CN112651923A - Adhesive film wrinkle defect detection method capable of removing fine residues based on area ratio - Google Patents
Adhesive film wrinkle defect detection method capable of removing fine residues based on area ratio Download PDFInfo
- Publication number
- CN112651923A CN112651923A CN202011256012.2A CN202011256012A CN112651923A CN 112651923 A CN112651923 A CN 112651923A CN 202011256012 A CN202011256012 A CN 202011256012A CN 112651923 A CN112651923 A CN 112651923A
- Authority
- CN
- China
- Prior art keywords
- adhesive film
- area
- wrinkle
- fine white
- fine
- 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
- 230000037303 wrinkles Effects 0.000 title claims abstract description 83
- 239000002313 adhesive film Substances 0.000 title claims abstract description 78
- 230000007547 defect Effects 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 title abstract description 17
- 239000000463 material Substances 0.000 claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000011218 segmentation Effects 0.000 claims abstract description 11
- 230000000877 morphologic effect Effects 0.000 claims description 12
- 239000000284 extract Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims 3
- 210000002268 wool Anatomy 0.000 abstract 2
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 230000001795 light effect Effects 0.000 abstract 1
- 238000005286 illumination Methods 0.000 description 4
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 210000004209 hair Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 208000030533 eye disease Diseases 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge 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
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of defect detection, in particular to an adhesive film wrinkle defect detection method for removing fine residues based on an area ratio. The adhesive film products generally have strong light reflection characteristics, so that coaxial light is used as a light source for wrinkle defect detection, the light reflection is reduced, and wrinkle defects are highlighted. Through the test of different color light sources, the red coaxial light effect is optimal. The invention adopts red coaxial light to shoot a picture of the adhesive film, fine white plastic wool which interferes with wrinkle defect detection exists on the surface of the adhesive film, and the fine white plastic wool is caused by the fact that a die-cutting machine is not cut cleanly and belongs to material residues. The fine white material residue is not a defect, but it is also extracted by the adaptive threshold segmentation method. Because the area of the bright part of the fine white residual material exceeds 90 percent of the area of the connected domain where the fine white residual material is located, the invention provides the method for detecting the wrinkle defect of the adhesive film based on the area ratio to remove the fine residual material, the connected domain where the fine white residual material is located is removed, and only the connected domain where the wrinkle is located is reserved. The interference of tiny white residual materials is avoided, and the adhesive film wrinkles are accurately detected.
Description
Technical Field
The invention relates to the technical field of defect detection, in particular to an adhesive film wrinkle defect detection method for removing fine residues based on an area ratio.
Background
The adhesive film product has wide application in the electronic industry, various varieties, different shapes and various defect types. The detection of the product quality is difficult in the industry at present, the wrinkle is one of the defects of the products, and the market has great demands on the automation and the intellectualization of the wrinkle defect detection of the adhesive film.
At present, most of the detection of the wrinkle defects of the adhesive film is judged by human eyes, and the wrinkle defects of the thin adhesive film are difficult to see by human eyes. The slight wrinkle defect can be found only by a worker carefully looking at the adhesive film under the light while changing the angle. The adhesive film on a roll of product has thousands of sheets, and the time consumption is very large when the film is judged by human eyes. And the light has certain injury to human eyes, and long-term detection of defects by the light can cause eye diseases.
The method for detecting the wrinkle defect of the adhesive film by removing the small residues based on the area ratio can meet the requirements of automation and intellectualization. The method solves the problem of wrinkle defect detection of hundreds of thousands of adhesive films every day, improves the efficiency and increases the benefit.
Disclosure of Invention
The invention aims to provide an adhesive film wrinkle defect detection method based on area ratio for removing fine residues, aiming at overcoming the defect of the prior art and the industrial requirement, solving the problem of industrial pain caused by judging hundreds of thousands of adhesive film defects by human eyes every day, realizing automatic and intelligent detection and improving the efficiency.
In order to achieve the above object, the present invention relates to a method for detecting wrinkle defects of an adhesive film with fine residues removed based on an area ratio, comprising the steps of:
step 1: taking red coaxial light as a light source, and obtaining an adhesive film picture with a wrinkle defect, wherein the picture is a single-channel gray scale image;
step 2: the method for detecting the wrinkle defect of the adhesive film extracts an interested area comprising wrinkles, fine white residual materials and the outline of the adhesive film;
and step 3: according to the method for detecting the wrinkle defect of the adhesive film, the outline of the adhesive film is removed, and only wrinkle and fine white residual material areas are reserved;
and 4, step 4: the method for detecting the wrinkle defect of the adhesive film extracts wrinkles and rejects fine white residual materials.
