CN115471465A - TFT substrate line defect detection method based on difference image method - Google Patents
TFT substrate line defect detection method based on difference image method Download PDFInfo
- Publication number
- CN115471465A CN115471465A CN202211050469.7A CN202211050469A CN115471465A CN 115471465 A CN115471465 A CN 115471465A CN 202211050469 A CN202211050469 A CN 202211050469A CN 115471465 A CN115471465 A CN 115471465A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- tft substrate
- detected
- difference
- 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 82
- 239000000758 substrate Substances 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 238000001914 filtration Methods 0.000 claims abstract description 9
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000007797 corrosion Effects 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 9
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000003706 image smoothing Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000001125 extrusion Methods 0.000 description 1
- 238000011031 large-scale manufacturing process Methods 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000011179 visual inspection Methods 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
- G06T7/0004—Industrial image inspection
-
- 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
- G01N21/95—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- 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
- 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
- G01N2021/8887—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 based on image processing techniques
-
- 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
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/30121—CRT, LCD or plasma display
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a TFT substrate line defect detection method based on a difference image method, which comprises the following steps of S101, collecting a standard TFT substrate gray image I and a TFT substrate gray image D to be detected by using an industrial camera; s102, carrying out Gaussian filtering on the image I and the image D; s103, performing subtraction operation on the standard TFT image I1 obtained after processing and the TFT image D1 to be detected to obtain an image G; s104, performing threshold segmentation on the image G by adopting an Otsu method; s105, carrying out corrosion-first expansion-second treatment on the image after threshold segmentation, and reducing the characteristics of defects; and S106, positioning the defect position. The detection method can effectively detect the defect sample, accurately position the defect position and improve the production efficiency.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a TFT substrate line defect detection method based on a difference image method.
Background
In recent years, the electronic information industry has been developed vigorously and has gradually become the backbone industry of national economy in China. Liquid crystal displays have attracted attention since their birth as an indispensable product for human-machine information exchange. The thin film transistor liquid crystal display (TFT-LCD) is a display device which skillfully combines the microelectronic technology and the liquid crystal display, and is the only display device which comprehensively catches up with and surpasses the CRT in the comprehensive performances of brightness, contrast, service life, power consumption, volume, weight and the like at present. The system has the advantages of excellent performance, high automation degree, good large-scale production characteristics and wide development space, and is widely applied to important fields of computers, industrial monitoring, global Positioning Systems (GPS), mobile phones and the like.
With the development of large size, high resolution, and light weight of the lcd, the internal electronic circuit is highly fine and intricate, and various circuit defects, mainly including various types of circuit breakage, scratch, foreign matter, dirt, etc., are easily generated due to collision, friction, etc. during the production process. The circuit fracture, also called as a breakpoint, is mainly caused by external force collision and extrusion in the preparation process, and can directly cause that part of functions of the liquid crystal display screen cannot work or even completely lose response.
At present, display screen manufacturers complete the detection of the defects of the display panel in a purely manual mode, and workers need to have certain defect identification capacity, so that strict training is required for the workers, and the production cost is increased. Meanwhile, the defects are various, the manual detection efficiency is low, fatigue is easy to occur and misjudgment or missed judgment is easy to occur when the screen works for a long time, and unstable human factors have great influence on the screen defect detection result.
The TFT-LCD defect detection comprises human eye detection, the manual detection efficiency is low, fatigue is easy to occur and misjudgment or missed judgment is easy to occur when the TFT-LCD defect detection works for a long time, and unstable human factors have great influence on a screen defect detection result. Machine visual inspection can reach unified detection standard when avoiding causing the damage in the testing process again, has greatly improved production efficiency, has reduced manufacturing cost.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide a method for effectively and automatically detecting the circuit defects of a TFT substrate, so that the TFT substrate not only can successfully realize automatic defect detection, but also can greatly improve the production efficiency of the TFT substrate.
In order to achieve the purpose, the invention adopts the following technical scheme: a TFT substrate circuit defect detection method based on a difference shadow method comprises the following steps in sequence:
s101, image acquisition: collecting a standard TFT substrate gray level image I and a TFT substrate gray level image D to be detected;
s102, image preprocessing: carrying out Gaussian filtering on the image I and the image D to obtain an image I1 and an image D1;
using a two-dimensional gaussian distribution function as an image smoothing filter:
wherein x and y represent the template coordinates of the pixels, the central position of the template is the origin, σ is the standard deviation of normal distribution, and the size of the template depends on the size of the image resolution.
S103, difference arithmetic processing: and performing difference operation between the salient region image I1 in the standard TFT substrate image after pretreatment and the salient region image D1 in the TFT substrate image to be detected, and subtracting pixel values of corresponding coordinates of the salient region image I1 and the salient region image D1 to be detected to obtain a difference image which is a TFT substrate defect image G.
S104, binarization operation: performing threshold segmentation on the image G by adopting an Otsu method;
after image binarization segmentation is performed according to a threshold value obtained by the Otsu method, the inter-class variance between the foreground image and the background image is maximum, namely:
s=α 0 ×α 1 (β 0 -β 1 ) (2)
where s is the maximum variance value, α 0 The number of pixels of the background being a proportion of the whole image, alpha 1 The number of foreground pixels in the whole image, beta 0 Is the average gray scale of the background image, beta 1 Is the average gray level of the foreground image.
S105, morphological processing: the obtained schematic diagram after binarization still has certain deviation, and for the accuracy of defect detection, the misjudgment information needs to be cleared, the graph is subjected to morphological processing, the difference image is subjected to processing of corrosion first and then expansion, the tiny difference and smaller noise points are removed, and the characteristics of real defects are restored.
S106, positioning the defect position: measuring the maximum length of the obtained defect, regarding the dead pixel with the length more than 80 mu m as a Mura defect, neglecting the dead pixel with the length less than 80 mu m, then calculating four vertex coordinates of the minimum circumscribed rectangle of the edge contour, drawing the minimum rectangular frame of the edge contour according to the four vertex coordinates of the minimum circumscribed rectangle of the edge contour, and finally drawing a defect area frame on the original picture.
Drawings
FIG. 1 is a standard flow chart of a TFT substrate line defect detection method based on a difference image method according to the present invention;
FIG. 2 is a schematic diagram of an experimental standard template in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an experimental sample of an embodiment of the present invention, showing a TFT substrate to be tested;
FIG. 4 is a schematic diagram of a standard TFT image of the present invention after Gaussian filtering;
FIG. 5 is a schematic diagram of a TFT image to be detected after Gaussian filtering processing;
FIG. 6 is a graph illustrating the difference image result of the present invention;
FIG. 7 is a schematic diagram of a difference image result graph obtained after threshold segmentation according to the present invention;
FIG. 8 is a diagram of the threshold segmentation of the present invention followed by morphological operations;
FIG. 9 shows the result of defect detection of the present invention, and the defect positions are indicated by circular frames.
Detailed Description
The invention will be further described with reference to the accompanying drawings and examples, which are simplified schematic drawings and illustrate only the basic structure of the invention in a schematic manner, and therefore only show the structures relevant to the invention.
As shown in fig. 1, a TFT substrate line defect detection method based on the difference image method includes the following steps:
s101, image acquisition: collecting a standard TFT substrate gray image I as shown in FIG. 2, and a TFT substrate gray image D to be detected as shown in FIG. 3;
s102, image preprocessing: carrying out Gaussian filtering on the image I and the image D;
using a two-dimensional Gaussian distribution function as an image smoothing filter;
wherein x and y represent the template coordinates of the pixels, the central position of the template is the origin, σ is the standard deviation of the normal distribution, the size of the template depends on the size of the image resolution, and the resolution of the image in this embodiment is 1528 × 1188.
S103, difference shadow operation processing: performing difference shadow operation on the standard TFT image 4 and the TFT image 5 to be detected obtained after the pretreatment, and subtracting pixel values of corresponding coordinates of the standard TFT image and the TFT image to be detected to obtain a difference image as a defect image, wherein the process can be represented by formula (2):
wherein, G (m, n) is a defect image after the difference operation, I (x, y) is a standard TFT image, D (x 1, y 1) is a TFT defect image, m, n, x, y, x1, y1 represent coordinate positions corresponding to the respective images, pixel values of their corresponding coordinates are differentiated, and the same are marked as "0", and the different are marked as "1". For the surface defect detection of the TFT substrate image, because the background is complex, the interference is large, the defect is small and the detection is difficult, the detection result obtained by the differential method also comprises some non-defect areas, the defect image is not complete, and the outline of the defect is further extracted and screened to obtain the complete defect area.
S104, binarization operation: performing threshold segmentation by using the Otsu method, and performing image binarization segmentation according to the threshold obtained by the Otsu method, wherein the between-class variance between the foreground image and the background image is maximum, namely:
s=α 0 ×α 1 (β 0 -β 1 ) (3)
where s is the maximum variance value, α 0 The number of pixels of the background being a proportion of the whole image, alpha 1 The number of foreground pixels in the whole image, beta 0 =127,β 1 =36。
S105, morphological processing: carrying out corrosion-first and expansion-second treatment on the image after the binarization operation to reduce the characteristics of defects;
after the defect map is obtained, there still exists some deviation, and the pattern is further processed morphologically for the purpose of accuracy of defect detection. Wherein, the size of the template used for corrosion and expansion is the same, the tiny difference between double images and non-defect is removed by corrosion operation, the noise point with small size is not misjudged as a defect point, and then the characteristic of the real defect is restored by expansion processing.
S106, positioning the defect position: judging whether the sample to be detected is qualified or not, measuring the maximum length of the defect, regarding the dead pixel with the length more than 80 μm as a Mura defect, neglecting the dead pixel with the length less than 80 μm, positioning the position of the defect, and judging the sample to be detected as a qualified sample if the sample to be detected has no defect, thereby completing the detection.
And (3) positioning the defect position, specifically: and calculating four vertex coordinates of the minimum external rectangle of the Mura defect edge outline, drawing a minimum rectangular frame of the edge outline according to the four vertex coordinates of the minimum external rectangle of the edge outline, and finally drawing a defect area frame on the original picture.
Example of the implementation
In order to verify the measurement effect of the TFT substrate line defect detection method based on the difference image method, the following experiments are carried out:
example 1
In order to verify the measurement effect of the TFT substrate line defect detection method based on the difference image method, the following experiments are carried out: the standard template is shown in FIG. 2, FIG. 3 is a diagram of a TFT sample to be detected, FIG. 4 and FIG. 5 are Gaussian filter diagrams of the standard template and the sample to be detected;
the difference shadow calculation is carried out on the images in the figure 4 and the figure 5, and a difference shadow result chart is shown in figure 6; and (3) carrying out binarization operation on the difference image result image 6 to obtain an image 7, judging that the length of the longest diameter of the defect area is smaller than 80 mu m as normal, judging that the length of the longest diameter is larger than 80 mu m as defect, carrying out morphological operation processing on the image 7 to obtain an image 8, judging that the maximum diameters of two defect areas in the image 8 are larger than 80 mu m as defect, and finally carrying out defect marking on the original image to be detected, wherein the area shown by a circular frame is the defect as shown in the image 9.
The embodiment proves that the TFT substrate line defect detection method based on the difference image method is simple in process and high in calculation speed.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A TFT substrate circuit defect detection method based on a difference image method is characterized by comprising the following steps:
s101, image acquisition: acquiring a standard TFT substrate gray level image I and a TFT substrate gray level image D to be detected by using an industrial camera;
s102, image preprocessing: carrying out Gaussian filtering on the image I and the image D;
s103, difference shadow operation processing: performing difference shadow operation on the standard TFT image I1 obtained after Gaussian filtering and the TFT image D1 to be detected to obtain an image G;
s104, performing binarization operation on the image G: performing threshold segmentation by Otsu method;
s105, morphological processing: carrying out corrosion-first and expansion-second treatment on the image after threshold segmentation to restore the characteristics of defects;
s106, positioning the defect position: and judging whether the sample to be detected is qualified or not, if the sample to be detected has defects, positioning the positions of the defects, and if the sample to be detected has no defects, judging the sample to be qualified, and finishing the detection.
2. The method for detecting the line defect of the TFT substrate based on the difference image method according to claim 1, wherein: step S102, specifically including: and preprocessing the standard TFT substrate I and the TFT substrate D to be detected by adopting a Gaussian filtering technology, filtering noise points on the surface of an image, and improving the quality of the image.
3. The method for detecting the line defect of the TFT substrate based on the difference image method according to claim 1, wherein: step S103, specifically including: and performing difference operation between the salient region image I1 in the standard TFT substrate image obtained after preprocessing and the salient region image D1 in the TFT substrate image to be detected, and subtracting the pixel values of the corresponding coordinates to obtain a difference image which is a TFT substrate defect image G.
4. The method for detecting the line defect of the TFT substrate based on the difference image method according to claim 1, wherein: step S105, specifically including: performing open operation on the defect image, namely corroding and expanding; the size of the template used for corrosion and expansion is the same, the crack and the low-density area are amplified, smaller noise points existing in the image are filtered, and the noise points with the undersize size cannot be mistakenly judged as defect points.
5. The method for detecting the line defect of the TFT substrate based on the difference image method according to claim 1, wherein: step S106, specifically including: firstly, judging whether a sample to be detected is qualified or not, wherein the judging method is that only defect information is reserved in a morphologically processed picture, the Mura defect can be judged only if the maximum diameter or the maximum length is greater than or equal to a specified distance in the size of a detected defect pixel through calculation, the position of the defect is positioned, a defect frame is drawn, and finally, a defect area frame is drawn on an original picture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211050469.7A CN115471465A (en) | 2022-08-29 | 2022-08-29 | TFT substrate line defect detection method based on difference image method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211050469.7A CN115471465A (en) | 2022-08-29 | 2022-08-29 | TFT substrate line defect detection method based on difference image method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115471465A true CN115471465A (en) | 2022-12-13 |
Family
ID=84371123
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211050469.7A Pending CN115471465A (en) | 2022-08-29 | 2022-08-29 | TFT substrate line defect detection method based on difference image method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115471465A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116359243A (en) * | 2023-03-16 | 2023-06-30 | 深圳市德勤建工集团有限公司 | Environment-friendly panel production quality detection method based on computer vision |
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 |
-
2022
- 2022-08-29 CN CN202211050469.7A patent/CN115471465A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116359243A (en) * | 2023-03-16 | 2023-06-30 | 深圳市德勤建工集团有限公司 | Environment-friendly panel production quality detection method based on computer vision |
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 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108460757B (en) | Mobile phone TFT-LCD screen Mura defect online automatic detection method | |
CN115471465A (en) | TFT substrate line defect detection method based on difference image method | |
CN107845087B (en) | Method and system for detecting uneven brightness defect of liquid crystal panel | |
CN107678192B (en) | Mura defect detection method based on machine vision | |
Liu et al. | Machine vision based online detection of PCB defect | |
WO2018040118A1 (en) | Gpu-based tft-lcd mura defect detection method | |
CN111986159B (en) | Electrode defect detection method and device for solar cell and storage medium | |
CN109801286B (en) | Surface defect detection method for LCD light guide plate | |
CN110021012B (en) | Mobile phone lens window glass defect detection method based on machine vision technology | |
CN112419229A (en) | Display screen linear defect detection method and device and storage medium | |
US20080226158A1 (en) | Data Processor and Data Processing Method | |
CN115100200B (en) | Optical fiber defect detection method and system based on optical means | |
CN109449093A (en) | Wafer detection method | |
CN110544231A (en) | lithium battery electrode surface defect detection method based on background standardization and centralized compensation algorithm | |
CN116468726B (en) | Online foreign matter line detection method and system | |
WO2024002187A1 (en) | Defect detection method, defect detection device, and storage medium | |
CN112489042A (en) | Metal product printing defect and surface damage detection method based on super-resolution reconstruction | |
CN111681213A (en) | Light guide plate line scratch defect detection method based on deep learning | |
CN113822893B (en) | Liquid crystal panel peripheral circuit detection method and system based on texture features | |
CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
Lin et al. | Surface defect detection of machined parts based on machining texture direction | |
Yang et al. | Crack identification of automobile steering knuckle fluorescent penetrant inspection based on deep convolutional generative adversarial networks data enhancement | |
CN117152129B (en) | Visual detection method and system for surface defects of battery cover plate | |
CN109426013B (en) | Method and device for analyzing and detecting and repairing defects of color film substrate | |
JP2004251781A (en) | Defect inspection method by image recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |