CN113820319A - Textile surface defect detection device and method - Google Patents
Textile surface defect detection device and method Download PDFInfo
- Publication number
- CN113820319A CN113820319A CN202111064818.6A CN202111064818A CN113820319A CN 113820319 A CN113820319 A CN 113820319A CN 202111064818 A CN202111064818 A CN 202111064818A CN 113820319 A CN113820319 A CN 113820319A
- Authority
- CN
- China
- Prior art keywords
- image
- textile
- defect
- module
- marking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 115
- 239000004753 textile Substances 0.000 title claims abstract description 110
- 238000001514 detection method Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000011218 segmentation Effects 0.000 claims abstract description 15
- 239000004744 fabric Substances 0.000 claims description 31
- 239000011324 bead Substances 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 6
- 238000005096 rolling process Methods 0.000 claims description 6
- 238000003705 background correction Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000009776 industrial production Methods 0.000 abstract description 4
- 230000008859 change Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
- G01N21/898—Irregularities in textured or patterned surfaces, e.g. textiles, wood
- G01N21/8983—Irregularities in textured or patterned surfaces, e.g. textiles, wood for testing textile webs, i.e. woven material
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
-
- G06T5/70—
-
- 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
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/888—Marking defects
-
- 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
-
- 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
- G06T2207/30204—Marker
Abstract
The invention discloses a textile surface defect detection device and method, relating to the technical field of textile surface defect detection and comprising the following steps: acquiring the surface image information of a textile area in advance, carrying out Blob feature point detection on the acquired surface image information of the area, acquiring a defect image, carrying out optimal threshold segmentation on the defect based on the defect image, marking the textile, dividing the defect image into a target image layer and a background image layer through a calibration threshold, acquiring inter-class variance and acquiring intra-class variance of the target image layer and the background image layer, and thus acquiring an image defect segmentation image. The invention realizes the detection and marking of the defect images, has high detection precision, accurate marking of textiles and wide application range, and can improve the industrial production efficiency.
Description
Technical Field
The invention relates to the technical field of textile surface defect detection, in particular to a device and a method for detecting textile surface defects.
Background
The detection of the surface quality of the textile is an important link in the production of the modern textile industry and plays an extremely important role in the production flow. At present, the so-called full-automatic cloth inspecting machine produced and sold in China still depends on human eyes to judge the quality of the surface of the textile, the work is monotonous, the labor intensity is high, and quality accidents caused by false detection and missing detection are easy to generate.
The invention patent CN1760437A of retrieval China discloses an automatic objective cloth inspection grade evaluation system, which mainly comprises a CCD camera, a fabric holding device, a light source, a computer and an image acquisition card, wherein the image acquisition card converts an acquired fabric image into a digital image, a defect detection DSP is used for detecting fabric defects, the fabric image with the detected defects is divided by a defect image division DSP module, the divided defects are automatically characterized by a defect characterization DSP module, the characterized result is input into the fabric grade evaluation DSP module, and finally, the fabric grade is automatically evaluated. However, when defects or chromatic aberration of the detected material is detected, the function is single and the detection accuracy is poor.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
The present invention provides a device and a method for detecting textile surface defects, which are directed to the problems in the related art, so as to overcome the above technical problems in the related art.
The technical scheme of the invention is realized as follows:
one aspect of the invention:
a textile surface defect detection method comprises the following steps:
step S1, collecting the surface image information of the textile area in advance;
step S2, performing Blob feature point detection on the acquired region surface image information, and acquiring a defect image;
step S3, performing optimal threshold segmentation of defects based on defect images and marking of textiles, comprising the steps of:
step S301, calibrating a threshold t to divide the defect image into a target image layer and a background image layer, and respectively calculating the occurrence probability u1、u2And the mean gray value w1、w2Expressed as:
step S302, obtaining the variance sigma between classes2(t), expressed as:
σ2(t)＝u1(t)*(w1(t)-w)2+u2(t)*(w2(t)-w)2；
step S303, obtaining the intra-class variance k of the target layer and the background layer respectively1And k2Expressed as:
step S304, calibrating the optimal adaptive threshold T*Expressed as:
T*＝Argmax0≤t＜l{(1-pi(t))*σ2(t)/(k1(t)+k2(t))}，
wherein p isi(t) is a function of the threshold value t;
in step S305, an image defect segmentation image g (u, v) is acquired, which is represented as:
wherein f (i, j) is the gray value of a certain point of the image, and T is a detection threshold;
step S306, marking the textile area is performed based on the image defect segmentation image g (u, v).
