standard deviation of the feature values of all the spacing distances under the current saturation according to the feature values of the spacing distances, and calculating a first correlation value between the pixel points corresponding to the current saturation by combining the feature values of each type of spacing distances under the current saturation, the mean value of the feature values and the standard deviation of the feature values, wherein the calculation formula of the first correlation value is as follows:
wherein, w b A first correlation value, P, corresponding to the saturation b j b Frequency of interval distance of j class under saturation b, epsilon b Is the mean value of the characteristic values at the saturation b, σ b Is the standard deviation of the characteristic value under the saturation b; and obtaining a first correlation value corresponding to each saturation in the suspected stain area according to a calculation formula of the first correlation values, adding all the first correlation values, and obtaining a correlation characteristic value between the pixel points in the suspected stain area as an addition result.
And setting a related characteristic value threshold, and when the related characteristic value is greater than the related characteristic value threshold, determining that the suspected stain area is the stain area, otherwise, determining that the suspected stain area is not the stain area.
And in the same way, the related characteristic values of the suspected stain areas in each sub-area are respectively calculated, the stain areas are confirmed according to the related characteristic values, and the printing and dyeing defect detection on the surface of the cloth is completed according to the confirmation result.
In summary, the embodiment of the present invention provides a method for detecting defects in printing and dyeing of cloth based on image processing, which divides a surface image of the cloth into a plurality of sub-regions, confirms a suspected stain area in each sub-region, analyzes a correlation characteristic value between pixel points in the suspected stain area according to a plurality of texture characteristic differences of the suspected stain area and colors of the sub-regions, and determines the stain area according to the correlation characteristic value, so that a stain defect detection result is more accurate, and a detection error of threshold segmentation is reduced.
Based on the same inventive concept as the method, the embodiment of the invention also provides an image processing-based cloth printing defect detection system, which comprises a memory, a processor and a computer program stored in the memory and run on the processor, wherein the processor executes the computer program to realize the steps of any one of the image processing-based cloth printing defect detection methods.
It should be noted that: the sequence of the above embodiments of the present invention is only for description, and does not represent the advantages or disadvantages of the embodiments. And specific embodiments thereof have been described above. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
Claims (7)
1. An image processing-based cloth printing and dyeing defect detection method is characterized by comprising the following steps:
collecting RGB images on the surface of the cloth, dividing the RGB images into a plurality of sub-regions according to equal areas, obtaining the color saturation of each sub-region, and confirming a suspected stain area in each sub-region according to the saturation value of each pixel point in each sub-region;
carrying out edge extraction on the current suspected stain area to obtain an edge contour, and respectively calculating a direction angle difference value between each edge point on the edge contour and a normal texture direction to obtain an overall texture direction difference value of the current suspected stain area; quantifying the direction angle difference value of each edge point to construct an edge histogram of the direction angle difference value, calculating the entropy of the edge histogram to serve as a texture complex index of the current suspected stain area, and calculating a texture uniformity index according to the length of a texture element in the current suspected stain area, wherein the length of the texture element represents the maximum pixel point set formed by continuous pixels of a constant level on a straight line texture; combining the integral texture direction difference value, the texture complex index, the texture uniform index and the corresponding color saturation to obtain a texture change parameter of the current suspected stain area;
respectively calculating the spacing distance between any two pixel points under each saturation in the current suspected stain area to obtain the frequency of each type of spacing distance under each saturation, and taking the product of each frequency and the texture change parameter as the characteristic value of the corresponding spacing distance under the corresponding saturation; calculating a related characteristic value between pixel points in the current suspected stain area by combining the interval distance under each saturation degree and the corresponding characteristic value, and confirming the stain area by the related characteristic value; and confirming the dyeing spot area in each sub-area to finish the cloth printing and dyeing defect detection.
2. The image processing-based cloth printing defect detection method of claim 1, wherein the method for calculating the direction angle difference between each edge point on the edge contour and the normal texture direction comprises the following steps:
establishing a rectangular coordinate system according to the direction of the normal dyeing texture in the sub-region, wherein the origin of the rectangular coordinate system is the boundary junction between the normal pixel point of the sub-region and the pixel point of the suspected stain region, the suspected stain region is divided into an upper part and a lower part by the X axis of the rectangular coordinate system, and the longitudinal coordinate distance of each part is equal;
and respectively acquiring an included angle between each edge point and the X axis of the rectangular coordinate system according to the positions of the edge points and the original point, and referring the included angle as a direction angle difference value between the corresponding edge point and the normal texture direction.
3. The method for detecting the printing and dyeing defects of the cloth based on the image processing as claimed in claim 1, wherein the method for acquiring the integral texture direction difference value comprises the following steps:
and calculating an average direction angle difference value according to the direction angle difference value of each edge point on the edge contour, and taking the average direction angle difference value as the overall texture direction difference value of the suspected stain area.
