CN115684176A - Online visual inspection system for film surface defects - Google Patents
Online visual inspection system for film surface defects Download PDFInfo
- Publication number
- CN115684176A CN115684176A CN202211302385.8A CN202211302385A CN115684176A CN 115684176 A CN115684176 A CN 115684176A CN 202211302385 A CN202211302385 A CN 202211302385A CN 115684176 A CN115684176 A CN 115684176A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- film
- area
- defect area
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 107
- 238000011179 visual inspection Methods 0.000 title claims abstract description 9
- 239000010408 film Substances 0.000 claims abstract description 84
- 238000001514 detection method Methods 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 23
- 239000010409 thin film Substances 0.000 claims abstract description 16
- 238000003709 image segmentation Methods 0.000 claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000002950 deficient Effects 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 230000008030 elimination Effects 0.000 claims 1
- 238000007689 inspection Methods 0.000 claims 1
- 239000000463 material Substances 0.000 description 13
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention provides an on-line visual inspection system for surface defects of a thin film. An online visual inspection system for film surface defects, comprising: the image acquisition module is used for acquiring an image to be detected of the film to be detected; the image conversion module is used for processing the image to be detected and converting the image to be detected into a gray image g (x, y); the image segmentation module is used for segmenting the image to be detected and removing a background part in the image to be detected; a defect detection module: the method is used for detecting the defects of the image to be detected. The method comprises the steps of collecting a film image in real time, carrying out noise reduction processing on the image, traversing the image by using square frames, calculating the mean value of gray values of pixel points in the square frames, comparing the mean value with a standard image to find out a suspected defect area, judging whether the suspected defect area is the defect area by adopting a similarity analysis method, finding out the position of a defect in the film image, and completing defect detection.
Description
Technical Field
The invention relates to the field of defect detection, in particular to an online visual detection system for surface defects of a thin film.
Background
In the production and processing processes of the film material, the prepared film material may have defects under the influence of factors such as process flow, workshop environment, machine performance and the like. The defective film material will have a great influence on the subsequent use and sale of the product, so that the defect detection of the film material is required after the production and processing of the film material are completed.
For the defect detection of the thin film material, a detection mode of manual detection is traditionally used, a lot of manpower and material resources are consumed, some tiny defects may not be detected completely in the detection process of manual detection, and the efficiency of detecting the defects of the thin film material by manual detection is low.
Disclosure of Invention
In order to solve the problems, the application provides an online visual inspection system for the surface defects of the thin film, which is used for shooting images of the thin film to be inspected in real time through an industrial CCD camera and detecting the defects of the thin film through an image processing technology, so that the defect detection efficiency of the thin film material is improved.
The technical scheme of the invention is as follows: an online visual inspection system for film surface defects, comprising:
the image acquisition module is used for acquiring an image to be detected of the film to be detected;
the image conversion module is used for processing the image to be detected and converting the image to be detected into a gray image g (x, y);
the image segmentation module is used for segmenting the image to be detected and removing a background part in the image to be detected;
a defect detection module: the image defect detection device is used for detecting defects of an image to be detected;
the image segmentation module removes the background part in the image to be detected to generate a film image g 1 (x,y)；
The defect detection of the image to be detected comprises the following steps:
for film image g 1 (x, y) performing noise reduction treatment to obtain a noise-reduced film image g 2 (x,y)；
Traversing the thin film image g subjected to noise reduction processing by using a square search box 2 (x, y) calculating the gray value level of pixel points in each search frame by taking the step length as the side length of the search frameAverage value, using normal film image as standard image, calculating film image g after noise reduction treatment 2 (x, y) the difference value of the gray value average values of the pixel points in the search frame at the same position as the standard image; the difference value is larger than the threshold value Q 1 The area is marked as a suspected defect area, otherwise, the area is marked as a normal area, and the suspected defect area is merged and eliminated to obtain a film image g 3 (x,y)；
And analyzing the similarity between the suspected defect area and the area at the same position of the standard image to obtain the accurate position of the defect area.
