CN117132593B - Cloth roughness detection method for resisting periodic texture influence - Google Patents
Cloth roughness detection method for resisting periodic texture influence Download PDFInfo
- Publication number
- CN117132593B CN117132593B CN202311385057.3A CN202311385057A CN117132593B CN 117132593 B CN117132593 B CN 117132593B CN 202311385057 A CN202311385057 A CN 202311385057A CN 117132593 B CN117132593 B CN 117132593B
- Authority
- CN
- China
- Prior art keywords
- cloth
- periodic
- vertical
- target
- period
- 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
- 239000004744 fabric Substances 0.000 title claims abstract description 159
- 230000000737 periodic effect Effects 0.000 title claims abstract description 68
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 230000003746 surface roughness Effects 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims description 22
- 230000000694 effects Effects 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 11
- 238000012545 processing Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007689 inspection Methods 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
- 239000004753 textile Substances 0.000 description 1
- 230000000007 visual effect Effects 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
-
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a cloth roughness detection method for resisting periodic texture influence, which relates to the technical field of image processing and comprises the steps of obtaining a target gray level image; acquiring a horizontal periodic graph of a target gray level image; acquiring a vertical periodic graph of a target gray level image; determining a horizontal period ratio according to the ratio of two adjacent periods in the horizontal period graph; determining a vertical period ratio according to the ratio of two adjacent periods in the vertical period graph; determining that cloth is affected by periodic textures according to the horizontal periodic ratio and the vertical periodic ratio; determining a dividing size of the target gray image according to the target horizontal period and the target vertical period, and dividing the target gray image into a plurality of sub-images according to the dividing size; acquiring the surface roughness of cloth; the invention solves the technical problems that in the related art, the detection precision is low and the whole roughness of the cloth cannot be accurately reflected when the defect detection is carried out on the cloth.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a cloth roughness detection method for resisting periodic texture influence.
Background
Cloth is an indispensable article in people's daily life, and its quality directly influences people's life experience. The pursuit of people for high-quality life makes the practicality and durability of cloth in the traditional sense not meet the needs of people, and the fashion and the aesthetic property are more focused and toughed by people. With the rapid development of textile industry, the yield of cloth becomes larger and larger, and the cloth defect detection is more challenging, and the traditional manual cloth inspection technology is more and more difficult to meet the industrial production requirement. The development of computing technology, in particular artificial intelligence technology, provides new and more reliable technical support for cloth defect detection.
In the production and processing process of the cloth, the roughness is a main evaluation parameter of the surface microscopic morphology of the cloth, and for the fine change of the surface microscopic morphology of the cloth, the traditional detection method is manual contact detection, so that the defects of low detection efficiency, poor accuracy and high manual labor intensity exist, and the cloth is damaged; at present, a cloth detection method based on machine vision gradually becomes a research hot spot, such as cloth defect detection based on fine vision, an image can be processed by using a high-precision line scanning camera and a visual detection system, the defect of the cloth can be detected, when the defect degree of the cloth is large, or when serious warp and weft breakage occurs in the production process of the cloth, the detection by using the prior art can have large errors, and the whole roughness degree of the cloth cannot be judged through a single defect area.
Disclosure of Invention
The invention aims to provide a cloth roughness detection method for resisting periodic texture influence, which aims to solve the technical problems that the detection precision is low and the whole roughness of cloth cannot be accurately reflected when the defect detection is carried out on the cloth in the related technology; in view of this, the present invention is achieved by the following technical means.
A cloth roughness detection method for resisting periodic texture influence comprises the following steps:
acquiring a gray image of cloth;
replacing the gray value of each pixel point by using the average value of the gray values of the pixel points in the neighborhood of each pixel point in the gray image to obtain a target gray image;
acquiring an average gray value of each row of pixel points and an average gray value of each column of pixel points in the target gray image;
acquiring a horizontal periodic graph of the target gray image according to the average gray value of each row of pixel points in the target gray image; acquiring a vertical periodic graph of the target gray image according to the average gray value of each column of pixel points in the target gray image;
determining a horizontal period ratio according to the ratio of two adjacent periods in the horizontal period graph; determining a vertical period ratio according to the ratio of two adjacent periods in the vertical period graph; determining cloth affected by periodic textures according to the horizontal periodic ratio and the vertical periodic ratio;
respectively acquiring a target horizontal period and a target vertical period according to the horizontal period curve graph and the vertical period curve graph of the cloth affected by the periodic texture; determining a dividing size of the target gray scale image according to the target horizontal period and the target vertical period, and dividing the target gray scale image into a plurality of sub-images according to the dividing size;
and acquiring the surface roughness of the cloth according to the gray values of the pixel points in the plurality of sub-images, and judging whether the cloth influenced by the periodic texture is qualified or not according to the surface roughness of the cloth.