4. The method for detecting the defects of the printing and dyeing cloth based on the image processing as claimed in claim 1, wherein the method for calculating the texture uniformity index according to the length of the texture element in the current suspected stain area comprises the following steps:
respectively acquiring the primitive length number of the length of the texture primitive corresponding to each gray level according to the lengths of the texture primitives corresponding to different gray levels in the suspected stain area on the basis of the gray level image of the sub-area where the suspected stain area is located, and calculating the total primitive length number according to the primitive length number of the length of the texture primitive corresponding to each gray level;
calculating the length sum of the texture primitive of the current gray level according to the length of the texture primitive of the current gray level and the corresponding length number of the primitive, and accumulating the length sum of the texture primitive of each gray level to obtain the length sum of the whole texture primitive; and calculating the ratio of the total length sum of the texture primitives to the total length of the texture primitives, and taking the ratio as a texture uniformity index.
5. The method for detecting the printing and dyeing defects of the cloth based on the image processing as claimed in claim 1, wherein the calculation formula for obtaining the texture variation parameter of the current suspected stain area by combining the overall texture direction difference value, the texture complexity index, the texture uniformity index and the corresponding color saturation comprises:
wherein gamma is a texture change parameter of the suspected stain area; delta is the difference value of the overall texture direction of the suspected stain area; beta is a texture complex index of a suspected stain area; alpha is the texture uniformity index of the suspected stain area; and S is the color saturation of the sub-area where the suspected stain area is located.
6. The method for detecting the printing and dyeing defects of the cloth based on the image processing as claimed in claim 1, wherein the method for calculating the related characteristic values between the pixel points in the current suspected stain area by combining the separation distances and the corresponding characteristic values under the respective saturation degrees comprises the following steps:
calculating the mean value and standard deviation of the feature values of all the spacing distances under the current saturation according to the feature values of the spacing distances, and calculating a first correlation value between the pixel points corresponding to the current saturation by combining the feature values of each type of spacing distance under the current saturation, the mean value of the feature values and the standard deviation of the feature values;
respectively calculating first correlation values corresponding to each saturation in the suspected stain area, and taking the addition result of all the first correlation values as correlation characteristic values among pixel points in the suspected stain area;
wherein, the calculation formula of the first correlation value is as follows:
wherein, w b A first correlation value, P, corresponding to the saturation b j b Frequency of interval distance of j class under saturation b, epsilon b Is the mean value of the characteristic values at the saturation b, σ b Is the standard deviation of the eigenvalues at saturation b.
7. An image processing based cloth printing defect detection system comprising a memory, a processor and a computer program stored in the memory and run on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1-6 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210555003.6A CN114998227A (en) | 2022-05-20 | 2022-05-20 | Cloth printing and dyeing defect detection method and system based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210555003.6A CN114998227A (en) | 2022-05-20 | 2022-05-20 | Cloth printing and dyeing defect detection method and system based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114998227A true CN114998227A (en) | 2022-09-02 |
Family
ID=83026525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210555003.6A Pending CN114998227A (en) | 2022-05-20 | 2022-05-20 | Cloth printing and dyeing defect detection method and system based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114998227A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115170570A (en) * | 2022-09-07 | 2022-10-11 | 南通睿谷纺织科技有限公司 | Fabric fuzzing and pilling detection method based on gray level run-length matrix |
| CN115237083A (en) * | 2022-09-23 | 2022-10-25 | 南通沐沐兴晨纺织品有限公司 | Textile singeing process control method and system based on computer vision |
| CN115272341A (en) * | 2022-09-29 | 2022-11-01 | 华联机械集团有限公司 | Packaging machine defect product detection method based on machine vision |
| CN116452589A (en) * | 2023-06-16 | 2023-07-18 | 山东伟国板业科技有限公司 | Intelligent detection method for surface defects of artificial board based on image processing |