Wherein, still include the following step:
step S101, pre-processing the fabric on the textile and rolling the fabric, and removing foreign matters on the surface of the textile and unfolding the textile;
and S102, acquiring the surface image information of the textile in the conveying process in real time based on the multispectral LED light source and the image acquisition module, and inputting the surface image information as the surface image information of the textile area.
Wherein the textile area surface image information comprises the following steps:
step S103, preprocessing the surface image of the textile area, wherein the preprocessing comprises flat field correction processing and smoothing processing;
step S104, carrying out graying processing on the preprocessed textile regional surface image, and carrying out filtering and denoising on the grayed textile regional surface image by using a filtering algorithm;
the method comprises the following steps that a defect image is divided into a target image layer and a background image layer by the aid of the calibration threshold t, and the method further comprises the following steps:
step S3011, obtaining the occurrence probability p of each gray level i of the defect imageiExpressed as:
wherein N isiThe number of pixels with the gray level i is N, and the number of all pixels of the image is N;
step S3012, obtaining the overall average gray value w of the defect image, which is expressed as:
wherein 0,1,2.
The method for acquiring the integral average gray value w of the defect image comprises the following steps:
step S3013, obtaining the most significant value of the defect image and calibrating
Is an initial threshold value, wherein the maximum value is represented as wmaxThe minimum value is represented as wmin。
Wherein, the marking of the textile comprises the following steps:
step S307, marking the textile area of the image defect segmentation image by the inkjet indicator based on the washable ink.
In another aspect of the invention:
a textile surface defect detection device is used for a detection device of a textile surface defect detection method, and comprises the following components:
the mechanical cloth inspecting module is used for carrying out cloth feeding and cloth rolling treatment on the textile, removing foreign matters on the surface of the textile and unfolding the textile;
the multispectral LED module is used for multispectral illumination of textiles in the detection area of the mechanical cloth inspecting module;
the image acquisition module is used for acquiring the image information of the textile area in the conveying process of the mechanical cloth inspecting module in real time;
the image surface defect analysis module is used for carrying out defect detection on the image information of the textile area and acquiring defect image information;
and the defect marking module is used for marking based on the defect image information of the image surface defect analysis module.
Further, the multispectral LED module comprises one or more combinations of ultraviolet LED lamp beads, blue LED lamp beads, green LED lamp beads, red LED lamp beads and infrared LED lamp beads.
Further, the image acquisition module is an industrial CCD camera.
Further, the defect marking module includes an ink-jet indicator.
The invention has the beneficial effects that:
the invention discloses a textile surface defect detection device and a method, which are used for carrying out Blob feature point detection on acquired area surface image information by acquiring textile area surface image information in advance, acquiring a defect image, carrying out optimal threshold segmentation on the defect based on the defect image, marking a textile, dividing the defect image into a target image layer and a background image layer by calibrating a threshold, acquiring an inter-class variance and acquiring intra-class variances of the target image layer and the background image layer, thereby acquiring an image defect segmentation image, realizing defect image detection marking, having high detection precision, accurate marking on the textile, wide application range and capability of improving industrial production efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for detecting defects on a textile surface according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of a textile surface defect detection apparatus according to an embodiment of the present invention.
In the figure:
1. a mechanical cloth inspection module; 2. a multispectral LED module; 3. an image acquisition module; 4. an image surface flaw analysis module; 5. and a defect marking module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
According to an embodiment of the present invention, a method for detecting defects on a surface of a textile is provided.
