CN117830299B - Non-woven fabric surface defect detection method and system - Google Patents
Non-woven fabric surface defect detection method and system Download PDFInfo
- Publication number
- CN117830299B CN117830299B CN202410238594.3A CN202410238594A CN117830299B CN 117830299 B CN117830299 B CN 117830299B CN 202410238594 A CN202410238594 A CN 202410238594A CN 117830299 B CN117830299 B CN 117830299B
- Authority
- CN
- China
- Prior art keywords
- concave structure
- center
- point
- area
- suspected
- 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
- 239000004745 nonwoven fabric Substances 0.000 title claims abstract description 107
- 230000007547 defect Effects 0.000 title claims abstract description 25
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 230000000737 periodic effect Effects 0.000 claims abstract description 58
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000009826 distribution Methods 0.000 claims description 50
- 238000000034 method Methods 0.000 claims description 37
- 238000004458 analytical method Methods 0.000 claims description 27
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000000835 fiber Substances 0.000 description 3
- 238000009941 weaving Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009954 braiding Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 239000002699 waste material Substances 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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- 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
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a non-woven fabric surface defect detection method and system, comprising the following steps: acquiring a non-woven fabric surface image; obtaining a temporary concave structure area formed by the alternative pixel points according to the non-woven fabric surface image; calculating the possibility that each candidate pixel point is the center of the concave structure; obtaining a suspected concave structure center point according to the possibility that each candidate pixel point is the concave structure center; calculating the region merging necessity of the center of each suspected concave structure; obtaining all complete concave structure areas and accurate center points of each complete concave structure area according to the area merging necessity; obtaining a periodic unit window according to the accurate center point of each complete concave structure area; and detecting a stain area in the non-woven fabric surface image according to the periodic unit window. Thus, accurate detection of the stain area is realized by accurately acquiring the periodic unit window.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a non-woven fabric surface defect detection method and system.
Background
A nonwoven fabric is a fibrous product not produced by weaving or braiding, but a textile product directly formed from fibers or fiber assemblies by mechanical, chemical or thermal action of the fibers, and because the manufacturing process of the nonwoven fabric is relatively simple, conventional weaving processes such as spinning and weaving are generally not required; meanwhile, the waste generated in the production and treatment processes of the non-woven fabric has small influence on the environment, meets the requirement of environmental protection sustainable development, and is widely applied. In the process of manufacturing the non-woven fabric, dust, particles, mold and other pollutants exist in the factory environment, and the pollutants may drift onto the non-woven fabric in the manufacturing process, so that stains appear. The stains on the non-woven fabric not only can influence the appearance effect of the non-woven fabric, but also can influence the service performance of the non-woven fabric. Therefore, detection of stain defects in nonwoven fabrics is required.
When the image information of the non-woven fabric is utilized for stain detection, as the non-woven fabric has a concave-convex structure, the gray value at the concave structure of the non-woven fabric is smaller, the gray value at the convex structure is larger, and the gray value span of the non-woven fabric is larger. Therefore, since the gray value interval of the stained area of the nonwoven fabric intersects with the gray value interval of the nonwoven fabric itself, it is difficult to distinguish the stained area from other areas on the nonwoven fabric by using one threshold value. Meanwhile, the concave-convex structure information of the non-woven fabric can cause the non-woven fabric to have edge information. The edge information of the non-woven fabric itself may interfere with the recognition of the stain edge. Thus, it is difficult to detect the stained area by means of edge detection.
Because the concave-convex structure information on the non-woven fabric has a certain periodic rule, the texture information generated by the concave-convex structure of the non-woven fabric has a certain periodic rule. When stains appear, the periodic rule of the texture information of the concave-convex structure is broken, so that the stain information can be detected according to the periodic rule of the concave-convex structure of the non-woven fabric. The key of realizing the stain detection by using the periodic rule of the texture information of the concave-convex structure is how to obtain the periodic unit of the texture information of the non-woven fabric concave-convex structure.
Disclosure of Invention
The invention provides a non-woven fabric surface defect detection method and a non-woven fabric surface defect detection system, which are used for solving the existing problems: how to realize accurate stain detection by accurately dividing the periodic unit.
The invention discloses a non-woven fabric surface defect detection method and a non-woven fabric surface defect detection system, which adopt the following technical scheme:
an embodiment of the present invention provides a method for detecting a surface defect of a nonwoven fabric, including the steps of:
acquiring a non-woven fabric surface image;
Obtaining a temporary concave structure area formed by the alternative pixel points according to the non-woven fabric surface image; according to the size of the temporary concave structure area to which each candidate pixel point belongs, the distance between each candidate pixel point and the center point of the nearest other temporary concave structure area obtains the transverse distribution possibility and the longitudinal distribution possibility of each candidate pixel point serving as the center of the concave structure; obtaining the possibility that each candidate pixel point is the center of the concave structure according to the transverse distribution possibility and the longitudinal distribution possibility that each candidate pixel point is the center of the concave structure; obtaining a suspected concave structure center point according to the possibility that each candidate pixel point is the concave structure center;
According to the area of the temporary concave structure area to which each suspected concave structure center point belongs, the distance between each suspected concave structure center point and the center point of other temporary concave structure areas, and the possibility that each suspected concave structure center point is the concave structure center, the area merging necessity of each suspected concave structure center is obtained; obtaining a to-be-merged concave structure center point according to the region merging necessity of each suspected concave structure center, and merging the temporary concave structure regions to which the to-be-merged concave structure center point belongs to obtain a first complete concave structure region; obtaining all complete concave structure areas and accurate center points of each complete concave structure area according to the area merging necessity of the center of each suspected concave structure and the first complete concave structure area; obtaining a periodic unit window according to the accurate center point of each complete concave structure area;
And detecting a stain area in the non-woven fabric surface image according to the periodic unit window.
Preferably, the method for obtaining the candidate pixel points and the temporary concave structure area formed by the candidate pixel points according to the non-woven fabric surface image includes the following specific steps:
Acquiring the median of the gray values of all pixels in the non-woven fabric surface image, taking the median of the gray values of all pixels in the non-woven fabric surface image as a structural threshold value, and marking the pixels smaller than the structural threshold value in the non-woven fabric surface image as candidate pixel points;
and (5) marking the communication area formed by the candidate pixel points as a temporary concave structure area.