Further, segmenting the image to be detected includes:
according to the formula
Wherein T is a segmentation threshold, converting the image into a black-and-white image s (x, y) to obtain a contour image of the film, and removing the background to obtain a film image g 1 (x,y)。
Further, the pair of film images g 1 (x, y) performing noise reduction processing includes:
removing noise in the image by using an average filter, and performing filtering processing by using a convolution kernel of 3 x 3 to obtain a thin film image g subjected to noise reduction processing 2 (x, y), film image g 1 The size of (x, y) is NxN, and the expression is satisfied
Further, the defect detection of the image to be detected further comprises:
traversing the thin film image g subjected to noise reduction processing by using the square search box and taking the side length of the search box as a step length 2 (x, y), calculating the gray value average value of the pixel points in each search frame, and generating a gray value average value matrix G 2 ；
The expression of the gray value average value h of the pixel points in the search frame is as follows:
in the formula (I), the compound is shown in the specification,i is the serial number of the pixel points in the search box, h i The gray value corresponding to the ith pixel point in the search frame is obtained;
traversing the film image g of the standard image by using the square search box and taking the side length of the search box as the step length 2 (x, y), calculating the gray value average value of the pixel points in each search frame, and generating a gray value average value matrix G 1 ；
Difference Δ h of gray value average value, expression Δ h = | G 1j -G 2j In the formula, j is G 1 And G 2 Number of terms of (G) 1j 、G 2j Each represents G 1 And G 2 The gray value average value of the pixel points in the search frame corresponding to the jth item;
make the difference value of deltah larger than the threshold value Q 1 The area is marked as a suspected defect area, otherwise, the area is marked as a normal area, and the suspected defect area is merged and eliminated to obtain a film image g 3 (x,y)。
Further, the merging and elimination process for the suspected defect areas includes:
traversing the film image g with a square search box with the side length of the search box 2 (x, y) if film image g 2 And (x, y) any suspected defect area exists in the 4 square search boxes in the four directions of the upper, the lower, the left and the right, which are adjacent to each other, and the suspected defect area does not need to be processed, otherwise, the suspected defect area is marked as a normal area.
Further, analyzing the similarity between the suspected defect area and the same-position area of the standard image includes:
image g of the film 3 (x, y) converting the image into a vector matrix to obtain a target vector to be detected corresponding to a suspected defect area with an adjacent relation;
converting the standard image into a vector matrix to obtain a standard vector corresponding to a region at the same position as a suspected defective region with an adjacent relation;
analyzing the similarity between a target vector to be detected and a standard vector by two methods, judging whether a suspected defect area is a defect area according to an analysis result, and if the analysis result of any one of the two methods is that the suspected defect area is judged to belong to the defect area, determining that the suspected defect area is the defect area, otherwise, determining that the suspected defect area is a normal area;
two methods for analyzing the similarity between the target vector to be detected and the standard vector are to analyze the similarity between the target vector to be detected and the standard vector by adopting a generalized Jackson similarity coefficient and a Pearson correlation coefficient.
Further, still include:
calculating generalized Jeld similarity coefficients between a target vector to be detected and a standard vector, if the absolute value of the generalized Jeld similarity coefficient corresponding to a certain region is smaller than a first preset coefficient, judging that the region belongs to a defect region, and if not, judging that the region belongs to a normal region;
and calculating a Pearson correlation coefficient between the target vector to be detected and the standard vector, if the absolute value of the Pearson correlation coefficient corresponding to a certain area is smaller than a second preset coefficient, judging that the area belongs to the defect area, and otherwise, judging that the area belongs to the normal area.
Further, the film image g is processed 1 Before the noise reduction processing is performed on (x, y), the film image g is subjected to 1 (x, y) performing local feature enhancement processing:
after filtering processing is carried out by using a convolution kernel of 3 x 3, the mean value E of the gray values of the pixel points in each 3 x 3 frame is calculated 1 And calculating the film image g at the same position 1 Mean value E of gray values of pixel points in 3 x 3 frames in (x, y) 2 If E is 2 -E 1 >Q 2 ，Q 2 And if the position is the enhancement threshold, enhancing the position, otherwise, not enhancing.
The invention has the following advantages:
1. the film image is collected in real time, noise reduction processing is carried out on the image, the image is traversed by using square frames, the mean value of gray values of pixel points in the square frames is calculated, the mean value is compared with a standard image to find out a suspected defect area, a similarity analysis method is adopted to judge whether the suspected defect area is the defect area, the position of the defect in the film image is found out, and defect detection is completed.
2. And the similarity analysis is carried out by the generalized Jacobian similarity coefficient and the Pearson correlation coefficient at the same time, so that the judgment of whether the suspected defect area is the defect area is more accurate.