| CN116580021A (en) * | 2023-07-03 | 2023-08-11 | 湖南益友新材料有限公司 | Environment-friendly concrete carbon reduction product production and quality detection method |
| CN117274248A (en) * | 2023-11-20 | 2023-12-22 | 滨州三元家纺有限公司 | Visual detection method for fabric printing and dyeing flaws and defects |
| CN117557873A (en) * | 2024-01-12 | 2024-02-13 | 四川高速公路建设开发集团有限公司 | Tunnel face crack identification method based on image identification |
| CN118014998A (en) * | 2024-04-09 | 2024-05-10 | 深圳市富安娜艺术家居有限公司 | Bed sheet cloth detection method and system based on machine vision |
-
2022
- 2022-05-20 CN CN202210555003.6A patent/CN114998227A/en active Pending
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115170570A (en) * | 2022-09-07 | 2022-10-11 | 南通睿谷纺织科技有限公司 | Fabric fuzzing and pilling detection method based on gray level run-length matrix |
| CN115237083A (en) * | 2022-09-23 | 2022-10-25 | 南通沐沐兴晨纺织品有限公司 | Textile singeing process control method and system based on computer vision |
| CN115237083B (en) * | 2022-09-23 | 2024-01-12 | 南通沐沐兴晨纺织品有限公司 | Textile singeing process control method and system based on computer vision |
| CN115272341A (en) * | 2022-09-29 | 2022-11-01 | 华联机械集团有限公司 | Packaging machine defect product detection method based on machine vision |
| CN116452589B (en) * | 2023-06-16 | 2023-10-20 | 山东伟国板业科技有限公司 | Intelligent detection method for surface defects of artificial board based on image processing |
| CN116452589A (en) * | 2023-06-16 | 2023-07-18 | 山东伟国板业科技有限公司 | Intelligent detection method for surface defects of artificial board based on image processing |
| CN116580021B (en) * | 2023-07-03 | 2023-09-22 | 湖南益友新材料有限公司 | Environment-friendly concrete carbon reduction product production and quality detection method |
| CN116580021A (en) * | 2023-07-03 | 2023-08-11 | 湖南益友新材料有限公司 | Environment-friendly concrete carbon reduction product production and quality detection method |
| CN117274248A (en) * | 2023-11-20 | 2023-12-22 | 滨州三元家纺有限公司 | Visual detection method for fabric printing and dyeing flaws and defects |
| CN117274248B (en) * | 2023-11-20 | 2024-02-02 | 滨州三元家纺有限公司 | Visual detection method for fabric printing and dyeing flaws and defects |
| CN117557873A (en) * | 2024-01-12 | 2024-02-13 | 四川高速公路建设开发集团有限公司 | Tunnel face crack identification method based on image identification |
| CN117557873B (en) * | 2024-01-12 | 2024-04-05 | 四川高速公路建设开发集团有限公司 | Tunnel face crack identification method based on image identification |
| CN118014998A (en) * | 2024-04-09 | 2024-05-10 | 深圳市富安娜艺术家居有限公司 | Bed sheet cloth detection method and system based on machine vision |
| CN118014998B (en) * | 2024-04-09 | 2024-06-11 | 深圳市富安娜艺术家居有限公司 | Bed sheet cloth detection method and system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114998227A (en) | Cloth printing and dyeing defect detection method and system based on image processing | |
| CN113781402B (en) | Method and device for detecting scratch defects on chip surface and computer equipment | |
| US6674904B1 (en) | Contour tracing and boundary detection for object identification in a digital image | |
| CN108629343B (en) | License plate positioning method and system based on edge detection and improved Harris corner detection | |
| CN116843688B (en) | Visual detection method for quality of textile | |
| US10713780B2 (en) | Color quality assessment based on multispectral imaging | |
| CN111161222B (en) | Printing roller defect detection method based on visual saliency | |
| CN115330795B (en) | Cloth burr defect detection method | |
| CN103866551B (en) | Based on the fabric skew quick detecting method of machine vision | |
| CN114862855B (en) | Textile defect detection method and system based on template matching | |
| JP4946878B2 (en) | Image identification apparatus and program | |
| CN115272304B (en) | Cloth defect detection method and system based on image processing | |
| CN112200790B (en) | Cloth defect detection method, device and medium | |
| CN114862836A (en) | Intelligent textile fabric printing and dyeing method and system based on data recognition graph | |
| CN104616298B (en) | Method for detecting moving target of ink-jet printing fabric based on mixed-state Gauss MRF (Markov Random Field) model | |
| CN117237354B (en) | Visual detection method for defects of textile clothes | |
| CN117152158B (en) | Textile defect detection method and system based on artificial intelligence | |
| JP5973804B2 (en) | Image processing apparatus and control method thereof | |
| CN116894840B (en) | Spinning proofing machine product quality detection method and system | |
| Lin et al. | License plate location method based on edge detection and mathematical morphology | |
| CN112669300A (en) | Defect detection method and device, computer equipment and storage medium | |
| CN115471504B (en) | Automatic thread end identification method based on textile fabric | |
| WO2021260765A1 (en) | Dimension measuring device, semiconductor manufacturing device, and semiconductor device manufacturing system | |
| Bergevin et al. | Detection and characterization of junctions in a 2D image | |
| CN114255253A (en) | Edge detection method, edge detection device, and computer-readable storage medium |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220902 |