As shown in FIG. 1, the method for detecting the surface defects of the textile according to the embodiment of the invention comprises the following steps:
step S1, collecting the surface image information of the textile area in advance;
step S2, performing Blob feature point detection on the acquired region surface image information, and acquiring a defect image;
step S3, performing optimal threshold segmentation of defects based on defect images and marking of textiles, comprising the steps of:
step S301, calibrating a threshold t to divide the defect image into a target image layer and a background image layer, and respectively calculating the occurrence probability u1、u2And the mean gray value w1、w2Expressed as:
step S302, obtaining the variance sigma between classes2(t), expressed as:
σ2(t)＝u1(t)*(w1(t)-w)2+u2(t)*(w2(t)-w)2；
step S303, obtaining the intra-class variance k of the target layer and the background layer respectively1And k2Expressed as:
step S304, calibrating the optimal adaptive threshold T*Expressed as:
T*＝Argmax0≤t＜l{(1-pi(t))*σ2(t)/(k1(t)+k2(t))}，
wherein p isi(t) is a function of the threshold value t;
in step S305, an image defect segmentation image g (u, v) is acquired, which is represented as:
wherein f (i, j) is the gray value of a certain point of the image, and T is a detection threshold;
step S306, marking the textile area is performed based on the image defect segmentation image g (u, v).
Wherein, still include the following step:
step S101, pre-processing the fabric on the textile and rolling the fabric, and removing foreign matters on the surface of the textile and unfolding the textile;
and S102, acquiring the surface image information of the textile in the conveying process in real time based on the multispectral LED light source and the image acquisition module, and inputting the surface image information as the surface image information of the textile area.
The method comprises the following steps of:
step S103, preprocessing the surface image of the textile area, wherein the preprocessing comprises flat field correction processing and smoothing processing;
step S104, carrying out graying processing on the preprocessed textile regional surface image, and carrying out filtering and denoising on the grayed textile regional surface image by using a filtering algorithm;
the method comprises the following steps that a calibration threshold t divides a defect image into a target image layer and a background image layer, and the method further comprises the following steps:
step S3011, obtaining the occurrence probability p of each gray level i of the defect imageiExpressed as:
wherein N isiThe number of pixels with the gray level i is N, and the number of all pixels of the image is N;
step S3012, obtaining the overall average gray value w of the defect image, which is expressed as:
wherein 0,1,2.
The method for acquiring the integral average gray value w of the defect image comprises the following steps:
step S3013, obtaining the most significant value of the defect image and calibrating
Is an initial threshold value, wherein the maximum value is represented as wmaxThe minimum value is represented as wmin。
The method for marking the textile comprises the following steps:
step S307, marking the textile area of the image defect segmentation image by the inkjet indicator based on the washable ink.
By means of the scheme, the information of the surface image of the textile area is collected in advance, Blob feature point detection is carried out on the obtained information of the surface image of the area, the image of the defects is obtained, the defects are segmented based on the image of the defects by the optimal threshold value, the textile is marked, the image of the defects is divided into the target image layer and the background image layer by the calibration threshold value, inter-class variance is obtained, and intra-class variance of the target image layer and the background image layer is obtained, so that the segmented image of the image defects is obtained, the defect image detection marking is realized, the detection precision is high, the marking of the textile is accurate, the application range is wide, and the industrial production efficiency can be improved.
According to the technical scheme, for the multispectral LED light source and the image acquisition module, the multispectral LED light source can adjust the brightness through a white balance algorithm. The brightness of the image can change along with the change of the type of the textile, the change of the external illumination intensity, the change of the speed of the movement of the textile and other factors, through a white balance algorithm, the scanning line frequency and the speed information obtained according to a frequency converter, the brightness of the image acquisition module is automatically adjusted, the image acquisition module is automatically adjusted along with the type of the cloth, the change of the external illumination intensity, the change of the speed of the movement of the textile and other factors, the image acquired by the image acquisition module has a better visual effect, the requirement of image analysis can be met by the definition of the acquired image, and the accuracy is improved.