3. The local feature enhancement processing is carried out before the noise reduction processing is carried out on the image, so that the influence brought by the noise reduction processing is reduced, and meanwhile, the image distortion is prevented from influencing the final detection effect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an online visual inspection system for film surface defects according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, some embodiments of the present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. However, it will be appreciated by those of ordinary skill in the art that in various embodiments of the application, numerous technical details are set forth in order to provide a better understanding of the application. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
Example 1
Referring to fig. 1, embodiment 1 of the present invention provides an online visual inspection system for surface defects of a thin film, including:
the image acquisition module is used for acquiring an image to be detected of the film to be detected, is configured to be an industrial CCD camera, and acquires the image to be detected of the film to be detected in real time;
conveying the film material to be detected to a shooting area of a CCD camera through a conveying belt, and acquiring a real-time image by using the CCD camera to obtain an image to be detected;
the image conversion module is used for processing the image to be detected and converting the image to be detected into a gray image;
the image segmentation module is used for segmenting an image to be detected, determining a region to be detected by adopting an image segmentation algorithm based on a gray image, and removing a background part in the image to be detected to obtain a gray image of the region to be detected;
a defect detection module: the method is used for detecting the defects of the image to be detected.
The image segmentation module comprises the following steps of:
generating a gray level histogram according to a gray level image corresponding to an image to be detected, and determining a segmentation threshold value T;
the method comprises the steps that a film material to be detected is transmitted to a shooting area through a conveyor belt, the area where the film material is located and a background area can be obviously distinguished from an image obtained through shooting, a gray level histogram generated based on a gray level image has a double peak characteristic, and a gray level corresponding to a valley between the double peaks is taken as a segmentation threshold value T;
determining a target area where the film is located through image segmentation, and removing the background to obtain a film image;
setting the image obtained by shooting as g (x, y) according to a formula
Converting the image into a black-and-white image s (x, y), obtaining a target area where the film is located in the shot image, and removing the background to obtain a film image g 1 (x,y)。
Defect detection module to film image g 1 (x, y) the process of performing defect detection includes:
for film image g 1 (x, y) performing noise reduction treatment;
setting up a film image g 1 Size N of (x, y), removing noise in image by mean filter, and reducing noiseNoise-treated film image g 2 (x, y) is expressed as:
in this embodiment, the filtering process is performed with a convolution kernel of 3 × 3.
In the process of acquiring the film image through the CCD camera, the film image is influenced by factors such as sensor materials, image acquisition environment and the like, the acquired film image has various noises, the detection result is influenced in the process of defect detection, the detection precision is reduced, and the accuracy of defect detection can be improved by adopting a mean value filter for noise reduction.
Traversing the image by using a square search box and taking the side length l of the search box as a step length, and calculating a gray value average value;
taking the film image without defects as a standard image, traversing the gray level image of the standard image by using a square search frame and taking the side length l of the search frame as a step length, calculating the gray level average value of pixel points in the search frame, and generating a gray level average value matrix G of the standard image 1 。
The expression of the gray value average value h of the pixel points in the search frame is as follows:
where i is the serial number of the pixel in the search box, h i And the gray value corresponding to the ith pixel point in the search frame.
Traversing the thin film image g subjected to noise reduction processing by using a square search box and taking the side length l of the search box as a step length 2 The gray image of (x, y) adopts the expression of the gray value average value h of the pixel points in the search frame to generate a film image g 2 Matrix G of mean values of the grey values of (x, y) 2 。
Gray value average value matrix G for standard image 1 And film image g 2 Matrix G of mean values of the grey values of (x, y) 2 Processing to obtain suspected existenceA defective region;
according to G 1 And G 2 Calculating the standard image and the film image g 2 (x, y) the difference value delta h of the gray value average values of the pixel points in the same position search frame, wherein:
Δh＝|G 1j -G 2j |
wherein j is G 1 And G 2 Number of items of (G) 1j 、G 2j Each represents G 1 And G 2 The gray value average value of the pixel points in the search frame corresponding to the jth item, namely the standard image and the film image g 2 (x, y) searching the average value of the gray values of the pixel points in the frame at the same position.
By comparing the difference Δ h with a defect detection threshold Q 1 Determining whether the position corresponding to the search box is a suspected defect area, if the difference value deltah is greater than the threshold value Q 1 The area is marked as suspected to be defective, otherwise the area is marked as normal.