Further, in the step 2:
step 2.1: performing edge extraction on the adhesive film picture with the wrinkle defect through a sobel operator, wherein the sobel operator can identify a part with pixel mutation, namely three interested areas, namely wrinkles, fine white residual materials and the adhesive film outline;
step 2.2: and (3) carrying out binarization on the gray-scale image obtained in the step (2.1) to obtain a binary image of three parts, namely folds, fine white residual materials and the contour of the adhesive film.
Step 2.3: and (3) performing morphological opening operation on the binary image obtained in the step (2.2), and using a circular template with the radius of 1 pixel to remove interference pixel points.
Further, in the step 3:
step 3.1: and (3) performing fixed threshold segmentation on the adhesive film gray-scale image with the wrinkle defect obtained in the step (1), and removing a background area to obtain a binary image of the adhesive film area.
Step 3.2: and (3) performing morphological corrosion operation on the binary image obtained in the step (3.1), and corroding the edge part of the adhesive film binary image by adopting a circular template with the radius of 7 pixels.
Step 3.3: the binary image obtained in step 2 contains three parts, namely wrinkles, fine white residue material and adhesive film contour, and the binary image obtained in step 3.2 is the adhesive film area with the edge contour removed. And (3) taking an intersection of the two, removing the adhesive film outline in the step (2), and reserving wrinkles and fine white residual material areas.
Further, in the step 4:
step 4.1: step 3 obtains a binary image of two regions, namely, a wrinkle region and a fine white residual material region, and inevitably, other pixel regions which are not removed in step 2.3 exist, but the regions have small areas and are removed through the areas.
Step 4.2: and (4) performing morphological closed operation on the binary image obtained in the step (4.1) to enable discrete wrinkle regions to be connected to form a connected domain with a larger area.
Step 4.3: and (4) taking the binary area obtained in the step (4.2) as a template, and reducing the area of the single-channel gray original image obtained in the step (1) to obtain a gray image only containing wrinkles and fine white residual materials.
Step 4.4: and (4) carrying out dynamic threshold segmentation on the gray-scale image obtained in the step (4.3) to obtain a bright-color part. The area of the bright part of the fine white residual material exceeds 90% of the area of the connected domain where the fine white residual material is located, the connected domain where the fine white residual material is located is removed through the area ratio, and only the connected domain where the wrinkles are located is reserved.
Step 4.5: and (4) taking the binary area obtained in the step (4.4) as a template, and reducing the area of the single-channel gray original image obtained in the step (1) to obtain a gray image only with a wrinkle area.
The invention has the advantages that:
the method avoids the interference of fine white residual materials and accurately detects the folds of the adhesive film. Because the common fixed threshold segmentation method has very high requirement on the uniformity of light source illumination, the edge and the central area of an image obtained by a red coaxial light source have gray level difference of more than 10 pixels, and the wrinkle gray level is closer to the background. The method is superior to the common fixed threshold segmentation method, and can adapt to certain illumination nonuniformity.
Drawings
FIG. 1 is a flow chart of the operation of the present invention;
FIG. 2 is a flow chart of removing adhesive film profiles;
FIG. 3 is a flow chart of fine white residue removal;
FIG. 4 is a gray scale view of an adhesive film;
FIG. 5 is an enlarged view of a portion of FIG. 4 with a fine white residue, wrinkles;
FIG. 6 is a diagram showing the results of sobel edge extraction;
FIG. 7 is the binarized map of FIG. 6;
FIG. 8 is a graph of the morphological open operation result of FIG. 7;
FIG. 9 is the global binary map of FIG. 4;
FIG. 10 is a graph of the morphological erosion results of FIG. 9;
FIG. 11 is a graph of the intersection result of FIGS. 8 and 10;
FIG. 12 is a graph showing the result of the morphological close operation of FIG. 11;
FIG. 13 is an enlarged view of FIG. 4 with a domain reduction of the extent of FIG. 12;
FIG. 14 is a graph of the result of the area ratio of the bright area;
fig. 15 is a graph of wrinkles obtained from the area ratio of fig. 14.
Detailed Description
The invention will be further described with reference to the following drawings and specific examples, which are not intended to limit the invention thereto.