Further, in the process of determining that the cloth is affected by the periodic texture according to the horizontal period ratio and the vertical period ratio, a first threshold value and a second threshold value are set, and whether the cloth is affected by the periodic texture or not is determined according to the horizontal period ratio and the vertical period ratio, and the first threshold value and the second threshold value.
Further, in the process of determining whether the cloth is affected by the periodic texture according to the horizontal period ratio and the vertical period ratio and the first threshold value and the second threshold value, when the horizontal period ratio and the vertical period ratio simultaneously meet the conditions that the horizontal period ratio and the vertical period ratio are larger than the first threshold value and smaller than the second threshold value, the cloth is affected by the periodic texture.
Further, acquiring a horizontal period of the target gray image according to the horizontal period curve graph, and acquiring a horizontal period ratio according to the horizontal period curve graph and a target horizontal period of the target gray image according to the horizontal period ratio in the process of acquiring a vertical period of the target gray image according to the vertical period curve graph; and acquiring a vertical period ratio according to the vertical period curve graph, and acquiring a target vertical period of the target gray level image according to the vertical period ratio.
Further, the division size is obtained by multiplying the target horizontal period by the target vertical period.
Further, the process of obtaining the surface roughness of the cloth according to the gray values of the pixel points in the plurality of sub-images is as follows:
obtaining the sum of pixel point gray values in each sub-image;
acquiring an average value of the sum of the gray values of the pixel points in all the sub-images;
and obtaining the surface roughness of the cloth according to the sum of the pixel gray values in each sub-image and the average value of the sum of the pixel gray values in all the sub-images.
Further, the surface roughness of the cloth is determined by the following formula:
wherein D is the surface roughness of cloth; n is the number of sub-images; ii is the sum of pixel gray values of the ith sub-image; i is the average value of the sum of pixel gray values of all the sub-images.
Further, in the process of judging whether the cloth is qualified according to the surface roughness of the cloth, setting a surface roughness threshold value, and when the surface roughness of the cloth is smaller than or equal to the surface roughness threshold value, judging that the cloth is qualified; when the surface roughness is greater than the threshold value of the surface roughness, the cloth is a rough cloth.
Further, the threshold value of the surface roughness is 15, and when the surface roughness of the cloth is less than or equal to 15, the cloth is qualified cloth; when the surface roughness is greater than 15, the cloth is rough cloth.
Further, the target horizontal period is the first period in a horizontal period graph; the target vertical period is the first period in the vertical period graph.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a cloth roughness detection method for resisting periodic texture influence, which comprises the following steps: acquiring a gray image of cloth; acquiring an average value of gray values of a plurality of pixel points in a neighborhood according to the gray values of the plurality of pixel points in the neighborhood of any pixel point in the gray image; acquiring a target gray value of the pixel point according to the gray value and the average value of the pixel point; in the gray image, the target gray value of the pixel point is the average value of the gray values of the pixel points in the neighborhood of the pixel point, the target gray image can be obtained according to the target gray value, and the enhancement of the gray image can be realized by replacing the target gray value of the pixel point in the gray image; acquiring an average gray value of each row of pixel points and an average gray value of each column of pixel points in a target gray image; acquiring a horizontal periodic graph of the target gray image according to the average gray value of each row of pixel points in the target gray image, and acquiring a vertical periodic graph of the target gray image according to the average gray value of each column of pixel points in the target gray image; in the horizontal cycle graph and the vertical cycle graph, since the texture characteristic horizontal cycle graph and the vertical cycle graph of the cloth are periodically distributed, the horizontal cycle and the vertical cycle can be determined through the horizontal cycle graph and the vertical cycle graph; determining the dividing size of the cloth through the horizontal period and the vertical period, dividing the target gray level image into a plurality of sub-images with the same size according to the dividing size, and obtaining the surface roughness of the cloth according to the gray level values of the pixel points in the plurality of sub-images; the surface roughness of the cloth is obtained to judge whether the cloth is rough cloth or not; by setting a threshold value, whether the cloth is rough cloth or not can be determined according to the threshold value and the surface roughness of the cloth; the invention solves the technical problems that in the related art, the detection precision is low and the whole roughness of the cloth cannot be accurately reflected when the defect detection is carried out on the cloth.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings that are necessary for the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of a cloth roughness detecting method according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment provides a cloth roughness detection method for resisting periodic texture influence, as shown in fig. 1, the detection method comprises the following steps:
s101, acquiring a cloth area image, and carrying out gray processing and edge detection on the cloth area image to acquire a gray level image of cloth; in the embodiment, edge detection is carried out on the cloth area image by using a Canny edge detection algorithm, so that a gray level image of the cloth is obtained;
acquiring an average value of gray values of a plurality of pixel points in a neighborhood according to the gray values of the plurality of pixel points in the neighborhood of any pixel point in the gray image; obtaining a difference value between a gray value of a pixel point and an average value to obtain a target gray value of the pixel point, and sequentially obtaining the target gray value of each pixel point in a gray image; assigning a target gray value of each pixel point to each corresponding pixel point in the gray image to obtain a target gray image;
s102, in a target gray level graph, acquiring a horizontal period curve graph according to an average value of gray level values of all pixel points in the vertical direction corresponding to the pixel points in the horizontal direction, and acquiring a horizontal period ratio according to the horizontal period curve graph; the horizontal period ratio is obtained by the following steps:
sequentially marking the serial numbers of one of the horizontal pixel points of the target gray level image, wherein the marking mode can be left to right or right to left, and in the embodiment, the serial numbers of one of the horizontal pixel points of the target gray level image are selected to be marked in a left to right mode;
taking the serial number of each pixel point in the horizontal direction as an abscissa, taking the average value of gray values of all pixel points in the vertical direction corresponding to the serial number as an ordinate, drawing a graph, wherein the graph is a horizontal periodic graph, and a plurality of peak points are arranged in the horizontal periodic graph; the horizontal period ratio is expressed by the following formula:
wherein T1 is a horizontal period ratio; n is the number of pixel points in the horizontal direction;an abscissa value of the i-th peak in the horizontal direction; />An abscissa value of the i+j-th peak in the horizontal direction; />Is horizontal direction->The abscissa value of each peak; />Is constant and->Is an integer less than n;
it should be noted that, the above formula is to determine the horizontal period ratio by the sum of the ratios of two adjacent periods in the horizontal period graph; constant (constant)Take values from 1, every time take one +.>Will result in a corresponding horizontal period ratio, stop constant +.>And determining the value of the horizontal period ratio T1;
in the target gray level diagram, a vertical periodic graph is obtained according to the average value of gray level values of all pixel points in the horizontal direction corresponding to the pixel points in the vertical direction, and a vertical periodic ratio is obtained according to the vertical periodic graph; the vertical period ratio is obtained by the following steps:
sequentially marking the sequence number of one of the vertical pixel points of the target gray level image in a mode from bottom to top or from top to bottom, and in the embodiment, selecting the mode from bottom to top to mark the sequence number of one of the vertical pixel points of the target gray level image;
taking the serial number of each pixel point in the vertical direction as an abscissa, taking the average value of gray values of all pixel points in the horizontal direction corresponding to the serial number as an ordinate, drawing a graph, wherein the graph is a vertical periodic graph, and a plurality of peak points are arranged in the vertical periodic graph; the vertical period ratio is expressed by the following formula:
wherein T2 is a vertical period ratio; m is the number of pixels in the vertical direction;vertical direction +>The abscissa value of each peak; />Is vertical direction->The abscissa value of each peak; />Is vertical direction->The abscissa value of each peak; />Is constant and->Is an integer less than m;
it should be noted that, the above formula is to determine the vertical period ratio by the sum of the ratios of two adjacent periods in the vertical period graph; constant (constant)Take values from 1, every time take one +.>Will result in a corresponding vertical period ratio, stop constant +.>And determining the value of the vertical period ratio T2;
in this embodiment, whether the cloth is affected by the periodic texture can be determined through this step, and when neither the horizontal periodic ratio nor the vertical periodic ratio is in the range from the minimum texture periodic ratio to the maximum texture periodic ratio, the cloth can be directly classified as a coarse cloth, and the coarse cloth can be regarded as a defective cloth; when the horizontal period ratio is larger than the minimum texture period ratio and smaller than the maximum texture period ratio, and the vertical period ratio is larger than the minimum texture period ratio and smaller than the maximum texture period ratio, the cloth is affected by the periodic texture, and further analysis of the surface roughness of the cloth is required; it should be noted that, in this embodiment, the minimum texture period ratio is selected to be 0.95, the maximum texture period ratio is selected to be 1.05, and the implementer may set other values as the minimum texture period ratio or the maximum texture period ratio according to the implementation conditions; the horizontal and vertical periodic patterns obtained by this embodiment are unique, that is, only one horizontal and one vertical periodic pattern can be obtained by this embodiment;