Preferably, the obtaining the lateral distribution possibility and the longitudinal distribution possibility of each candidate pixel point as the center of the concave structure according to the size of the temporary concave structure area to which each candidate pixel point belongs and the distance between each candidate pixel point and the center point of the nearest other temporary concave structure area includes the following specific methods:
taking each candidate pixel point as a center, acquiring N continuous pixel points in the same row as reference pixel points of each candidate pixel point, wherein N represents preset selection quantity, acquiring a temporary concave structure area adjacent to the left side of a temporary concave structure area to which each candidate pixel point belongs, and recording the temporary concave structure area as a reference temporary concave structure area of each candidate pixel point;
the calculation method of the transverse distribution possibility that each candidate pixel point is the center of the concave structure comprises the following steps:
wherein, Representing the gray value of the j-th reference pixel point on the left side of the i-th candidate pixel point,/>The gray value of the j-th reference pixel on the right side of the i-th candidate pixel point is represented, N represents the preset selection quantity,/>Representing the number of pixel points of the temporary concave structure area to which the ith candidate pixel point belongs,/>Representing the Euclidean distance between the ith candidate pixel point and the center point of the affiliated temporary concave structure area,/>Represents the lateral width of the temporary concave structure area to which the ith candidate pixel point belongs,/>Representing the Euclidean distance between the ith candidate pixel point and the central point of the reference temporary concave structure area; /(I)Representing an exponential function based on a natural constant,/>Representing the possibility of transverse distribution of the ith alternative pixel point as the center of the concave structure;
And acquiring the longitudinal distribution possibility that each candidate pixel point is the center of the concave structure.
Preferably, the possibility that each candidate pixel point is the center of the concave structure is obtained according to the possibility that each candidate pixel point is the horizontal distribution and the possibility that each candidate pixel point is the longitudinal distribution of the center of the concave structure; obtaining a suspected concave structure center point according to the possibility that each candidate pixel point is a concave structure center, wherein the method comprises the following specific steps:
wherein, Representing the possibility of lateral distribution of the ith candidate pixel point as the center of the concave structure,/>Representing the longitudinal distribution possibility that the ith candidate pixel point is the center of the concave structure,/>Representing the possibility that the ith candidate pixel point is the center of the concave structure;
And taking the candidate pixel point with the highest possibility of the concave structure center in each temporary concave structure area as a suspected concave structure center point.
Preferably, the method for obtaining the center point of the concave structure to be combined according to the area of the temporary concave structure region to which each center point of the suspected concave structure belongs, the distance between each center point of the suspected concave structure and the center point of other temporary concave structure regions, and the possibility that each center point of the suspected concave structure is the center of the concave structure, obtains the region combining necessity of each center point of the suspected concave structure, and obtains the center point of the concave structure to be combined according to the region combining necessity of each center point of the suspected concave structure, includes the specific steps as follows:
Acquiring four suspected concave structure center points closest to each suspected concave structure center point from all the suspected concave structure center points, marking the four suspected concave structure center points as reference suspected concave structure center points of each suspected concave structure center point, and marking a quadrilateral area formed by the four reference suspected concave structure center points of each suspected concave structure center point as an analysis area of each suspected concave structure center point;
The calculation method of the region merging necessity of the center point of each suspected concave structure comprises the following steps:
wherein, Indicating Euclidean distance between the center point of the t suspected concave structure and the center point of the analysis area,/>Representing the variance of the distances of the t-th suspected concave structure center point from all reference suspected concave structure center points,/>Represents the possibility that the t suspected concave structure center point is the concave structure center,/>Mean value of distances between the center point of the t-th suspected concave structure and the center points of all reference suspected concave structures is expressedRepresents the average value of the distances between the center points of the kth suspected concave structure except the center point of the kth suspected concave structure and all reference suspected concave structure center points, J represents the number of the center points of the suspected concave structure,/>The region merging necessity of the t suspected concave structure center point is represented; /(I)An exponential function that is based on a natural constant;
And marking the suspected concave structure center point with the region merging necessity larger than the preset merging threshold value as the concave structure center point to be merged.
Preferably, the merging processing is performed on the temporary concave structure area to which the center point of the concave structure to be merged belongs to obtain a first complete concave structure area, which comprises the following specific steps:
The method comprises the steps that a set formed by all concave structure center points to be combined is called a first analysis set, one concave structure center point to be combined is selected in the first analysis set to be marked as a first concave structure center point to be combined, a standby combining point which is closest to the first concave structure center point to be combined and is marked as a first concave structure center point to be combined is obtained in the first analysis set, and a temporary concave structure area which the first concave structure center point to be combined belongs to is combined with a temporary concave structure area which the standby combining point belongs to obtain a first complete concave structure area; removing center points of concave structures to be combined which are already involved in combining processing from a first analysis set to obtain a second analysis set, optionally marking one center point of the concave structures to be combined as a second center point of the concave structures to be combined in the second analysis set, marking the center point of the concave structures to be combined closest to the second center point of the concave structures to be combined as a standby combining point of the second center point of the concave structures to be combined in the second analysis set, and combining a temporary concave structure region to which the center point of the second concave structures to be combined belongs with a temporary concave structure region to which the standby combining point belongs to obtain a first complete concave structure region; and similarly, finishing the merging treatment of the temporary concave structure areas of all the to-be-merged concave structure center points to obtain a plurality of first complete concave structure areas.
Preferably, the method for obtaining all the complete concave structure areas and the accurate center point of each complete concave structure area according to the area merging necessity of each suspected concave structure center and the first complete concave structure area includes the following specific steps:
the temporary concave structure area with the area merging necessity smaller than or equal to a preset merging threshold value and to which the suspected concave structure central point belongs is marked as a second complete concave structure area, and the suspected concave structure central point of the second complete concave structure area is used as the accurate central point of the second complete concave structure area; taking the central point of the first complete concave structure area as the accurate central point of the first complete concave structure area; the first complete concave structural region and the second complete concave structural region are both referred to as complete concave structural regions.
Preferably, the periodic unit window is obtained according to the accurate center point of each complete concave structure area, and the specific method comprises the following steps:
Acquiring four accurate center points closest to the accurate center point of each complete concave structure area, marking the four accurate center points as adjacent center points of the accurate center point of each complete concave structure area, and enabling a quadrilateral area formed by the four adjacent center points of the accurate center point of each complete concave structure area to be called a temporary periodic unit of each complete concave structure area;
taking the average value of the lengths of the temporary period units of all the complete concave structure areas as the comprehensive length; taking the average value of the widths of the temporary period units of all the complete concave structure areas as the comprehensive width; rectangular windows with length of integrated length and width of integrated width are called periodic unit windows.
Preferably, the detecting the stained area in the non-woven fabric surface image according to the periodic unit window includes the following specific steps:
Overlapping each pixel of the non-woven fabric surface image with the center of the periodic unit window to obtain a periodic unit window image of each pixel; marking any pixel as a target pixel, taking the accumulated sum of the gray values of all pixels in a periodic unit window image of the target pixel as the comprehensive gray value of the target pixel, and obtaining the comprehensive gray value of each pixel; obtaining a segmentation threshold of the comprehensive gray values of all pixels of the non-woven fabric surface image by using an Ojin threshold method, and marking the segmentation threshold as a stain segmentation threshold; pixels with the integrated gray value smaller than the stain dividing threshold value are marked as stain pixels, and a connected region formed by the stain pixels is called a stain region.