Referring to fig. 1 to 3, a method for detecting wrinkle defects of an adhesive film with fine residues removed based on an area ratio includes the following steps:
step 1: taking red coaxial light as a light source, and obtaining an adhesive film picture with a wrinkle defect, wherein the picture is a single-channel gray scale image;
step 2: the method for detecting the wrinkle defect of the adhesive film extracts an interested area comprising wrinkles, fine white residual materials and the outline of the adhesive film;
step 2.1: performing edge extraction on the adhesive film picture with the wrinkle defect through a sobel operator, wherein the sobel operator can identify a part with pixel mutation, namely three interested areas, namely wrinkles, fine white residual materials and the adhesive film outline;
step 2.2: and (3) carrying out binarization on the gray-scale image obtained in the step (2.1) to obtain a binary image of three parts, namely folds, fine white residual materials and the contour of the adhesive film.
Step 2.3: and (3) performing morphological opening operation on the binary image obtained in the step (2.2), and using a circular template with the radius of 1 pixel to remove interference pixel points.
And step 3: according to the method for detecting the wrinkle defect of the adhesive film, the outline of the adhesive film is removed, and only wrinkle and fine white residual material areas are reserved;
step 3.1: and (3) performing fixed threshold segmentation on the adhesive film gray-scale image with the wrinkle defect obtained in the step (1), and removing a background area to obtain a binary image of the adhesive film area.
Step 3.2: and (3) performing morphological corrosion operation on the binary image obtained in the step (3.1), and corroding the edge part of the adhesive film binary image by adopting a circular template with the radius of 7 pixels.
Step 3.3: the binary image obtained in step 2 contains three parts, namely wrinkles, fine white residue material and adhesive film contour, and the binary image obtained in step 3.2 is the adhesive film area with the edge contour removed. And (3) taking an intersection of the two, removing the adhesive film outline in the step (2), and reserving wrinkles and fine white residual material areas.
And 4, step 4: the method for detecting the wrinkle defect of the adhesive film extracts wrinkles and rejects fine white residual materials.
Step 4.1: step 3 obtains a binary image of two regions, namely, a wrinkle region and a fine white residual material region, and inevitably, other pixel regions which are not removed in step 2.3 exist, but the regions have small areas and are removed through the areas.
Step 4.2: and (4) performing morphological closed operation on the binary image obtained in the step (4.1) to enable discrete wrinkle regions to be connected to form a connected domain with a larger area.
Step 4.3: and (4) taking the binary area obtained in the step (4.2) as a template, and reducing the area of the single-channel gray original image obtained in the step (1) to obtain a gray image only containing wrinkles and fine white residual materials.
Step 4.4: and (4) carrying out dynamic threshold segmentation on the gray-scale image obtained in the step (4.3) to obtain a bright-color part. The area of the bright part of the fine white residual material exceeds 90% of the area of the connected domain where the fine white residual material is located, the connected domain where the fine white residual material is located is removed through the area ratio, and only the connected domain where the wrinkles are located is reserved.
Step 4.5: and (4) taking the binary area obtained in the step (4.4) as a template, and reducing the area of the single-channel gray original image obtained in the step (1) to obtain a gray image only with a wrinkle area.
FIGS. 4-5 show gray scale images of adhesive films, and their partial enlarged views, with fine white residue, wrinkle defects;
as shown in fig. 6 to 15, the actual picture of the processing process shown in fig. 2 to 3 is displayed, and a grayscale result graph with only wrinkle defects is finally obtained according to the area of the bright color part occupying the respective connected domain.
In conclusion, the invention discloses an area ratio-based adhesive film wrinkle defect detection method for removing fine residues, which is characterized in that a single-channel gray-scale image of an adhesive film with wrinkle defects is obtained by using a red coaxial light source, fine and white plastic hairs which interfere with wrinkle defect detection exist on the surface of the adhesive film, and the fine and white plastic hairs are caused by the fact that a die-cutting machine is not cut cleanly and belong to material residues. The method avoids the interference of the fine white residual materials and accurately detects the wrinkles of the adhesive film. Because the common fixed threshold segmentation method has very high requirement on the uniformity of light source illumination, the edge and the central area of an image obtained by a red coaxial light source have gray level difference of more than 10 pixels, and the wrinkle gray level is closer to the background. The method is superior to the common fixed threshold segmentation method, and can adapt to certain illumination nonuniformity.
Finally, it should be noted that the above embodiments are merely representative examples of the present invention. It is obvious that the invention is not limited to the above-described embodiments, but that many variations are possible. Any simple modifications, equivalent variations and modifications of the above embodiments of the method according to the principles of the present invention shall be considered to fall within the scope of the present invention.
Claims (4)
1. A method for detecting wrinkle defects of an adhesive film with fine residues removed based on an area ratio is characterized by comprising the following steps:
step 1: taking red coaxial light as a light source, and obtaining an adhesive film picture with a wrinkle defect, wherein the picture is a single-channel gray scale image;
step 2: the method for detecting the wrinkle defect of the adhesive film extracts an interested area comprising wrinkles, fine white residual materials and the outline of the adhesive film;
and step 3: according to the method for detecting the wrinkle defect of the adhesive film, the outline of the adhesive film is removed, and only wrinkle and fine white residual material areas are reserved;
and 4, step 4: the method for detecting the wrinkle defect of the adhesive film extracts wrinkles and rejects fine white residual materials.
2. The method for detecting the wrinkle defect of the adhesive film with fine residues removed based on the area ratio as claimed in claim 1, wherein in the step 2:
the processing method comprises the following steps:
step 2.1: performing edge extraction on the adhesive film picture with the wrinkle defect through a sobel operator, wherein the sobel operator can identify a part with pixel mutation, namely three interested areas, namely wrinkles, fine white residual materials and the adhesive film outline;
step 2.2: binarizing the gray level image obtained in the step 2.1 to obtain binary images of three parts, namely folds, fine white residual materials and the contour of the adhesive film;
step 2.3: and (3) performing morphological opening operation on the binary image obtained in the step (2.2), and using a circular template with the radius of 1 pixel to remove interference pixel points.
3. The method for detecting the wrinkle defect of the adhesive film with fine residues removed based on the area ratio as claimed in claim 1, wherein in the step 3:
the processing method comprises the following steps:
step 3.1: performing fixed threshold segmentation on the adhesive film gray-scale image with the wrinkle defect obtained in the step (1), and removing a background area to obtain a binary image of the adhesive film area;
step 3.2: performing morphological corrosion operation on the binary image obtained in the step 3.1, and corroding the edge part of the adhesive film binary image by adopting a circular template with the radius of 7 pixels;
step 3.3: the binary image obtained in the step 2 comprises three parts of folds, fine white residual materials and adhesive film outlines, the binary image obtained in the step 3.2 is the adhesive film area with the edge outline removed, the two parts are intersected, the adhesive film outline in the step 2 is removed, and the folds and the fine white residual material area are reserved.
4. The method for detecting the wrinkle defect of the adhesive film with fine residues removed based on the area ratio as claimed in claim 1, wherein in the step 4:
the processing method comprises the following steps:
step 4.1: step 3, obtaining a binary image of two parts of regions, namely wrinkles and fine white residual materials, wherein other pixel regions which are not removed in the step 2.3 are inevitable and have small areas, and the regions are removed through the areas;
step 4.2: performing morphological closed operation on the binary image obtained in the step 4.1, so that discrete wrinkle regions can be connected to form a connected domain with a larger area;
step 4.3: taking the binary area obtained in the step 4.2 as a template, and carrying out domain reduction on the single-channel gray original image obtained in the step 1 to obtain a gray image only containing wrinkles and fine white residual materials;
step 4.4: performing dynamic threshold segmentation on the gray level image obtained in the step 4.3 to obtain that the area of the bright color part of the fine white residual material exceeds 90% of the area of the connected domain where the bright color part of the fine white residual material is located, removing the connected domain where the fine white residual material is located through the area ratio, and only keeping the connected domain where the wrinkles are located;
step 4.5: and (4) taking the binary area obtained in the step (4.4) as a template, and reducing the area of the single-channel gray original image obtained in the step (1) to obtain a gray image only with a wrinkle area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011256012.2A CN112651923A (en) | 2020-11-11 | 2020-11-11 | Adhesive film wrinkle defect detection method capable of removing fine residues based on area ratio |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011256012.2A CN112651923A (en) | 2020-11-11 | 2020-11-11 | Adhesive film wrinkle defect detection method capable of removing fine residues based on area ratio |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112651923A true CN112651923A (en) | 2021-04-13 |
Family