in this embodiment, the horizontal period for obtaining the target gray scale is based on the horizontal period ratioWherein->An abscissa value of the i-th peak in the horizontal direction; />An abscissa value of the i+j-th peak in the horizontal direction; according to the vertical period ratio, the vertical period of the target gray level map is +.>Wherein->Is vertical direction->The abscissa value of each peak; />Is vertical direction->The abscissa value of each peak; the horizontal period ratio obtained due to the present embodiment +.>And vertical period ratio->Is a value close to 1, so the first period in the horizontal period graph can be determined as the target horizontal period +.>Determining the first period in the vertical period graph as the target vertical period +.>；
S103, dividing the target gray scale image into a plurality of sub-images by a horizontal period and a vertical period, wherein the length of each sub-image is the target horizontal periodWidth is the target vertical period +.>The method comprises the steps of carrying out a first treatment on the surface of the I.e. the size of each sub-picture is +.>；
Obtaining the sum of pixel gray values of the single sub-image; obtaining the surface roughness of the cloth according to the sum of the pixel gray values of the single sub-image and the average value of the sum of the pixel gray values of all the sub-images; the surface roughness of the cloth is obtained by the following formula:
wherein D is the surface roughness of cloth; n is the number of sub-images; ii is the sum of pixel gray values of the ith sub-image; i is the average value of the sum of the gray values of the pixel points of all the sub-images;
when the surface roughness of cloth is the same as that of the clothThe smaller the value of (c) the closer the roughness of each piece of cloth is to the roughness of the surface of a large piece of cloth, thereby indicating that the excessive difference in gray scale is mainly due to the periodic texture of the surface of the piece of cloth, the smoother the surface of the piece of cloth; when the surface roughness of cloth is->When the value of (2) is larger, the larger the gray level difference value is mainly caused by the fact that the cloth surface is too rough, but not the influence caused by periodic textures, and the rough the cloth surface is;
s104, defining a threshold value of the surface roughness of the cloth, and judging whether the cloth is qualified or not through comparison of the threshold value of the surface roughness and the surface roughness of the cloth; when the surface roughness of the cloth is smaller than or equal to the threshold value of the surface roughness, the cloth is qualified cloth; when the surface roughness of the cloth is larger than the threshold value of the surface roughness, the cloth is rough cloth; thus finishing the detection of the roughness of the cloth;
in this embodiment, the threshold value of the surface roughness of the cloth is set to be 15 according to specific implementation conditions, and when the surface roughness of the cloth is less than or equal to 15, the cloth is qualified; when the surface roughness of the cloth is greater than 15, the cloth is rough cloth; thus, and the detection of the cloth roughness is completed, the practitioner can set other values as thresholds of the cloth surface roughness according to specific implementation conditions.
In summary, the present embodiment provides a method for detecting roughness of cloth against periodic texture effects, which is a method for detecting roughness of non-contact cloth, and acquires a gray image of the cloth; acquiring an average value of gray values of a plurality of pixel points in a neighborhood according to the gray values of the plurality of pixel points in the neighborhood of any pixel point in the gray image; acquiring a target gray value of the pixel point according to the gray value and the average value of the pixel point; in the gray image, the target gray value of the pixel point is the average value of the gray values of the pixel points in the neighborhood of the pixel point, the target gray image can be obtained according to the target gray value, and the enhancement of the gray image can be realized by replacing the target gray value of the pixel point in the gray image; acquiring an average gray value of each row of pixel points and an average gray value of each column of pixel points in a target gray image; acquiring a horizontal periodic graph of the target gray image according to the average gray value of each row of pixel points in the target gray image, and acquiring a vertical periodic graph of the target gray image according to the average gray value of each column of pixel points in the target gray image; in the horizontal cycle graph and the vertical cycle graph, since the texture characteristic horizontal cycle graph and the vertical cycle graph of the cloth are periodically distributed, the horizontal cycle and the vertical cycle can be determined through the horizontal cycle graph and the vertical cycle graph; determining the dividing size of the cloth through the horizontal period and the vertical period, dividing the target gray level image into a plurality of sub-images with the same size according to the dividing size, and obtaining the surface roughness of the cloth according to the gray level values of the pixel points in the plurality of sub-images; the surface roughness of the cloth is obtained to judge whether the cloth is rough cloth or not; by setting a threshold value, whether the cloth is rough cloth or not can be determined according to the threshold value and the surface roughness of the cloth; the invention solves the technical problems that in the related art, the detection precision is low and the whole roughness of the cloth cannot be accurately reflected when the defect detection is carried out on the cloth.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather to enable any modification, equivalent replacement and improvement made within the spirit and principles of the invention.
Claims (10)
1. A cloth roughness detection method for resisting periodic texture influence is characterized by comprising the following steps:
acquiring a gray image of cloth;
replacing the gray value of each pixel point by using the average value of the gray values of the pixel points in the neighborhood of each pixel point in the gray image to obtain a target gray image;
acquiring an average gray value of each row of pixel points and an average gray value of each column of pixel points in the target gray image;
acquiring a horizontal periodic graph of the target gray image according to the average gray value of each row of pixel points in the target gray image; acquiring a vertical periodic graph of the target gray image according to the average gray value of each column of pixel points in the target gray image;
determining a horizontal period ratio according to the ratio of two adjacent periods in the horizontal period graph; determining a vertical period ratio according to the ratio of two adjacent periods in the vertical period graph; determining cloth affected by periodic textures according to the horizontal periodic ratio and the vertical periodic ratio;
respectively acquiring a target horizontal period and a target vertical period according to the horizontal period curve graph and the vertical period curve graph of the cloth affected by the periodic texture; determining a dividing size of the target gray scale image according to the target horizontal period and the target vertical period, and dividing the target gray scale image into a plurality of sub-images according to the dividing size;
acquiring the surface roughness of the cloth according to the gray values of the pixel points in the plurality of sub-images, and judging whether the cloth influenced by the periodic texture is qualified or not according to the surface roughness of the cloth;
the horizontal period ratio is expressed by the following formula:
wherein T1 is a horizontal period ratio; n is the number of pixel points in the horizontal direction;an abscissa value of the i-th peak in the horizontal direction;an abscissa value of the i+j-th peak in the horizontal direction; />Is horizontal direction->The abscissa value of each peak;is constant and->Is an integer less than n;
the vertical period ratio is expressed by the following formula:
wherein T2 is a vertical period ratio; m is the number of pixels in the vertical direction;vertical direction +>The abscissa value of each peak;is vertical direction->The abscissa value of each peak; />Is vertical direction->The abscissa value of each peak; />Is constant and->Is an integer less than m.
2. The method for detecting roughness of cloth against periodic texture influence according to claim 1, wherein in the process of determining that the cloth is influenced by periodic texture according to the horizontal period ratio and the vertical period ratio, a first threshold value and a second threshold value are set, and whether the cloth is influenced by periodic texture is determined according to the horizontal period ratio and the vertical period ratio, and the first threshold value and the second threshold value.
3. The cloth roughness detecting method of claim 2, wherein in determining whether the cloth is affected by the periodic texture according to the horizontal periodic ratio and the vertical periodic ratio, and the first threshold and the second threshold, when the horizontal periodic ratio and the vertical periodic ratio simultaneously satisfy more than the first threshold and less than the second threshold, the cloth is affected by the periodic texture.
4. The cloth roughness detecting method of claim 1, wherein in the process of obtaining the horizontal period of the target gray image according to the horizontal period graph and the vertical period of the target gray image according to the vertical period graph, further comprising obtaining a horizontal period ratio according to the horizontal period graph and obtaining the target horizontal period of the target gray image according to the horizontal period ratio; and acquiring a vertical period ratio according to the vertical period curve graph, and acquiring a target vertical period of the target gray level image according to the vertical period ratio.
5. The cloth roughness detecting method resistant to periodical texture influence as claimed in claim 1, wherein the dividing size is obtained by multiplying the target horizontal period by the target vertical period.