A nonwoven fabric surface defect detection system, the system comprising the following modules:
the image acquisition module is used for acquiring the surface image of the non-woven fabric;
The suspected concave structure center point acquisition module is used for acquiring an alternative pixel point and a temporary concave structure area formed by the alternative pixel point according to the non-woven fabric surface image; according to the size of the temporary concave structure area to which each candidate pixel point belongs, the distance between each candidate pixel point and the center point of the nearest other temporary concave structure area obtains the transverse distribution possibility and the longitudinal distribution possibility of each candidate pixel point serving as the center of the concave structure; obtaining the possibility that each candidate pixel point is the center of the concave structure according to the transverse distribution possibility and the longitudinal distribution possibility that each candidate pixel point is the center of the concave structure; obtaining a suspected concave structure center point according to the possibility that each candidate pixel point is the concave structure center;
The periodic unit window acquisition module is used for acquiring the region merging necessity of each suspected concave structure center according to the area of the temporary concave structure region to which each suspected concave structure center point belongs, the distance between each suspected concave structure center point and the center point of other temporary concave structure regions, and the possibility that each suspected concave structure center point is the concave structure center; obtaining a to-be-merged concave structure center point according to the region merging necessity of each suspected concave structure center, and merging the temporary concave structure regions to which the to-be-merged concave structure center point belongs to obtain a first complete concave structure region; obtaining all complete concave structure areas and accurate center points of each complete concave structure area according to the area merging necessity of the center of each suspected concave structure and the first complete concave structure area; obtaining a periodic unit window according to the accurate center point of each complete concave structure area;
and the stain area detection module is used for detecting the stain area in the non-woven fabric surface image according to the periodic unit window.
The technical scheme of the invention has the beneficial effects that: acquiring a non-woven fabric surface image, and acquiring each candidate pixel point and a plurality of temporary concave structure areas formed by the candidate pixel points in the non-woven fabric image, wherein the temporary concave structure areas are obtained through rough segmentation, so that the temporary concave structure areas are not complete concave structure areas; and obtaining a suspected concave structure center point according to the distance between each candidate pixel point and the center point of the temporary concave structure area, wherein the suspected concave structure center point is a pixel point with high possibility of being the center point of the concave structure area among a plurality of pixel points of the non-woven fabric surface image, and the preparation is made for obtaining a periodic unit subsequently. Because the temporary concave structure area may be only a part of the complete concave structure area, the temporary concave structure areas to which the center point of each suspected concave structure belongs need to be combined to obtain the complete concave structure area. The exact center point is obtained by the complete concave structure region. And obtaining a periodic unit window according to the accurate center point. The periodic element window can reflect the smallest element of the repeated cycle in the nonwoven surface image. And detecting the dirty area according to the difference of the gray value accumulation sum of the pixels in each periodic unit window and the gray value accumulation sums of the pixels in other periodic unit windows.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of 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 may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart showing the steps of a method for detecting surface defects of a nonwoven fabric according to the present invention;
FIG. 2 is a block diagram showing a system for detecting surface defects of a nonwoven fabric according to the present invention;
FIG. 3 is a view showing the surface image of a nonwoven fabric according to the present invention;
Fig. 4 is a schematic view of a periodic unit window according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to specific implementation, structure, characteristics and effects of a method and a system for detecting surface defects of non-woven fabrics according to the invention, which are provided by the invention, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of a non-woven fabric surface defect detection method and system provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for detecting surface defects of a nonwoven fabric according to an embodiment of the invention is shown, the method includes the following steps:
Step S001: and acquiring a non-woven fabric surface image.
Specifically, in order to implement the method for detecting the surface defects of the non-woven fabric provided in this embodiment, the image of the surface of the non-woven fabric needs to be collected first. The specific operation of collecting the surface image of the non-woven fabric comprises the following steps:
The non-woven fabric surface image is acquired by utilizing a linear array CCD camera, and is subjected to gray processing to obtain a gray image of the non-woven fabric surface image, which is still called as the non-woven fabric surface image for convenience of description. The nonwoven fabric surface image is shown in fig. 3, with the stained area within the rectangular box in fig. 3.
Step S002: and obtaining candidate pixel points in the non-woven fabric surface image, calculating the possibility that each candidate pixel point is a concave structure center point, and obtaining a suspected concave structure center point according to the possibility that each candidate pixel point is the concave structure center point.
In order to acquire the periodic unit of the nonwoven fabric surface image, the center point of the concave structure region of the nonwoven fabric surface image needs to be acquired first, and the pixels in the concave structure region need to be acquired to acquire the center point of the concave structure region.
It should be further noted that, as shown in the surface image of the non-woven fabric in fig. 3, the area occupied by the concave structure area and the convex structure area on the non-woven fabric is similar, and the stained area is generally smaller, so that the dividing threshold value of the concave structure area and the convex structure area should be in the median position of all the pixel gray values. Pixels of the areas of concave structures in the nonwoven surface image can thus be acquired based on this.
Specifically, the median of the gray values of all pixels in the non-woven fabric surface image is obtained, the median of the gray values of all pixels in the non-woven fabric surface image is used as a structural threshold, and pixels smaller than the structural threshold in the non-woven fabric surface image are recorded as candidate pixel points.
And (5) marking the communication area formed by the candidate pixel points as a temporary concave structure area.
It should be noted that, due to the insufficiently accurate set segmentation threshold, a complete concave structure region may not be segmented, i.e., each temporary concave structure region is not a complete concave structure region. It is not accurate to directly use the center point of each temporary concave structural region as the center point of the concave structural region.
It should be further noted that, as shown in fig. 3, the concave structure areas and the convex structure areas of the nonwoven fabric are alternately distributed, the concave structure areas are square, and the width of each concave structure area is similar to the width of the convex structure area between the two concave structure areas. The likelihood of each candidate pixel being the center of the concave structure can thus be analyzed based on this information and the distance relationship of the center point of the concave structure region in the horizontal and vertical directions.
Further, N continuous pixel points in the same row are obtained by taking each candidate pixel point as the center and used as the reference pixel point of each candidate pixel point. N represents a preset selection number. In this embodiment, N is taken as 21 as an example, and other values may be taken in other embodiments, and the present embodiment is not particularly limited. And acquiring a temporary concave structure area adjacent to the left side of the temporary concave structure area to which each candidate pixel point belongs, and recording the temporary concave structure area as a reference temporary concave structure area of each candidate pixel point.