ID=75346958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011256012.2A Pending CN112651923A (en) | 2020-11-11 | 2020-11-11 | Adhesive film wrinkle defect detection method capable of removing fine residues based on area ratio |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112651923A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115170572A (en) * | 2022-09-08 | 2022-10-11 | 山东瑞峰新材料科技有限公司 | BOPP composite film surface gluing quality monitoring method |
| CN115631173A (en) * | 2022-10-28 | 2023-01-20 | 兰州理工大学 | Composite film defect identification method |
| CN116681664A (en) * | 2023-05-30 | 2023-09-01 | 佛山市明焱科技有限公司 | Detection method and device for operation of stamping equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110062603A1 (en) * | 2009-05-08 | 2011-03-17 | Hawker Craig J | Encapsulation architectures for utilizing flexible barrier films |
| CN103439338A (en) * | 2013-08-30 | 2013-12-11 | 无锡金视界科技有限公司 | Classification method for film defects |
| CN205931895U (en) * | 2016-07-11 | 2017-02-08 | 九阳股份有限公司 | A capsule that is used for diaphragm of material discernment and is equipped with this diaphragm |
| CN106529510A (en) * | 2016-12-12 | 2017-03-22 | 中国科学院合肥物质科学研究院 | Wrinkle recognition method and apparatus for capacitor thin film |
| CN109900717A (en) * | 2017-12-08 | 2019-06-18 | 英飞凌科技股份有限公司 | Use the inspection method and check device for semiconductor substrate of slope data |
-
2020
- 2020-11-11 CN CN202011256012.2A patent/CN112651923A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110062603A1 (en) * | 2009-05-08 | 2011-03-17 | Hawker Craig J | Encapsulation architectures for utilizing flexible barrier films |
| CN103439338A (en) * | 2013-08-30 | 2013-12-11 | 无锡金视界科技有限公司 | Classification method for film defects |
| CN205931895U (en) * | 2016-07-11 | 2017-02-08 | 九阳股份有限公司 | A capsule that is used for diaphragm of material discernment and is equipped with this diaphragm |
| CN106529510A (en) * | 2016-12-12 | 2017-03-22 | 中国科学院合肥物质科学研究院 | Wrinkle recognition method and apparatus for capacitor thin film |
| CN109900717A (en) * | 2017-12-08 | 2019-06-18 | 英飞凌科技股份有限公司 | Use the inspection method and check device for semiconductor substrate of slope data |
Non-Patent Citations (1)
| Title |
|---|
| 朱慧: "圆柱形锂电池端面缺陷检测方法研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 08, 15 August 2019 (2019-08-15), pages 042 - 1124 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115170572A (en) * | 2022-09-08 | 2022-10-11 | 山东瑞峰新材料科技有限公司 | BOPP composite film surface gluing quality monitoring method |
| CN115631173A (en) * | 2022-10-28 | 2023-01-20 | 兰州理工大学 | Composite film defect identification method |
| CN116681664A (en) * | 2023-05-30 | 2023-09-01 | 佛山市明焱科技有限公司 | Detection method and device for operation of stamping equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112651923A (en) | Adhesive film wrinkle defect detection method capable of removing fine residues based on area ratio | |
| CN109975308B (en) | Surface detection method based on deep learning | |
| CN111179225B (en) | Test paper surface texture defect detection method based on gray gradient clustering | |
| CN108460757B (en) | Mobile phone TFT-LCD screen Mura defect online automatic detection method | |
| CN111539935B (en) | Online cable surface defect detection method based on machine vision | |
| US8908957B2 (en) | Method for building rule of thumb of defect classification, and methods for classifying defect and judging killer defect based on rule of thumb and critical area analysis | |
| Choi et al. | Detection of pinholes in steel slabs using Gabor filter combination and morphological features | |
| CN111681213A (en) | Light guide plate line scratch defect detection method based on deep learning | |
| CN104792794A (en) | Machine vision based optical film surface defect detecting method | |
| CN108830857B (en) | Self-adaptive Chinese character copy label image binarization segmentation method | |
| CN110021012B (en) | Mobile phone lens window glass defect detection method based on machine vision technology | |
| CN113298769B (en) | FPC flexible flat cable appearance defect detection method, system and medium | |
| CN116542976A (en) | Visual detection system for die-cutting piece defects | |
| CN116542975B (en) | Defect classification method, device, equipment and medium for glass panel | |
| CN108986055B (en) | Visual detection method for tiny cracks on egg shell surface | |
| CN114445707A (en) | Intelligent visual fine detection method for defects of bottled water labels | |
| CN106780437A (en) | A kind of quick QFN chips plastic packaging image is obtained and amplification method | |
| CN113139943B (en) | Method and system for detecting appearance defects of open circular ring workpiece and computer storage medium | |
| JiWei et al. | Bottom-hat filtering for defect detection with cnn classification on car wiper arm | |
| CN113916893A (en) | Method for detecting die-cutting product defects | |
| CN108171691B (en) | Detection method of plastic container | |
| US6289123B1 (en) | Character extracting method and its apparatus | |
| CN107833222B (en) | Nonmetal part surplus detection device and method | |
| CN112200805A (en) | Industrial product image target extraction and defect judgment method | |
| CN116773528A (en) | Visual defect detection method and system for candidate region |
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 |