In addition, the image capture module can adjust the exposure time. The average speed of the minimum picture element shot in the exposure time is far greater than the moving speed of the textile so as to clearly capture the image, the requirement on the illumination intensity is increased along with the increase of the speed of the textile, the average speed of the minimum picture element shot in the exposure time is far greater than the moving speed of the textile through the automatic adjustment of the exposure time, and the satisfactory image definition and the proper light intensity can be obtained simultaneously
In addition, in the technical scheme, the textile area surface image is preprocessed, the amplitude of the acquired image is wide, noise signals cannot be generated in the image acquisition process, a linear light source cannot guarantee absolute uniform light emitting, the image performance is poor due to factors such as time delay in the image acquisition process, and therefore the image needs to be subjected to flat field correction. Specifically, when the method is applied, a flat field correction algorithm provided by Sapera LT + + can be used for selecting a Basic algorithm and a Low Pass algorithm to correct image inconsistency, fixed image noise, image response inconsistency, lens and light source inconsistency and the like generated in the image acquisition process.
In addition, when the method is applied, common noises (such as salt and pepper noises, impulse noises, Gaussian noises and the like) generated by random signal pollution in the image acquisition process can be filtered through a Gaussian filtering algorithm, so that the interference of noise signals on image analysis is reduced.
According to another embodiment of the present invention, a textile surface defect detecting apparatus is provided.
As shown in fig. 2, a textile surface defect detecting device for a textile surface defect detecting method comprises:
the mechanical cloth inspecting module 1 is used for carrying out cloth feeding and cloth rolling treatment on the textile, removing foreign matters on the surface of the textile and unfolding the textile;
the multispectral LED module 2 is used for multispectral illumination of textiles in the detection area of the mechanical cloth inspecting module 1;
the image acquisition module 3 is used for acquiring the image information of the textile area in the conveying process of the mechanical cloth inspecting module 1 in real time;
the image surface defect analysis module 4 is used for carrying out defect detection on the image information of the textile area and acquiring defect image information;
and the defect marking module 5 is used for marking based on the defect image information of the image surface defect analysis module 4.
In addition, the multispectral LED module 2 comprises one or more combinations of ultraviolet LED lamp beads, blue LED lamp beads, green LED lamp beads, red LED lamp beads and infrared LED lamp beads.
In addition, the image acquisition module 3 is an industrial CCD camera.
In addition, defect marking module 5 includes an inkjet indicator.
In summary, according to the technical scheme of the invention, the information of the area surface image of the textile is collected in advance, the Blob feature point detection is performed on the obtained information of the area surface image, the defect image is obtained, the defects are segmented based on the defect image by the optimal threshold value, the textile is marked, the defect image is divided into the target image layer and the background image layer by calibrating the threshold value, the inter-class variance is obtained, and the intra-class variance of the target image layer and the background image layer is obtained, so that the defect image segmentation image of the image is obtained, the defect image detection marking is realized, the detection precision is high, the marking accuracy on the textile is accurate, the application range is wide, and the industrial production efficiency can be improved.
While the foregoing is directed to the preferred embodiment of the present invention, other and further embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A textile surface defect detection method is characterized by comprising the following steps:
acquiring surface image information of a textile area in advance;
performing Blob feature point detection on the obtained region surface image information, and obtaining a defect image;
performing optimal threshold segmentation of defects based on defect images and marking of textiles, comprising the steps of:
the defect image is divided into a target image layer and a background image layer by a calibration threshold t, and the occurrence probability u is calculated respectively1、u2And the mean gray value w1、w2Expressed as:
obtaining the variance between classes sigma2(t), expressed as:
σ2(t)＝u1(t)*(w1(t)-w)2+u2(t)*(w2(t)-w)2；
then, the intra-class variance k of the target layer and the background layer is respectively obtained1And k2Expressed as:
calibrating an optimal adaptive threshold T*Expressed as:
T*＝Arg max0≤t＜l{(1-pi(t))*σ2(t)/(k1(t)+k2(t))}，
wherein p isi(t) is a function of the threshold value t;
an image defect segmentation image g (u, v) is acquired, represented as:
wherein f (i, j) is the gray value of a certain point of the image, and T is a detection threshold;
the marking of the textile area is performed on the basis of the image defects segmentation image g (u, v).