Merging or removing the suspected defect areas;
traversing the film image g by using a square search box and taking the side length l of the search box as a step length 2 (x, y) for film image g 2 If any suspected defect area exists in 4 square search boxes in the four directions of (x, y), the suspected defect area is not processed, otherwise, the suspected defect area is marked as a normal area, and the square search boxes are used for traversing the film image g 2 (x, y) then, the non-adjacent suspected defective areas are subjected to a film image g consisting of the normal area and the suspected defective areas in an adjacent relationship 3 (x,y)。
A film image g consisting of a normal area and a suspected defective area in an adjacent relationship 3 (x, y) is converted into a vector matrix, a target vector to be detected corresponding to a suspected defect area with an adjacent relation is obtained, the standard image is converted into the vector matrix, a standard vector corresponding to an area at the same position as the suspected defect area with the adjacent relation is obtained, and the similarity between the target vector to be detected and the standard vector is analyzed to determine the film image g 3 (xAnd y) judging whether the suspected defect area is a defect area, specifically including:
and analyzing the similarity between the target vector to be detected and the standard vector by two methods, and judging whether the suspected defective area is a defective area or not by combining the analysis results of the two methods.
The first method adopts a generalized Jackside similarity coefficient to measure the similarity between a target vector to be detected and a standard vector, and the second method adopts a Pearson correlation coefficient to measure the similarity between the target vector to be detected and the standard vector.
The generalized Jacobian coefficient of similarity expression is as follows:
in the formula, J (A, B) represents a generalized Jacobian similarity coefficient, A represents a target vector to be detected, and A = a 1 ，a 2 ，…，a k B is expressed as a normal vector, B = B 1 ，b 2 ，…，b k And k represents the number of terms of the standard vector and the target vector to be detected.
And if the absolute value of the generalized Jacobian similarity coefficient corresponding to a certain region is smaller than a first preset coefficient, judging that the region belongs to a defect region, otherwise, judging that the region belongs to a normal region.
The pearson correlation coefficient expression is as follows:
in the formula, P (a, B) represents a pearson correlation coefficient, a represents an object vector to be detected, and a = a 1 ，a 2 ，…，a k ，BExpressed as a normal vector, B = B 1 ，b 2 ，…，b k K represents the number of terms of the standard vector and the target vector to be detected, and n represents the total amount of samples.
And calculating a Pearson correlation coefficient between the target vector to be detected and the standard vector, if the absolute value of the Pearson correlation coefficient corresponding to a certain area is smaller than a second preset coefficient, judging that the area belongs to a defect area, otherwise, judging that the area belongs to a normal area, finally obtaining the position of the defect in the film image to be detected, and finishing the detection of the surface defect of the film.
In the above, the first predetermined coefficient and the second predetermined coefficient are artificially set for the film image g 1 (x, y) performing noise reduction processing, which may cause loss of image details, in an optional embodiment, the influence caused by the noise reduction processing may be reduced by performing feature enhancement on the image, specifically, performing feature enhancement on a local area of the image before performing noise reduction processing on the image, and the area confirmation method that needs to perform feature enhancement is:
after filtering processing is carried out by using a convolution kernel of 3 x 3, the mean value E of pixel points in each 3 x 3 frame is calculated 1 And calculating the film image g at the same position 1 Mean E of pixel points in 3 x 3 boxes in (x, y) 2 If E is 2 -E 1 >Q 2 Then the location is enhanced, otherwise no enhancement is performed, where Q 2 To enhance the threshold, the threshold is set empirically by a human.
The image characteristic enhancement is completed by selecting a proper area to carry out image local characteristic enhancement processing, so that the influence brought by noise reduction processing is reduced, and meanwhile, the image distortion is prevented, and the final detection effect is influenced.
Those skilled in the art can understand that all or part of the solutions in the methods of the foregoing embodiments are implemented, and each module in the embodiments of the present invention may be integrated into a whole, or may exist alone.
It will be appreciated that modifications and variations are possible to those skilled in the art in light of the above teachings, and it is intended to cover all such modifications and variations as fall within the scope of the appended claims. Parts of the description that are not described in detail are known to the person skilled in the art.