The calculation method of the transverse distribution possibility that each candidate pixel point is the center of the concave structure comprises the following steps:
wherein, Representing the gray value of the j-th reference pixel point on the left side of the i-th candidate pixel point,/>The gray value of the j-th reference pixel on the right side of the i-th candidate pixel point is represented, N represents the preset selection quantity,/>The difference of gray values of the pixel points at the left side and the right side of the ith candidate pixel point is reflected. The smaller the value, the greater the probability that the ith candidate pixel point is the center of the concave structure, i.e./>The number of the pixel points of the temporary concave structure area to which the ith candidate pixel point belongs is represented, and the larger the value is, the more complete the temporary concave structure area to which the ith candidate pixel point belongs is, and the more accurate the central point of the concave structure area can be obtained. /(I)The euclidean distance between the ith candidate pixel point and the center point of the temporary concave structure area, which is related to the ith candidate pixel point, is represented, and the larger the value is, the greater the possibility that the ith candidate pixel point is the center point of the concave structure area is. /(I)Represents the lateral width of the temporary concave structure area to which the ith candidate pixel point belongs,/>Representing the Euclidean distance between the ith candidate pixel point and the central point of the reference temporary concave structure area; when the ith alternative pixel point is the center point of the concave structural area, the distance between the ith alternative pixel point and the center point of the reference temporary concave structural area is equal to the side length of the concave structural area, the width of the convex structural area between the temporary concave structural area to which the ith alternative pixel point belongs and the reference temporary concave structural area is added, and the side length of the concave structural area is added and the width of the convex structural area between the concave structural areas is equal to 2 times of the side length of the concave structural area because the widths of the concave structural areas are similar to each other, thereby/>The smaller the probability that the i-th candidate pixel point is the center point of the concave structure region is larger. /(I)An exponential function based on a natural constant is represented. /(I)Representing the lateral distribution possibility that the i-th candidate pixel point is the center of the concave structure.
And similarly, obtaining the possibility of longitudinal distribution of each candidate pixel point serving as the center of the concave structure.
The calculation method for obtaining the possibility that each candidate pixel point is the concave structure center according to the transverse distribution possibility and the longitudinal distribution possibility that each candidate pixel point is the concave structure center comprises the following steps:
wherein, Representing the possibility of lateral distribution of the ith candidate pixel point as the center of the concave structure,/>Representing the possibility of longitudinal distribution of the i-th candidate pixel point as the center of the concave structure. Because the concave structure area is square, when the ith alternative pixel point is the center point of the concave structure area, the possibility that the ith alternative pixel point is transversely distributed at the center of the concave structure and the possibility that the ith alternative pixel point is longitudinally distributed at the center of the concave structure are close, so/>The smaller the probability that the i-th candidate pixel point is the center point of the concave structure region is larger. /(I)Representing the likelihood that the i-th candidate pixel is the center of the concave structure.
Further, the candidate pixel point with the highest possibility of the concave structure center in each temporary concave structure area is taken as a suspected concave structure center point.
Step S003: calculating the region merging necessity of the center point of each suspected concave structure, obtaining a complete concave structure region and the accurate center point of each complete concave structure region according to the region merging necessity of the center point of each suspected concave structure, and obtaining a periodic unit window according to the accurate center point of each complete concave structure region.
It should be noted that, since the temporary concave structure region may not be a complete concave structure region, that is, there may be a concave structure region divided into two or more temporary concave structure regions, the center point of the suspected concave structure selected in each temporary concave structure region is not the center point of the true concave structure region. Therefore, the merging condition of the temporary concave structure area where the center point of each suspected concave structure is located needs to be analyzed.
Specifically, four suspected concave structure center points closest to each suspected concave structure center point are obtained from all suspected concave structure center points and are recorded as reference suspected concave structure center points of each suspected concave structure center point. And marking a quadrilateral area formed by four reference suspected concave structure center points of each suspected concave structure center point as an analysis area of each suspected concave structure center point.
The calculation method of the region merging necessity of the center point of each suspected concave structure comprises the following steps:
wherein, The Euclidean distance between the center point of the t suspected concave structure and the center point of the analysis area is represented, and the larger the value is, the less possibility that the center point of the t suspected concave structure is the center point of the concave structure area is shown, the greater the possibility that the temporary concave structure area to which the center point of the t suspected concave structure belongs is part of the concave structure area, and therefore the greater the area merging necessity of the center point of the t suspected concave structure is. /(I)The variance of the distances between the t-th suspected concave structure center point and all the reference suspected concave structure center points is represented, when the t-th suspected concave structure center point is the center point of the concave structure area, the distances between the t-th suspected concave structure center point and each reference suspected concave structure center point should be similar, so when the variance of the distances between the t-th suspected concave structure center point and the midpoints of all the reference suspected concave structures is larger, the probability that the t-th suspected concave structure center point is the center point of the concave structure area is smaller, the probability that the temporary concave structure area to which the t-th suspected concave structure center point belongs is a part of the concave structure area is larger, and therefore the region merging necessity of the t-th suspected concave structure center point is larger. /(I)Represents the possibility that the t suspected concave structure center point is the concave structure center,/>Mean value of distances between the center point of the t-th suspected concave structure and the center points of all reference suspected concave structures is expressedRepresents the average value of the distances between the kth suspected concave structure center point except the t suspected concave structure center point and all the reference suspected concave structure center points, J represents the number of suspected concave structure center points,The average value of the distances between the t suspected concave structure center point and all the reference suspected concave structure center points is reflected, and the difference value of the average value of the distances between the t suspected concave structure center point and all the reference suspected concave structure center points is larger, so that the greater the value is, the smaller the possibility that the t suspected concave structure center point is the concave structure region center point is, the greater the possibility that the temporary concave structure region to which the t suspected concave structure center point belongs is a part of the concave structure region is, and therefore the greater the region merging necessity of the t suspected concave structure center point is. /(I)The region merging necessity of the t-th suspected concave structure center point is represented. /(I)An exponential function based on a natural constant is represented.
And normalizing the region merging necessity of each suspected concave structure center point by using a linear normalization method to obtain the normalized region merging necessity of each suspected concave structure center point, wherein the normalized region merging necessity of each suspected concave structure center point is still called as the region merging necessity of each suspected concave structure center point for convenience of description.
And marking the center points of the suspected concave structures with the region merging necessity larger than the preset merging threshold Y1 as the center points of the concave structures to be merged. In this embodiment, Y1 is taken as an example of 0.3, and other values may be taken in other embodiments, and the embodiment is not particularly limited.
And (3) selecting a set formed by all the concave structure central points to be combined as a first analysis set, marking one concave structure central point to be combined as a first concave structure central point to be combined in the first analysis set, acquiring a standby combining point which is closest to the first concave structure central point to be combined and is marked as the first concave structure central point to be combined in the first analysis set, and combining a temporary concave structure area which the first concave structure central point to be combined belongs to with a temporary concave structure area which the standby combining point belongs to obtain a first complete concave structure area. Removing center points of concave structures to be combined which are already involved in combining processing from a first analysis set to obtain a second analysis set, optionally marking one center point of the concave structures to be combined as a second center point of the concave structures to be combined in the second analysis set, marking the center point of the concave structures to be combined closest to the second center point of the concave structures to be combined as a standby combining point of the second center point of the concave structures to be combined in the second analysis set, and combining a temporary concave structure region to which the center point of the second concave structures to be combined belongs with a temporary concave structure region to which the standby combining point belongs to obtain a first complete concave structure region. And similarly, finishing the merging treatment of the temporary concave structure areas of all the to-be-merged concave structure center points to obtain a plurality of first complete concave structure areas. And taking the central point of the first complete concave structure area as the accurate central point of the first complete concave structure area.
And marking the temporary concave structure area with the regional merging necessity smaller than or equal to the preset merging threshold Y1 and to which the suspected concave structure center point belongs as a second complete concave structure area. And taking the suspected concave structure center point of the second complete concave structure area as the accurate center point of the second complete concave structure area.
The first complete concave structural region and the second complete concave structural region are both referred to as complete concave structural regions.
Further, four accurate center points closest to the accurate center point of each complete concave structure area are acquired and recorded as adjacent center points of the accurate center point of each complete concave structure area, and a quadrilateral area formed by the four adjacent center points of the accurate center point of each complete concave structure area is called a temporary periodic unit of each complete concave structure area.
Taking the average value of the lengths of the temporary period units of all the complete concave structure areas as the comprehensive length; the average value of the widths of the temporary periodic units of all the complete concave structure areas is taken as the comprehensive width. Rectangular windows with length of integrated length and width of integrated width are called periodic unit windows. Fig. 4 shows a schematic view of a periodic cell window, in which the large quadrangle is the periodic cell window and the small quadrangle is the complete concave structural region in fig. 4.
Step S004: and detecting stains according to the periodic unit window to obtain a stain area.
When the non-woven fabric surface image does not have a stained area, the non-woven fabric surface image should have a cycle repeatability. Thus the sum of the gray values of the pixels in each periodic unit should be similar when no stained area is present. Thus, a stained area can be detected based thereon.
Specifically, each pixel of the non-woven fabric surface image is overlapped with the center of the periodic unit window, and the periodic unit window image of each pixel is obtained. And marking any pixel as a target pixel, and taking the accumulated sum of the gray values of all pixels in the periodic unit window image of the target pixel as the comprehensive gray value of the target pixel. And the integrated gray value of each pixel is obtained by the same method. And obtaining a segmentation threshold of the comprehensive gray value of all pixels of the non-woven fabric surface image by using an Ojin threshold method, and marking the segmentation threshold as a stain segmentation threshold. Pixels with integrated gray values less than the smear segmentation threshold are noted as smear pixels. The connected region constituted by the stained pixels is referred to as a stained region.
Referring to fig. 2, a non-woven fabric surface defect detection system provided by an embodiment of the invention is shown, and the system includes the following modules:
the image acquisition module is used for acquiring the surface image of the non-woven fabric;
The suspected concave structure center point acquisition module is used for acquiring an alternative pixel point and a temporary concave structure area formed by the alternative pixel point according to the non-woven fabric surface image; according to the size of the temporary concave structure area to which each candidate pixel point belongs, the distance between each candidate pixel point and the center point of the nearest other temporary concave structure area obtains the transverse distribution possibility and the longitudinal distribution possibility of each candidate pixel point serving as the center of the concave structure; obtaining the possibility that each candidate pixel point is the center of the concave structure according to the transverse distribution possibility and the longitudinal distribution possibility that each candidate pixel point is the center of the concave structure; obtaining a suspected concave structure center point according to the possibility that each candidate pixel point is the concave structure center;
The periodic unit window acquisition module is used for acquiring the region merging necessity of each suspected concave structure center according to the area of the temporary concave structure region to which each suspected concave structure center point belongs, the distance between each suspected concave structure center point and the center point of other temporary concave structure regions, and the possibility that each suspected concave structure center point is the concave structure center; obtaining a to-be-merged concave structure center point according to the region merging necessity of each suspected concave structure center, and merging the temporary concave structure regions to which the to-be-merged concave structure center point belongs to obtain a first complete concave structure region; obtaining all complete concave structure areas and accurate center points of each complete concave structure area according to the area merging necessity of the center of each suspected concave structure and the first complete concave structure area; obtaining a periodic unit window according to the accurate center point of each complete concave structure area;
and the stain area detection module is used for detecting the stain area in the non-woven fabric surface image according to the periodic unit window.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (7)
1. A method for detecting surface defects of a nonwoven fabric, comprising the steps of:
acquiring a non-woven fabric surface image;
Obtaining a temporary concave structure area formed by the alternative pixel points according to the non-woven fabric surface image; according to the size of the temporary concave structure area to which each candidate pixel point belongs, the distance between each candidate pixel point and the center point of the nearest other temporary concave structure area obtains the transverse distribution possibility and the longitudinal distribution possibility of each candidate pixel point serving as the center of the concave structure; obtaining the possibility that each candidate pixel point is the center of the concave structure according to the transverse distribution possibility and the longitudinal distribution possibility that each candidate pixel point is the center of the concave structure; obtaining a suspected concave structure center point according to the possibility that each candidate pixel point is the concave structure center;
According to the area of the temporary concave structure area to which each suspected concave structure center point belongs, the distance between each suspected concave structure center point and the center point of other temporary concave structure areas, and the possibility that each suspected concave structure center point is the concave structure center, the area merging necessity of each suspected concave structure center is obtained; obtaining a to-be-merged concave structure center point according to the region merging necessity of each suspected concave structure center, and merging the temporary concave structure regions to which the to-be-merged concave structure center point belongs to obtain a first complete concave structure region; obtaining all complete concave structure areas and accurate center points of each complete concave structure area according to the area merging necessity of the center of each suspected concave structure and the first complete concave structure area; obtaining a periodic unit window according to the accurate center point of each complete concave structure area;
Detecting a stain area in the non-woven fabric surface image according to the periodic unit window;
The method for obtaining the temporary concave structure area formed by the candidate pixel points and the candidate pixel points according to the non-woven fabric surface image comprises the following specific steps:
Acquiring the median of the gray values of all pixels in the non-woven fabric surface image, taking the median of the gray values of all pixels in the non-woven fabric surface image as a structural threshold value, and marking the pixels smaller than the structural threshold value in the non-woven fabric surface image as candidate pixel points;