6. The method for detecting roughness of cloth against periodic texture influence according to claim 1, wherein the process of obtaining the surface roughness of the cloth according to the gray values of the pixel points in the plurality of sub-images is as follows:
obtaining the sum of pixel point gray values in each sub-image;
acquiring an average value of the sum of the gray values of the pixel points in all the sub-images;
and obtaining the surface roughness of the cloth according to the sum of the pixel gray values in each sub-image and the average value of the sum of the pixel gray values in all the sub-images.
7. The method for detecting roughness of cloth against periodic texture influence according to claim 6, wherein the surface roughness of the cloth is determined by the following formula:
wherein D is the surface roughness of cloth; n is the number of sub-images; ii is the sum of pixel gray values of the ith sub-image; i is the average value of the sum of pixel gray values of all the sub-images.
8. The cloth roughness detection method for resisting periodic texture influence according to claim 1, wherein in the process of judging whether the cloth is qualified according to the surface roughness of the cloth, a threshold value of the surface roughness is set, and when the surface roughness of the cloth is smaller than or equal to the threshold value of the surface roughness, the cloth is qualified; when the surface roughness is greater than the threshold value of the surface roughness, the cloth is a rough cloth.
9. The method for detecting roughness of cloth against periodic texture influence according to claim 8, wherein the threshold value of the surface roughness is 15, and when the surface roughness of the cloth is less than or equal to 15, the cloth is a qualified cloth; when the surface roughness is greater than 15, the cloth is rough cloth.
10. The method for detecting cloth roughness resistant to periodic texture effects of claim 1, wherein the target horizontal period is the first period in a horizontal period graph; the target vertical period is the first period in the vertical period graph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311385057.3A CN117132593B (en) | 2023-10-25 | 2023-10-25 | Cloth roughness detection method for resisting periodic texture influence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311385057.3A CN117132593B (en) | 2023-10-25 | 2023-10-25 | Cloth roughness detection method for resisting periodic texture influence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117132593A CN117132593A (en) | 2023-11-28 |
| CN117132593B true CN117132593B (en) | 2024-03-26 |
Family
ID=88860362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311385057.3A Active CN117132593B (en) | 2023-10-25 | 2023-10-25 | Cloth roughness detection method for resisting periodic texture influence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117132593B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976441A (en) * | 2010-11-09 | 2011-02-16 | 东华大学 | Method for extracting Sobel operator filtering profile for representing fabric texture and fractal detail mixed characteristic vector |
| CN102331425A (en) * | 2011-06-28 | 2012-01-25 | 合肥工业大学 | Textile defect detection method based on defect enhancement |
| CN103149147A (en) * | 2011-12-06 | 2013-06-12 | 重庆国际复合材料有限公司 | Detecting device and detecting method for glass fiber fabric deformation resistance |
| CN103234969A (en) * | 2013-04-12 | 2013-08-07 | 江苏大学 | Method for measuring fabric weft density based on machine vision |
| CN103366145A (en) * | 2013-07-01 | 2013-10-23 | 北京印刷学院 | Anti-error detection method and system based on magnetic coding and identification technology for sample book production |
| CN107870172A (en) * | 2017-07-06 | 2018-04-03 | 黎明职业大学 | A kind of Fabric Defects Inspection detection method based on image procossing |
| CN113936001A (en) * | 2021-12-17 | 2022-01-14 | 杭州游画丝界文化艺术发展有限公司 | Textile surface flaw detection method based on image processing technology |
| CN114529549A (en) * | 2022-04-25 | 2022-05-24 | 南通东德纺织科技有限公司 | Cloth defect labeling method and system based on machine vision |
| CN114723705A (en) * | 2022-03-31 | 2022-07-08 | 海门市恒创织带有限公司 | Cloth flaw detection method based on image processing |
| CN115131348A (en) * | 2022-08-30 | 2022-09-30 | 海门喜满庭纺织品有限公司 | Method and system for detecting textile surface defects |
| CN115330763A (en) * | 2022-10-12 | 2022-11-11 | 江苏鑫缘医疗科技有限公司 | Medical gauze defect detection method |
| CN116630309A (en) * | 2023-07-21 | 2023-08-22 | 微山县天阔纺织有限公司 | Cloth weft-break flaw detection method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5776334B2 (en) * | 2011-05-31 | 2015-09-09 | セイコーエプソン株式会社 | Stress detection element, sensor module, electronic device, and gripping device |
| KR102708859B1 (en) * | 2020-11-09 | 2024-09-24 | 엘지디스플레이 주식회사 | Display device and image processing method thereof |
-
2023
- 2023-10-25 CN CN202311385057.3A patent/CN117132593B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101976441A (en) * | 2010-11-09 | 2011-02-16 | 东华大学 | Method for extracting Sobel operator filtering profile for representing fabric texture and fractal detail mixed characteristic vector |
| CN102331425A (en) * | 2011-06-28 | 2012-01-25 | 合肥工业大学 | Textile defect detection method based on defect enhancement |
| CN103149147A (en) * | 2011-12-06 | 2013-06-12 | 重庆国际复合材料有限公司 | Detecting device and detecting method for glass fiber fabric deformation resistance |
| CN103234969A (en) * | 2013-04-12 | 2013-08-07 | 江苏大学 | Method for measuring fabric weft density based on machine vision |
| CN103366145A (en) * | 2013-07-01 | 2013-10-23 | 北京印刷学院 | Anti-error detection method and system based on magnetic coding and identification technology for sample book production |
| CN107870172A (en) * | 2017-07-06 | 2018-04-03 | 黎明职业大学 | A kind of Fabric Defects Inspection detection method based on image procossing |
| CN113936001A (en) * | 2021-12-17 | 2022-01-14 | 杭州游画丝界文化艺术发展有限公司 | Textile surface flaw detection method based on image processing technology |
| CN114723705A (en) * | 2022-03-31 | 2022-07-08 | 海门市恒创织带有限公司 | Cloth flaw detection method based on image processing |
| CN114529549A (en) * | 2022-04-25 | 2022-05-24 | 南通东德纺织科技有限公司 | Cloth defect labeling method and system based on machine vision |
| CN115131348A (en) * | 2022-08-30 | 2022-09-30 | 海门喜满庭纺织品有限公司 | Method and system for detecting textile surface defects |
| CN115330763A (en) * | 2022-10-12 | 2022-11-11 | 江苏鑫缘医疗科技有限公司 | Medical gauze defect detection method |
| CN116630309A (en) * | 2023-07-21 | 2023-08-22 | 微山县天阔纺织有限公司 | Cloth weft-break flaw detection method |
Non-Patent Citations (1)
| Title |
|---|
| 赵大兴 ; 朱锦雷 ; 李九灵 ; 颜云辉 ; .基于机器视觉的织物检测方法的研究.计算机工程与设计.2008,(第01期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117132593A (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101526484B (en) | Bearing defect detecting technique based on embedded-type machine vision | |
| CN116630309B (en) | Cloth weft-break flaw detection method | |
| CN116309671B (en) | Geosynthetic fabric quality detection system | |
| CN109409290B (en) | Thermometer verification reading automatic identification system and method | |
| CN109934839A (en) | A kind of workpiece inspection method of view-based access control model | |
| CN115439481A (en) | Deaerator welding quality detection method based on image processing | |
| CN115049671A (en) | Cloth surface defect detection method and system based on computer vision | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN115861310B (en) | Method for detecting textile defects on surface of bed sheet | |
| CN108921819A (en) | A kind of cloth examination device and method based on machine vision | |
| CN116977358A (en) | Visual auxiliary detection method for corrugated paper production quality | |
| CN115100206A (en) | Printing defect identification method for textile with periodic pattern | |
| CN115277984B (en) | Method for adjusting exposure time of adaptive camera in glass size detection | |
| CN115294097A (en) | Textile surface defect detection method based on machine vision | |
| CN113781446A (en) | Method and device for detecting greasy dirt on glass fiber surface, storage medium and electronic equipment | |
| CN114693659B (en) | Copper pipe surface cleaning effect evaluation method and system based on image processing | |
| CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
| CN110458809B (en) | Yarn evenness detection method based on sub-pixel edge detection | |
| CN117132593B (en) | Cloth roughness detection method for resisting periodic texture influence | |
| CN108805854B (en) | Method for rapidly counting tablets and detecting completeness of tablets in complex environment | |
| CN106546197A (en) | Based on the self-alignment polished surface detection method of level and its system | |
| CN109461155B (en) | Raw silk quality detection method | |
| CN108416790A (en) | A kind of detection method for workpiece breakage rate | |
| CN105606623A (en) | Linear array camera based steel plate surface defect detection system | |
| CN114693652B (en) | Fabric Defect Detection Method Based on Gaussian Mixture Model |
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 |