Claims (8)
1. An online visual inspection system for film surface defects, comprising:
the image acquisition module is used for acquiring an image to be detected of the film to be detected;
the image conversion module is used for processing the image to be detected and converting the image to be detected into a gray image g (x, y);
the image segmentation module is used for segmenting the image to be detected and removing a background part in the image to be detected;
a defect detection module: the image defect detection device is used for detecting defects of an image to be detected;
the image segmentation module removes the background part in the image to be detected to generate a film image g 1 (x,y)；
The defect detection of the image to be detected comprises the following steps:
for film image g 1 (x, y) performing noise reduction treatment to obtain a noise-reduced film image g 2 (x,y)；
Traversing the thin film image g subjected to noise reduction processing by using a square search box 2 (x, y) the step length is the side length of the search frame, the average value of the gray values of the pixel points in each search frame is calculated, the normal film image is used as a standard image, and the film image g after noise reduction processing is calculated 2 (x, y) the difference value of the gray value average values of the pixel points in the search frame at the same position as the standard image; the difference value is greater than a threshold value Q 1 Marking the area as a suspected defect area, otherwise marking the area as a normal area, merging and eliminating the suspected defect area to obtain a film image g 3 (x,y)；
And analyzing the similarity between the suspected defect area and the area at the same position of the standard image to obtain the accurate position of the defect area.
2. The system of claim 1, wherein the segmenting the image to be detected comprises:
according to the formula
Wherein T is a segmentation threshold, converting the image into a black-and-white image s (x, y) to obtain a contour image of the film, and removing the background to obtain a film image g 1 (x,y)。
3. The system of claim 1, wherein the film image g is processed by a vision inspection system 1 (x, y) performing noise reduction processing includes:
removing noise in the image by using an average filter, and performing filtering processing by using a convolution kernel of 3-by-3 to obtain a thin film image g subjected to noise reduction processing 2 (x, y), film image g 1 The size of (x, y) is NxN, and the expression is satisfied
4. The system of claim 1, wherein the step of detecting the defects of the image to be detected further comprises:
traversing the thin film image g subjected to noise reduction processing by using the side length of the square search box as a step length 2 (x, y), calculating the gray value average value of the pixel points in each search frame, and generating a gray value average value matrix G 2 ；
The expression of the gray value average value h of the pixel points in the search frame is as follows:
in the formula, i is the serial number of the pixel point in the search frame, and hi is the gray value corresponding to the ith pixel point in the search frame;
traversing the film image g of the standard image by using the square search box and taking the side length of the search box as the step length 2 (x, y), calculating the gray value average value of the pixel points in each search frame, and generating the gray value average momentArray G 1 ；
Difference Δ h of gray value average value, expression Δ h = | G 1j -G 2j In the formula, j is G 1 And G 2 Number of items of (G) 1j 、G 2j Each represents G 1 And G 2 The gray value average value of the pixel points in the search frame corresponding to the jth item; make the difference value of deltah larger than the threshold value Q 1 The area is marked as a suspected defect area, otherwise, the area is marked as a normal area, and the suspected defect area is merged and eliminated to obtain a film image g 3 (x,y)。
5. The system of claim 1, wherein the merging and elimination of suspected defect areas comprises:
traversing the film image g with a square search box with the search box side length 2 (x, y) if film image g 2 And (4) any suspected defect area in the (x, y) is not processed if the suspected defect area exists in the 4 square search frames in the adjacent four directions, namely the upper direction, the lower direction, the left direction and the right direction, and if the suspected defect area does not exist in the (x, y) any suspected defect area, the suspected defect area is marked as a normal area.
6. The system of claim 1, wherein analyzing the similarity between the suspected defect area and the same location area of the standard image comprises:
image g of the film 3 (x, y) converting the image into a vector matrix to obtain a target vector to be detected corresponding to a suspected defect area with an adjacent relation;
converting the standard image into a vector matrix to obtain a standard vector corresponding to a region at the same position as a suspected defective region with an adjacent relation;
analyzing the similarity between a target vector to be detected and a standard vector by two methods, judging whether a suspected defect area is a defect area according to an analysis result, and if the suspected defect area is judged to belong to the defect area by one of the two methods, determining that the suspected defect area is the defect area, otherwise, determining that the suspected defect area is a normal area;
the two methods for analyzing the similarity between the target vector to be detected and the standard vector are to analyze the similarity between the target vector to be detected and the standard vector by adopting a generalized Jackson similarity coefficient and a Pearson correlation coefficient.