the communication area formed by the candidate pixel points is marked as a temporary concave structure area;
according to the size of the temporary concave structure area to which each candidate pixel belongs, the distance between each candidate pixel and the center point of the nearest other temporary concave structure area obtains the transverse distribution possibility and the longitudinal distribution possibility of each candidate pixel as the center of the concave structure, and the specific method comprises the following steps:
taking each candidate pixel point as a center, acquiring N continuous pixel points in the same row as reference pixel points of each candidate pixel point, wherein N represents preset selection quantity, acquiring a temporary concave structure area adjacent to the left side of a temporary concave structure area to which each candidate pixel point belongs, and recording the temporary concave structure area as a reference temporary concave structure area of each candidate pixel point;
the calculation method of the transverse distribution possibility that each candidate pixel point is the center of the concave structure comprises the following steps:
wherein, Representing the gray value of the j-th reference pixel point on the left side of the i-th candidate pixel point,/>The gray value of the j-th reference pixel on the right side of the i-th candidate pixel point is represented, N represents the preset selection quantity,/>Representing the number of pixel points of the temporary concave structure area to which the ith candidate pixel point belongs,/>Representing the Euclidean distance between the ith candidate pixel point and the center point of the affiliated temporary concave structure area,/>Represents the lateral width of the temporary concave structure area to which the ith candidate pixel point belongs,/>Representing the Euclidean distance between the ith candidate pixel point and the central point of the reference temporary concave structure area; /(I)Representing an exponential function based on a natural constant,/>Representing the possibility of transverse distribution of the ith alternative pixel point as the center of the concave structure;
Acquiring the longitudinal distribution possibility of each candidate pixel point serving as the center of the concave structure;
the periodic unit window is obtained according to the accurate center point of each complete concave structure area, and the method comprises the following specific steps:
Acquiring four accurate center points closest to the accurate center point of each complete concave structure area, marking the four accurate center points as adjacent center points of the accurate center point of each complete concave structure area, and enabling a quadrilateral area formed by the four adjacent center points of the accurate center point of each complete concave structure area to be called a temporary periodic unit of each complete concave structure area;
taking the average value of the lengths of the temporary period units of all the complete concave structure areas as the comprehensive length; taking the average value of the widths of the temporary period units of all the complete concave structure areas as the comprehensive width; rectangular windows with length of integrated length and width of integrated width are called periodic unit windows.
2. The method for detecting surface defects of non-woven fabrics according to claim 1, wherein the possibility that each candidate pixel point is a concave structure center is obtained according to the possibility of transverse distribution and the possibility of longitudinal distribution that each candidate pixel point is a concave structure center; obtaining a suspected concave structure center point according to the possibility that each candidate pixel point is a concave structure center, wherein the method comprises the following specific steps:
wherein, Representing the possibility of lateral distribution of the ith candidate pixel point as the center of the concave structure,/>Representing the longitudinal distribution possibility that the ith candidate pixel point is the center of the concave structure,/>Representing the possibility that the ith candidate pixel point is the center of the concave structure;
And taking the candidate pixel point with the highest possibility of the concave structure center in each temporary concave structure area as a suspected concave structure center point.
3. The method for detecting surface defects of non-woven fabrics according to claim 1, wherein the method for obtaining the region merging necessity of each suspected concave structure center according to the region merging necessity of each suspected concave structure center and the distance between each suspected concave structure center and the center point of other temporary concave structure regions comprises the following specific steps:
Acquiring four suspected concave structure center points closest to each suspected concave structure center point from all the suspected concave structure center points, marking the four suspected concave structure center points as reference suspected concave structure center points of each suspected concave structure center point, and marking a quadrilateral area formed by the four reference suspected concave structure center points of each suspected concave structure center point as an analysis area of each suspected concave structure center point;
The calculation method of the region merging necessity of the center point of each suspected concave structure comprises the following steps:
wherein, Indicating Euclidean distance between the center point of the t suspected concave structure and the center point of the analysis area,/>Representing the variance of the distances of the t-th suspected concave structure center point from all reference suspected concave structure center points,/>Represents the possibility that the t suspected concave structure center point is the concave structure center,/>Mean value of distances between the center point of the t-th suspected concave structure and the center points of all reference suspected concave structures is expressedRepresents the average value of the distances between the center points of the kth suspected concave structure except the center point of the kth suspected concave structure and all reference suspected concave structure center points, J represents the number of the center points of the suspected concave structure,/>The region merging necessity of the t suspected concave structure center point is represented; /(I)An exponential function that is based on a natural constant;
And marking the suspected concave structure center point with the region merging necessity larger than the preset merging threshold value as the concave structure center point to be merged.
4. The method for detecting surface defects of non-woven fabrics according to claim 1, wherein the method for merging the temporary concave structure areas to which the center points of the concave structures to be merged belong to obtain a first complete concave structure area comprises the following specific steps:
The method comprises the steps that a set formed by all concave structure center points to be combined is called a first analysis set, one concave structure center point to be combined is selected in the first analysis set to be marked as a first concave structure center point to be combined, a standby combining point which is closest to the first concave structure center point to be combined and is marked as a first concave structure center point to be combined is obtained in the first analysis set, and a temporary concave structure area which the first concave structure center point to be combined belongs to is combined with a temporary concave structure area which the standby combining point belongs to obtain a first complete concave structure area; removing center points of concave structures to be combined which are already involved in combining processing from a first analysis set to obtain a second analysis set, optionally marking one center point of the concave structures to be combined as a second center point of the concave structures to be combined in the second analysis set, marking the center point of the concave structures to be combined closest to the second center point of the concave structures to be combined as a standby combining point of the second center point of the concave structures to be combined in the second analysis set, and combining a temporary concave structure region to which the center point of the second concave structures to be combined belongs with a temporary concave structure region to which the standby combining point belongs to obtain a first complete concave structure region; and similarly, finishing the merging treatment of the temporary concave structure areas of all the to-be-merged concave structure center points to obtain a plurality of first complete concave structure areas.
5. The method for detecting surface defects of non-woven fabrics according to claim 1, wherein the method for obtaining all the complete concave structure areas and the accurate center point of each complete concave structure area according to the area merging necessity of the center of each suspected concave structure and the first complete concave structure area comprises the following specific steps:
the temporary concave structure area with the area merging necessity smaller than or equal to a preset merging threshold value and to which the suspected concave structure central point belongs is marked as a second complete concave structure area, and the suspected concave structure central point of the second complete concave structure area is used as the accurate central point of the second complete concave structure area; taking the central point of the first complete concave structure area as the accurate central point of the first complete concave structure area; the first complete concave structural region and the second complete concave structural region are both referred to as complete concave structural regions.
6. The method for detecting surface defects of a non-woven fabric according to claim 1, wherein the detecting the stained area in the non-woven fabric surface image according to the periodic unit window comprises the following specific steps:
Overlapping each pixel of the non-woven fabric surface image with the center of the periodic unit window to obtain a periodic unit window image of each pixel; marking any pixel as a target pixel, taking the accumulated sum of the gray values of all pixels in a periodic unit window image of the target pixel as the comprehensive gray value of the target pixel, and obtaining the comprehensive gray value of each pixel; obtaining a segmentation threshold of the comprehensive gray values of all pixels of the non-woven fabric surface image by using an Ojin threshold method, and marking the segmentation threshold as a stain segmentation threshold; pixels with the integrated gray value smaller than the stain dividing threshold value are marked as stain pixels, and a connected region formed by the stain pixels is called a stain region.
7. A nonwoven fabric surface defect detection system, characterized in that the system comprises the following modules:
the image acquisition module is used for acquiring the surface image of the non-woven fabric;
The suspected concave structure center point acquisition module is used for acquiring an alternative pixel point and a temporary concave structure area formed by the alternative pixel point according to the non-woven fabric surface image; according to the size of the temporary concave structure area to which each candidate pixel point belongs, the distance between each candidate pixel point and the center point of the nearest other temporary concave structure area obtains the transverse distribution possibility and the longitudinal distribution possibility of each candidate pixel point serving as the center of the concave structure; obtaining the possibility that each candidate pixel point is the center of the concave structure according to the transverse distribution possibility and the longitudinal distribution possibility that each candidate pixel point is the center of the concave structure; obtaining a suspected concave structure center point according to the possibility that each candidate pixel point is the concave structure center;
The periodic unit window acquisition module is used for acquiring the region merging necessity of each suspected concave structure center according to the area of the temporary concave structure region to which each suspected concave structure center point belongs, the distance between each suspected concave structure center point and the center point of other temporary concave structure regions, and the possibility that each suspected concave structure center point is the concave structure center; obtaining a to-be-merged concave structure center point according to the region merging necessity of each suspected concave structure center, and merging the temporary concave structure regions to which the to-be-merged concave structure center point belongs to obtain a first complete concave structure region; obtaining all complete concave structure areas and accurate center points of each complete concave structure area according to the area merging necessity of the center of each suspected concave structure and the first complete concave structure area; obtaining a periodic unit window according to the accurate center point of each complete concave structure area;
The stain area detection module is used for detecting a stain area in the non-woven fabric surface image according to the periodic unit window;
The method for obtaining the temporary concave structure area formed by the candidate pixel points and the candidate pixel points according to the non-woven fabric surface image comprises the following specific steps:
Acquiring the median of the gray values of all pixels in the non-woven fabric surface image, taking the median of the gray values of all pixels in the non-woven fabric surface image as a structural threshold value, and marking the pixels smaller than the structural threshold value in the non-woven fabric surface image as candidate pixel points;
the communication area formed by the candidate pixel points is marked as a temporary concave structure area;
according to the size of the temporary concave structure area to which each candidate pixel belongs, the distance between each candidate pixel and the center point of the nearest other temporary concave structure area obtains the transverse distribution possibility and the longitudinal distribution possibility of each candidate pixel as the center of the concave structure, and the specific method comprises the following steps:
taking each candidate pixel point as a center, acquiring N continuous pixel points in the same row as reference pixel points of each candidate pixel point, wherein N represents preset selection quantity, acquiring a temporary concave structure area adjacent to the left side of a temporary concave structure area to which each candidate pixel point belongs, and recording the temporary concave structure area as a reference temporary concave structure area of each candidate pixel point;
the calculation method of the transverse distribution possibility that each candidate pixel point is the center of the concave structure comprises the following steps:
wherein, Representing the gray value of the j-th reference pixel point on the left side of the i-th candidate pixel point,/>The gray value of the j-th reference pixel on the right side of the i-th candidate pixel point is represented, N represents the preset selection quantity,/>Representing the number of pixel points of the temporary concave structure area to which the ith candidate pixel point belongs,/>Representing the Euclidean distance between the ith candidate pixel point and the center point of the affiliated temporary concave structure area,/>Represents the lateral width of the temporary concave structure area to which the ith candidate pixel point belongs,/>Representing the Euclidean distance between the ith candidate pixel point and the central point of the reference temporary concave structure area; /(I)Representing an exponential function based on a natural constant,/>Representing the possibility of transverse distribution of the ith alternative pixel point as the center of the concave structure;
Acquiring the longitudinal distribution possibility of each candidate pixel point serving as the center of the concave structure;
the periodic unit window is obtained according to the accurate center point of each complete concave structure area, and the method comprises the following specific steps:
Acquiring four accurate center points closest to the accurate center point of each complete concave structure area, marking the four accurate center points as adjacent center points of the accurate center point of each complete concave structure area, and enabling a quadrilateral area formed by the four adjacent center points of the accurate center point of each complete concave structure area to be called a temporary periodic unit of each complete concave structure area;
taking the average value of the lengths of the temporary period units of all the complete concave structure areas as the comprehensive length; taking the average value of the widths of the temporary period units of all the complete concave structure areas as the comprehensive width; rectangular windows with length of integrated length and width of integrated width are called periodic unit windows.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410238594.3A CN117830299B (en) | 2024-03-04 | 2024-03-04 | Non-woven fabric surface defect detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410238594.3A CN117830299B (en) | 2024-03-04 | 2024-03-04 | Non-woven fabric surface defect detection method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117830299A CN117830299A (en) | 2024-04-05 |
CN117830299B true CN117830299B (en) | 2024-05-17 |
Family
ID=90507990
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410238594.3A Active CN117830299B (en) | 2024-03-04 | 2024-03-04 | Non-woven fabric surface defect detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117830299B (en) |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5123144A (en) * | 1989-08-09 | 1992-06-23 | Maschinenfabrik Rieter Ag | Method and apparatus for establishing whether fiber material is contaminated with foreign objects |
JP2005345290A (en) * | 2004-06-03 | 2005-12-15 | Seiko Epson Corp | Streak-like flaw detecting method and streak-like flaw detector |
JP4629150B1 (en) * | 2009-10-19 | 2011-02-09 | 有限会社サン・オリオン | Image data processing apparatus for fabric, image data processing method, and computer program for image data processing |
JP2013246674A (en) * | 2012-05-28 | 2013-12-09 | Nippon Telegr & Teleph Corp <Ntt> | Figure detection processing device, figure detection processing method and figure detection processing program |
CN108765402A (en) * | 2018-05-30 | 2018-11-06 | 武汉理工大学 | Non-woven fabrics defects detection and sorting technique |
CN114627111A (en) * | 2022-05-12 | 2022-06-14 | 南通英伦家纺有限公司 | Textile defect detection and identification device |
CN114842007A (en) * | 2022-07-04 | 2022-08-02 | 南通东德纺织科技有限公司 | Textile wear defect detection method based on image processing |
CN115272303A (en) * | 2022-09-26 | 2022-11-01 | 睿贸恒诚(山东)科技发展有限责任公司 | Textile fabric defect degree evaluation method, device and system based on Gaussian blur |
WO2023070911A1 (en) * | 2021-10-27 | 2023-05-04 | 西安工程大学 | Self-attention-based method for detecting defective area of color-textured fabric |
CN116229438A (en) * | 2023-05-04 | 2023-06-06 | 山东超越纺织有限公司 | Spinning quality visual identification system |
CN116309671A (en) * | 2023-05-23 | 2023-06-23 | 浩珂科技有限公司 | Geosynthetic fabric quality detection system |
CN116805312A (en) * | 2023-08-21 | 2023-09-26 | 青岛时佳汇服装有限公司 | Knitted fabric quality detection method based on image processing |
CN116977333A (en) * | 2023-09-22 | 2023-10-31 | 山东恒海钢结构有限公司 | Image data-based quality detection method for assembled steel structural member |
CN117237354A (en) * | 2023-11-15 | 2023-12-15 | 宜兴启明星物联技术有限公司 | Visual detection method for defects of textile clothes |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6842532B2 (en) * | 2001-02-08 | 2005-01-11 | The Hong Kong Polytechnic University | Three dimensional measurement, evaluation and grading system for fabric/textile structure/garment appearance |
US7375806B2 (en) * | 2003-03-27 | 2008-05-20 | Bst Safety Textiles Gmbh | Method for inspecting the quality criteria of flat textile structures embodied in a multi-layer form according to a contour |
-
2024
- 2024-03-04 CN CN202410238594.3A patent/CN117830299B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5123144A (en) * | 1989-08-09 | 1992-06-23 | Maschinenfabrik Rieter Ag | Method and apparatus for establishing whether fiber material is contaminated with foreign objects |
JP2005345290A (en) * | 2004-06-03 | 2005-12-15 | Seiko Epson Corp | Streak-like flaw detecting method and streak-like flaw detector |
JP4629150B1 (en) * | 2009-10-19 | 2011-02-09 | 有限会社サン・オリオン | Image data processing apparatus for fabric, image data processing method, and computer program for image data processing |
JP2013246674A (en) * | 2012-05-28 | 2013-12-09 | Nippon Telegr & Teleph Corp <Ntt> | Figure detection processing device, figure detection processing method and figure detection processing program |
CN108765402A (en) * | 2018-05-30 | 2018-11-06 | 武汉理工大学 | Non-woven fabrics defects detection and sorting technique |
WO2023070911A1 (en) * | 2021-10-27 | 2023-05-04 | 西安工程大学 | Self-attention-based method for detecting defective area of color-textured fabric |
CN114627111A (en) * | 2022-05-12 | 2022-06-14 | 南通英伦家纺有限公司 | Textile defect detection and identification device |
CN114842007A (en) * | 2022-07-04 | 2022-08-02 | 南通东德纺织科技有限公司 | Textile wear defect detection method based on image processing |
CN115272303A (en) * | 2022-09-26 | 2022-11-01 | 睿贸恒诚(山东)科技发展有限责任公司 | Textile fabric defect degree evaluation method, device and system based on Gaussian blur |
CN116229438A (en) * | 2023-05-04 | 2023-06-06 | 山东超越纺织有限公司 | Spinning quality visual identification system |
CN116309671A (en) * | 2023-05-23 | 2023-06-23 | 浩珂科技有限公司 | Geosynthetic fabric quality detection system |
CN116805312A (en) * | 2023-08-21 | 2023-09-26 | 青岛时佳汇服装有限公司 | Knitted fabric quality detection method based on image processing |
CN116977333A (en) * | 2023-09-22 | 2023-10-31 | 山东恒海钢结构有限公司 | Image data-based quality detection method for assembled steel structural member |
CN117237354A (en) * | 2023-11-15 | 2023-12-15 | 宜兴启明星物联技术有限公司 | Visual detection method for defects of textile clothes |
Non-Patent Citations (3)
Title |
---|
《Fabric defect detection using morphological filters》;K.L Mak et al.;《Image and vision computing》;20090930;全文 * |
《基于机器视觉的无纺布缺陷在线检测技术研究》;张渤;《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》;20140715;全文 * |
《网格布断裂缺陷检测方法的研究》;方利华 等;《机械设计与制造》;20210430;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117830299A (en) | 2024-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113643289A (en) | Fabric surface defect detection method and system based on image processing | |
CN105160654A (en) | Towel label defect detecting method based on feature point extraction | |
CN115311507B (en) | Building board classification method based on data processing | |
CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
CN116977358B (en) | Visual auxiliary detection method for corrugated paper production quality | |
CN101806583A (en) | Microscopic image-based fiber fineness measurement method | |
CN101452532B (en) | Text identification method and device irrelevant to handwriting | |
CN116309671B (en) | Geosynthetic fabric quality detection system | |
CN104021561A (en) | Fabric fuzzing and pilling image segmentation method based on wavelet transformation and morphological algorithm | |
CN115272304B (en) | Cloth defect detection method and system based on image processing | |
CN113393426A (en) | Method for detecting surface defects of rolled steel plate | |
CN114998321B (en) | Textile material surface hairiness degree identification method based on optical means | |
CN110332886A (en) | A kind of precision visual method for rapidly positioning | |
CN108510544B (en) | Light strip positioning method based on feature clustering | |
CN112330598A (en) | Method and device for detecting stiff silk defects on chemical fiber surface and storage medium | |
CN115082744A (en) | Solar energy heat collection efficiency analysis method and system based on artificial intelligence | |
CN111507942A (en) | Chemical fiber filament broken filament detection device and method based on multi-view image analysis | |
CN115170475A (en) | Non-woven fabric defect detection method based on deep learning method | |
CN114782416A (en) | Textile quality detection method and system based on image recognition | |
CN117830299B (en) | Non-woven fabric surface defect detection method and system | |
CN106529551A (en) | Intelligent recognition, counting, and detection algorithm for quasi-circle object facing packaging industry | |
CN115272305A (en) | Button hole defect detection method | |
CN101853374B (en) | Fingerprint monitoring method during image acquisition process of planar fingerprint sensor | |
CN102073868A (en) | Digital image closed contour chain-based image area identification method | |
CN111339937B (en) | Method for extracting handwritten data in key column in simple table photo |
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 |