2. A textile surface defect detection method as defined in claim 1, further comprising the steps of:
carrying out cloth feeding and cloth rolling treatment on the textile in advance, and removing foreign matters on the surface of the textile and unfolding the textile;
based on the multispectral LED light source and the image acquisition module, the surface image information of the textile in the conveying process is acquired in real time and is input as the surface image information of the textile area.
3. A textile surface defect detection method as claimed in claim 2 wherein said textile area surface image information comprises the steps of:
preprocessing the surface image of the textile area, wherein the preprocessing comprises flat field correction processing and smoothing processing;
and carrying out graying treatment on the surface image of the pretreated textile area, and carrying out filtering and denoising on the grayed textile area surface image by using a filtering algorithm.
4. A textile surface defect detection method according to claim 3, wherein said calibration threshold t divides the defect image into a target image layer and a background image layer, further comprising the steps of:
obtaining the occurrence probability p of each gray level i of the defect imageiExpressed as:
wherein N isiThe number of pixels with the gray level i is N, and the number of all pixels of the image is N;
acquiring the overall average gray value w of the defect image, and expressing as:
wherein 0,1,2.
5. A textile surface defect detection method according to claim 4, wherein said obtaining an ensemble average gray scale value w of defect images comprises the steps of:
obtaining the maximum value of the defect image and calibrating
Is an initial threshold value, wherein the maximum value is represented as wmaxThe minimum value is represented as wmin。
6. The method of detecting textile surface defects of claim 5 wherein said marking the textile comprises the steps of:
the textile areas of the image segmented image of the image defect are marked by an inkjet indicator based on a washable ink.
7. A textile surface defect inspection apparatus for use in the textile surface defect inspection method of any one of claims 1-6, comprising:
the mechanical cloth inspecting module (1) is used for carrying out cloth feeding and cloth rolling treatment on the textile, removing foreign matters on the surface of the textile and unfolding the textile;
the multispectral LED module (2) is used for multispectral illumination of textiles in the detection area of the mechanical cloth inspecting module (1);
the image acquisition module (3) is used for acquiring the image information of the textile area in the conveying process of the mechanical cloth inspecting module (1) in real time;
the image surface flaw analysis module (4) is used for carrying out flaw detection on the image information of the textile area and acquiring the image information of the flaws;
and the defect marking module (5) is used for marking based on the defect image information of the image surface defect analysis module (4).
8. The textile surface defect detection device of claim 7, wherein the multispectral LED module (2) comprises one or more combinations of ultraviolet LED beads, blue LED beads, green LED beads, red LED beads and infrared LED beads.
9. A textile surface defect detection apparatus according to claim 7, wherein the image acquisition module (3) is an industrial CCD camera.
10. A textile surface defect detection apparatus according to claim 7, wherein said defect marking module (5) comprises an inkjet indicator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111064818.6A CN113820319A (en) | 2021-09-11 | 2021-09-11 | Textile surface defect detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111064818.6A CN113820319A (en) | 2021-09-11 | 2021-09-11 | Textile surface defect detection device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113820319A true CN113820319A (en) | 2021-12-21 |
Family
ID=78922026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111064818.6A Pending CN113820319A (en) | 2021-09-11 | 2021-09-11 | Textile surface defect detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113820319A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419037A (en) * | 2022-03-28 | 2022-04-29 | 江苏智云天工科技有限公司 | Workpiece defect detection method and device |
| CN114627111A (en) * | 2022-05-12 | 2022-06-14 | 南通英伦家纺有限公司 | Textile defect detection and identification device |
| CN116152230A (en) * | 2023-04-17 | 2023-05-23 | 江苏华拓纺织科技有限公司 | Textile surface dyeing quality detection method based on spectrum data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1760437A (en) * | 2005-11-10 | 2006-04-19 | 东华大学 | Automatic system for assessing grade of cloth inspection objectively |
| CN103778624A (en) * | 2013-12-20 | 2014-05-07 | 中原工学院 | Fabric defect detection method based on optical threshold segmentation |
| CN106780464A (en) * | 2016-12-15 | 2017-05-31 | 东华大学 | A kind of fabric defect detection method based on improvement Threshold segmentation |
-
2021
- 2021-09-11 CN CN202111064818.6A patent/CN113820319A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1760437A (en) * | 2005-11-10 | 2006-04-19 | 东华大学 | Automatic system for assessing grade of cloth inspection objectively |
| CN103778624A (en) * | 2013-12-20 | 2014-05-07 | 中原工学院 | Fabric defect detection method based on optical threshold segmentation |
| CN106780464A (en) * | 2016-12-15 | 2017-05-31 | 东华大学 | A kind of fabric defect detection method based on improvement Threshold segmentation |
Non-Patent Citations (1)
| Title |
|---|
| 赵小川: "《现代数字图像处理技术提高及应用案例详解 MATLAB版》", vol. 2012, 北京航空航天大学出版社, pages: 221 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419037A (en) * | 2022-03-28 | 2022-04-29 | 江苏智云天工科技有限公司 | Workpiece defect detection method and device |
| CN114627111A (en) * | 2022-05-12 | 2022-06-14 | 南通英伦家纺有限公司 | Textile defect detection and identification device |
| CN114627111B (en) * | 2022-05-12 | 2022-07-29 | 南通英伦家纺有限公司 | Textile defect detection and identification device |
| CN116152230A (en) * | 2023-04-17 | 2023-05-23 | 江苏华拓纺织科技有限公司 | Textile surface dyeing quality detection method based on spectrum data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113820319A (en) | Textile surface defect detection device and method | |
| CN109454006B (en) | Detection and classification method based on device for online detection and classification of chemical fiber spindle tripping defects | |
| US10041888B2 (en) | Surface defect inspecting device and method for hot-dip coated steel sheets | |
| KR20190128049A (en) | System and associated method for on-line detection of micro defects on / on glass sheet | |
| EP1580691A2 (en) | Automatic adjustment of acquisition of inspection image | |
| US10607333B2 (en) | Real-time, full web image processing method and system for web manufacturing supervision | |
| CN109856164B (en) | Optimization device for acquiring large-range images by machine vision and detection method thereof | |
| JP4633245B2 (en) | Surface inspection apparatus and surface inspection method | |
| CN110567968A (en) | part defect detection method and device | |
| CN113034488A (en) | Visual detection method of ink-jet printed matter | |
| CN112950541A (en) | Synthetic leather gluing online monitoring method based on machine vision | |
| SE528526C2 (en) | Method and apparatus for optical evaluation of a paper surface | |
| CN110402386B (en) | Cylindrical body surface inspection device and cylindrical body surface inspection method | |
| JP2012251983A (en) | Wrap film wrinkle inspection method and device | |
| JP2008249413A (en) | Defect detection method and device | |
| CN116087208A (en) | Plastic product detecting system based on image recognition | |
| CN115343313A (en) | Visual identification method based on artificial intelligence | |
| JP2008146432A (en) | Method of detecting mark | |
| JP4820971B2 (en) | Surface inspection method | |
| JP2003156451A (en) | Defect detecting device | |
| JP5949690B2 (en) | Evaluation method and evaluation apparatus | |
| JP2003329428A (en) | Device and method for surface inspection | |
| JP2021189238A (en) | Belt inspection system and belt inspection program | |
| JP2021006854A (en) | Belt inspection system and belt inspection program | |
| JP2001235319A (en) | Shading correcting apparatus and shading correcting method, and surface inspection apparatus |
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 |