7. The system of claim 6, further comprising:
calculating generalized Jeld similarity coefficients between a target vector to be detected and a standard vector, if the absolute value of the generalized Jeld similarity coefficient corresponding to a certain region is smaller than a first preset coefficient, judging that the region belongs to a defect region, and if not, judging that the region belongs to a normal region;
and if the absolute value of the Pearson correlation coefficient corresponding to a certain region is smaller than a second preset coefficient, judging that the region belongs to a defect region, otherwise, judging that the region belongs to a normal region.
8. The system of claim 3, further comprising:
in the film image g 1 Before the noise reduction processing is performed on (x, y), the film image g is subjected to 1 (x, y) performing local feature enhancement processing:
after filtering processing is carried out by using a convolution kernel of 3 x 3, the mean value E of the gray values of the pixel points in each 3 x 3 frame is calculated 1 And calculating the film image g at the same position 1 Mean value E of gray values of pixel points in 3 x 3 frames in (x, y) 2 If E is 2 -E 1 >Q 2 ，Q 2 And if the position is the enhancement threshold, enhancing the position, otherwise, not enhancing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211302385.8A CN115684176B (en) | 2022-10-24 | Online visual detection system for film surface defects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211302385.8A CN115684176B (en) | 2022-10-24 | Online visual detection system for film surface defects |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115684176A true CN115684176A (en) | 2023-02-03 |
| CN115684176B CN115684176B (en) | 2024-07-12 |
Family
ID=
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958070A (en) * | 2023-07-06 | 2023-10-27 | 钛玛科（北京）工业科技有限公司 | Lithium-ion-based coating process wave edge detection system and method |
| CN116973367A (en) * | 2023-07-05 | 2023-10-31 | 广东汇发塑业科技有限公司 | Method for inspecting degradation defect position of biodegradable film |
| CN116985444A (en) * | 2023-07-05 | 2023-11-03 | 广东汇发塑业科技有限公司 | Traction method for improving transmittance in degradation process of biodegradable film |
| CN116993718A (en) * | 2023-09-25 | 2023-11-03 | 深圳市东陆科技有限公司 | TFT array substrate defect detection method based on machine vision |
| CN117291916A (en) * | 2023-11-24 | 2023-12-26 | 深圳市润海电子有限公司 | Polyimide film surface detection method and system based on machine vision |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170004612A1 (en) * | 2015-07-03 | 2017-01-05 | Yuan Ze University | Optical film defect detection method and system thereof |
| CN112070710A (en) * | 2019-06-10 | 2020-12-11 | 北京平恒智能科技有限公司 | Method for detecting industrial product defect image |
| CN113252695A (en) * | 2021-06-16 | 2021-08-13 | 上海启迪睿视智能科技有限公司 | Plastic packaging film defect detection method and detection device based on image processing |
| CN113947598A (en) * | 2021-12-20 | 2022-01-18 | 昌亚新材料科技有限公司 | Plastic lunch box defect detection method, device and system based on image processing |
| CN114627111A (en) * | 2022-05-12 | 2022-06-14 | 南通英伦家纺有限公司 | Textile defect detection and identification device |
| CN114627117A (en) * | 2022-05-13 | 2022-06-14 | 启东市鸿盛纺织有限公司 | Knitted fabric defect detection method and system based on projection method |
| CN114742749A (en) * | 2022-02-27 | 2022-07-12 | 扬州盛强薄膜材料有限公司 | PVC film quality detection method based on image processing |
| CN114913365A (en) * | 2022-04-22 | 2022-08-16 | 海门王巢家具制造有限公司 | Artificial board quality classification method and system based on machine vision |
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170004612A1 (en) * | 2015-07-03 | 2017-01-05 | Yuan Ze University | Optical film defect detection method and system thereof |
| CN112070710A (en) * | 2019-06-10 | 2020-12-11 | 北京平恒智能科技有限公司 | Method for detecting industrial product defect image |
| CN113252695A (en) * | 2021-06-16 | 2021-08-13 | 上海启迪睿视智能科技有限公司 | Plastic packaging film defect detection method and detection device based on image processing |
| CN113947598A (en) * | 2021-12-20 | 2022-01-18 | 昌亚新材料科技有限公司 | Plastic lunch box defect detection method, device and system based on image processing |
| CN114742749A (en) * | 2022-02-27 | 2022-07-12 | 扬州盛强薄膜材料有限公司 | PVC film quality detection method based on image processing |
| CN114913365A (en) * | 2022-04-22 | 2022-08-16 | 海门王巢家具制造有限公司 | Artificial board quality classification method and system based on machine vision |
| CN114627111A (en) * | 2022-05-12 | 2022-06-14 | 南通英伦家纺有限公司 | Textile defect detection and identification device |
| CN114627117A (en) * | 2022-05-13 | 2022-06-14 | 启东市鸿盛纺织有限公司 | Knitted fabric defect detection method and system based on projection method |
Non-Patent Citations (1)
| Title |
|---|
| 陈琦 等: "基于机器视觉的滑动轴承缺陷检测***设计", 组合机床与自动化加工技术, no. 05, 20 May 2017 (2017-05-20), pages 92 - 95 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116973367A (en) * | 2023-07-05 | 2023-10-31 | 广东汇发塑业科技有限公司 | Method for inspecting degradation defect position of biodegradable film |
| CN116985444A (en) * | 2023-07-05 | 2023-11-03 | 广东汇发塑业科技有限公司 | Traction method for improving transmittance in degradation process of biodegradable film |
| CN116973367B (en) * | 2023-07-05 | 2024-01-30 | 广东汇发塑业科技有限公司 | Method for inspecting degradation defect position of biodegradable film |
| CN116985444B (en) * | 2023-07-05 | 2024-04-02 | 广东汇发塑业科技有限公司 | Traction method for improving transmittance in degradation process of biodegradable film |
| CN116958070A (en) * | 2023-07-06 | 2023-10-27 | 钛玛科（北京）工业科技有限公司 | Lithium-ion-based coating process wave edge detection system and method |
| CN116993718A (en) * | 2023-09-25 | 2023-11-03 | 深圳市东陆科技有限公司 | TFT array substrate defect detection method based on machine vision |
| CN116993718B (en) * | 2023-09-25 | 2023-12-22 | 深圳市东陆科技有限公司 | TFT array substrate defect detection method based on machine vision |
| CN117291916A (en) * | 2023-11-24 | 2023-12-26 | 深圳市润海电子有限公司 | Polyimide film surface detection method and system based on machine vision |
| CN117291916B (en) * | 2023-11-24 | 2024-02-02 | 深圳市润海电子有限公司 | Polyimide film surface detection method and system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107490582B (en) | Assembly line workpiece detection system | |
| CN107478657A (en) | Stainless steel surfaces defect inspection method based on machine vision | |
| CN111369516B (en) | Transformer bushing heating defect detection method based on infrared image recognition | |
| CN115760654B (en) | Industrial microscope image processing system | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN112669265B (en) | Method for realizing surface defect detection based on Fourier transform and image gradient characteristics | |
| CN112258444A (en) | Elevator steel wire rope detection method | |
| Daniel et al. | Automatic road distress detection and analysis | |
| Tang et al. | Surface inspection system of steel strip based on machine vision | |
| Fu et al. | Research on image-based detection and recognition technologies for cracks on rail surface | |
| CN114332081A (en) | Textile surface abnormity determination method based on image processing | |
| Dang et al. | A novel method for detecting weld defects accurately and reliably in radiographic images | |
| CN115684176B (en) | Online visual detection system for film surface defects | |
| CN115684176A (en) | Online visual inspection system for film surface defects | |
| CN116381053A (en) | Ultrasonic detection method and system for welding metal materials | |
| CN114638822B (en) | Method and system for detecting surface quality of automobile cover plate by using optical means | |
| CN114354631A (en) | Valve blank surface defect detection method based on vision | |
| CN112785594B (en) | Automatic bridge structure crack identification method based on image two-dimensional amplitude estimation | |
| CN111062939B (en) | Method for rapidly screening quality of strip steel surface and automatically extracting defect characteristics | |
| CN114004812A (en) | Threaded hole detection method and system adopting guide filtering and neural network model | |
| CN112508908B (en) | Method for detecting disconnection fault of sanding pipe joint of motor train unit based on image processing | |
| CN111476779B (en) | Sawn timber surface defect position positioning method and sawn timber surface defect position positioning system | |
| Qi et al. | On-line detection of Hami big jujubes' size and shape based on machine vision | |
| Nandhitha et al. | A comparative study on the performance of the classical and wavelet based edge detection for image denoising on defective weld thermographs | |
| Liu | Defect detection method of product appearance design based on visual communication model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |