CN109856156A - A kind of display panel tiny flaw determination method and device based on AOI - Google Patents
A kind of display panel tiny flaw determination method and device based on AOI Download PDFInfo
- Publication number
- CN109856156A CN109856156A CN201910060055.4A CN201910060055A CN109856156A CN 109856156 A CN109856156 A CN 109856156A CN 201910060055 A CN201910060055 A CN 201910060055A CN 109856156 A CN109856156 A CN 109856156A
- Authority
- CN
- China
- Prior art keywords
- image
- camera
- tiny flaw
- display panel
- aoi
- 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
Abstract
The invention belongs to display screen defect detecting technique fields, disclose a kind of display panel tiny flaw determination method and device based on AOI, the position of tiny flaw is obtained by big phase machine testing, secondary image acquisition is carried out to tiny flaw by small camera, and it is analyzed and processed, final output defect type.The present invention can carry out exact classification to tiny flaw, realize the classification such as the correct drop of panel.
Description
Technical field
It is small scarce that the present invention relates to display screen defect detecting technique fields more particularly to a kind of display panel based on AOI
Fall into determination method and device.
Background technique
With the development of LCD (Liquid Crystal Display, liquid crystal display) panel detection industry, manufacturer for
The requirement of panel detection is higher and higher, there is different degraded specifications for the defect of different types.AOI(Automated
Optical Inspection, automatic optics inspection) equipment in order to correctly carry out the output such as dropping to panel, needs to inspection
The defect measured is accurately classified, and carries out degradation output according to the requirement of client to sorted defect.
Existing AOI equipment detects panel using big resolution camera, and (area is in 0.25- for tiny flaw
Defect between 6subpixel) it is very low in entire panel image intermediate-resolution, it can not be carried out by image precise classification,
Detection very influences the omission factor of equipment and crosses inspection rate.
Summary of the invention
The embodiment of the present application is solved by providing a kind of display panel tiny flaw determination method and device based on AOI
The problem of precise classification, detection can not being carried out to tiny flaw by panel image in the prior art.
The embodiment of the present application provides a kind of display panel tiny flaw determination method based on AOI, comprising the following steps:
Image Acquisition is carried out by whole region of the first camera to display panel, obtains the first image;
The location information of tiny flaw is obtained according to the first image;
According to the location information of the tiny flaw, image is carried out by defect area of the second camera to display panel and is adopted
Collection, obtains the second image;
Detection classification processing is carried out to tiny flaw according to second image;
Wherein, the first camera is black and white camera, and the second camera is color camera, the resolution of the first camera
Rate is higher than the second camera.
Preferably, second image includes the picture image of five modes of L255, R255, G255, B255, L0;It is described
Detection classification processing includes image rotation correction, image segmentation, abnormal area segmentation, defects detection, defect classification.
Preferably, described image rotation correction includes: to obtain image using blob analytic approach based on L255 picture image
Angle is rotated, and image is corrected according to the rotation angle.
Preferably, described image segmentation includes: based on L255 picture image, and the horizontal partition of analytical calculation liquid crystal unit is straight
The analytic equation of line group and longitudinally split straight line group is split image according to parsing result.
Preferably, the abnormal area segmentation includes: abnormal dark based on the extraction of L255, R255, G255, B255 picture image
Abnormal bright area is extracted based on L0, R255, G255, B255 picture image in region.
Preferably, the defects detection includes: to calculate the characteristic value of each abnormal area, and according to the number of the characteristic value
It is worth range and carries out defects detection.
Preferably, defect classification includes: the coordinate information according to fleck defect and DSD dark spot defect respectively, using recurrence
Algorithm classifies to defect, defect classification include single dim spot, it is two even dark, three even dark, connect more dark, single bright spot, two connect it is bright,
Connect bright, bright dark arranged side by side, point away from class defect more.
On the other hand, the embodiment of the present application provides a kind of display panel tiny flaw decision maker based on AOI, comprising:
Phase unit and image acquisition and processing unit;
The phase unit includes first camera and second camera, and the first camera is black and white camera, the second camera
For color camera, for the high resolution of the first camera in the second camera, the second camera has tri- directions x-y-z
Freedom degree;
The first camera is used to carry out Image Acquisition to the whole region of display panel, obtains the first image, and according to
The location information of the first image acquisition tiny flaw;The second camera is used for the location information according to the tiny flaw
Image Acquisition is carried out to the defect area of display panel, obtains the second image;
Described image acquisition process unit is used to obtain the location information of the tiny flaw according to the first image, uses
In carrying out detection classification processing to tiny flaw according to second image.
Preferably, the second camera uses doubly telecentric camera lens.
Preferably, the resolution ratio of the first camera is 71M, and the resolution ratio of the second camera is 5M.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
In the embodiment of the present application, the position for obtaining tiny flaw is detected by big camera (first camera) first, then
Small camera (second camera) is moved to defective locations, acquire image and is analyzed and processed, final output defect type.I.e. originally
Colored small camera is added in invention in existing AOI equipment, carries out secondary acquisition image to the tiny flaw that can not be determined, and locate
Reason analysis realizes the classification such as the correct drop of panel to obtain the exact classification of defect.It is proposed by the present invention aobvious based on AOI
Show that panel tiny flaw determination method carries out Image Acquisition to tiny flaw using colored small camera, it is ensured that single in panel
Accounting requirement of the pixel in small camera image, can be improved the resolution ratio and clarity of defect.In addition, being rectified using image rotation
Just, the processing method of image segmentation is, it can be achieved that desired detection accuracy, rapidly can carry out detection and accurate point to defect
Class.To sum up, the present invention quickly and effectively can accurately carry out tiny flaw detection judgement work, can reduce the mistake of AOI equipment
Inspection rate and omission factor, improve the recall rate of AOI equipment, and can effectively replace manpower.
Detailed description of the invention
It, below will be to needed in embodiment description in order to illustrate more clearly of the technical solution in the present embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is one embodiment of the present of invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is image of the point away from the point for 2 away from class defect on big camera;
Fig. 2 is image of the point away from the point for 2 away from class defect on small camera;
Fig. 3 is a kind of display panel tiny flaw decision maker small camera based on AOI provided in an embodiment of the present invention
Mobile schematic diagram;
Fig. 4 is detection point in a kind of display panel tiny flaw determination method based on AOI provided in an embodiment of the present invention
The general flow chart of class processing;
Fig. 5 is image rotation in a kind of display panel tiny flaw determination method based on AOI provided in an embodiment of the present invention
It transfers to another school positive flow chart;
Fig. 6 is image rotation in a kind of display panel tiny flaw determination method based on AOI provided in an embodiment of the present invention
Schematic diagram before transferring to another school just;
Fig. 7 is image rotation in a kind of display panel tiny flaw determination method based on AOI provided in an embodiment of the present invention
Schematic diagram after transferring to another school just;
Fig. 8 is image point in a kind of display panel tiny flaw determination method based on AOI provided in an embodiment of the present invention
The schematic illustration cut;
Fig. 9 is image point in a kind of display panel tiny flaw determination method based on AOI provided in an embodiment of the present invention
The effect diagram cut;
Figure 10 is a kind of display panel tiny flaw determination method small camera based on AOI provided in an embodiment of the present invention
The L255 picture of acquisition;
Figure 11 is a kind of display panel tiny flaw determination method small camera based on AOI provided in an embodiment of the present invention
The R255 picture of acquisition;
Figure 12 is a kind of display panel tiny flaw determination method small camera based on AOI provided in an embodiment of the present invention
The G255 picture of acquisition;
Figure 13 is a kind of display panel tiny flaw determination method small camera based on AOI provided in an embodiment of the present invention
The B255 picture of acquisition;
Figure 14 is a kind of display panel tiny flaw determination method small camera based on AOI provided in an embodiment of the present invention
The L0 picture of acquisition;
Figure 15 is exceptions area in a kind of display panel tiny flaw determination method based on AOI provided in an embodiment of the present invention
The flow chart of regional partition;
Figure 16 is defect point in a kind of display panel tiny flaw determination method based on AOI provided in an embodiment of the present invention
The schematic diagram of class.
Specific embodiment
In order to better understand the above technical scheme, in conjunction with appended figures and specific embodiments to upper
Technical solution is stated to be described in detail.
In the panel AOI equipment of existing major device manufacturer's production, panel pixel and image pixel are than being usually 1:3, i.e.,
3*3=9pixel is only accounted in single subpixel image of panel, and in the application of microdefect detection classification, customer requirement inspection
The 0.25subpixel that precision reaches panel is surveyed, the image of corresponding big camera is 0.25/3*9=0.75pixel.And in big camera
Image processing process in, consider the precision of algorithm, the influence of noise, liquid crystal image the factors such as halation phenomenon, realize
The detection accuracy of 0.75pixel is difficult to realize.And such as Cell foreign matter, two companies are bright, connect dim spot, Cell foreign matter is swooned and opened more
The defects of with panel upper and lower surface dust caused by dirty or foreign matter in big camera image, imaging characteristic is unobvious, commonly uses
Detection algorithm is not easily distinguishable, and be easy to cause and largely crosses inspection and missing inspection, influences the recall rate and detection effect of AOI equipment.
To solve the above-mentioned problems, the present invention combines small camera accurately to be sentenced to realize to display panel tiny flaw
It is fixed.The collection effect of big camera, small camera is compared first.For example, point away from the point for 2 away from class defect (tiny flaw
It is a kind of) image under big camera (resolution ratio 71M) and small camera (resolution ratio 5M) distinguishes as shown in Figure 1 and Figure 2, passes through
Comparison is apparent that such defect is relatively sharp intuitive by the image that small camera acquires.
The present invention proposes a kind of display panel tiny flaw determination method and device based on AOI.Using the coloured silk of 2-4 multiplying power
The small camera of color and doubly telecentric camera lens carry out Image Acquisition to tiny flaw, guarantee that single pixel accounts in small camera image in panel
Than being greater than 30*30=900pixel, the resolution ratio and clarity of defect are improved.Using image rotation correction, the place of image segmentation
Reason method realizes the detection accuracy of 0.25subpixel, quickly can carry out detection and Accurate classification to defect, and then realize
To accurately sentencing for panel, inspection rate and omission factor are crossed to reduction AOI equipment, reducing business manpower cost has significant work
With.
Specifically, a kind of display panel tiny flaw decision maker based on AOI provided by the invention includes sentencing camera again.
There are three the mechanical arms of direction freedom degree to control the movement for sentencing camera again using tool by the present invention, i.e., to sentence camera again there are x-y-
The freedom degree in tri- directions z, reference can be made to Fig. 3.The optical texture of camera is sentenced again using colored small camera+doubly telecentric camera lens, wherein
The image of colored small camera shooting contains colouring information, can distinguish the defect letter of the subpixel of any color channel of panel
Breath;Telecentric lens can generate mirror image distortion to avoid image, guarantee that the single subpixel of any position in image is in the same size,
Has the function of simplified operation.
The present invention obtains the testing result of big camera detection panel first, obtains the position of point class defect.Pass through manipulator
Colored small camera is moved to corresponding position (defect coordinate that i.e. big phase machine testing obtains) by arm, and acquisition image carries out at analysis
Reason exports defect type and area, and area is as unit of subpiel in panel.I.e. the present invention is first by big camera to panel
It is detected to obtain defect coordinate, but big camera can not judge defect type, therefore then by small camera according to defect coordinate
Defective locations are moved to, carry out adopting figure, and then judge defect type.
Detection classification processing (i.e. image analysis processing) of the present invention mainly includes image rotation correction, image point
It cuts, abnormal area segmentation, defects detection, defect 5 steps of classification, as shown in Figure 4.Below to image rotation correction and image point
The principle cut is introduced, and subsequent three steps are based on existing detection algorithm, repeats no more.
(1) image rotation corrects
Since liquid crystal image integral-rotation angle is consistent, can be deposited some liquid crystal unit according to picture centre region
Angle, calculate its rotation to 90 degree corresponding affine matrixs, then whole image utilizes affine transformation progress image rotation
Correction.The process of image rotation correction is as shown in Figure 5.Calibration result comparison is as shown in Figure 6, Figure 7, wherein Fig. 6 indicates original graph
Picture, Fig. 7 indicate the image after rotation correction.
(2) image segmentation
It is to carry out the segmentation based on each liquid crystal unit that liquid crystal image, which handles the first step,.Since liquid crystal unit size is identical,
Arranged distribution is regular uniformly, so can be equivalent to solve the parallel lines Lr of two groups of intersections for the image segmentation of liquid crystal uniti、
Lci(i=1,2,3 ...).And straight line Lri、Lri+1、Lck、Lck+1Area defined is exactly the i-th row in image, a k column liquid crystal base
The image of member.Fig. 8 show 4k panel topography, LriFor horizontal partition straight line group, LciFor longitudinally split straight line group.In the hope of
Solve LciFor dividing straight line group, image segmentation algorithm is equivalent to solve straight line group LciSlope k, between adjacent two parallel lines
Away from b and the endpoint P0 coordinate of first cutting line these parameters.
Global threshold segmentation is carried out, is extracted after extracting single channel (as extracted the channel R) image based on white picture image
Then each subpixel centre coordinate carries out straight line fitting using least square method, solves horizontal LriWith vertical divider group
LciAnalytic equation, realization be split according to subpixel for unit, segmentation effect is as shown in Figure 9.
Overall procedure of the invention mainly comprises the steps that
Step 1 will be sentenced again after camera (i.e. small camera) is moved to designated position (i.e. big camera obtain defective locations), adopt
The picture image for collecting L255, R255, G255, B255, L0 totally 5 modes, respectively as shown in Figure 10-Figure 14.
Step 2 is based on L255 picture image, and the rotation angle of image is obtained using blob analytic approach, carries out school to image
Just.
Step 3 is based on L255 picture image, the analytic equation of analytical calculation cut-off rule group.
Step 4, according to the arrangement of cut-off rule and the distribution character of image, abnormal area segmentation is carried out to image, reference can be made to
Figure 15.Wherein, L255 extracts different dark areas, and L0 picture extracts abnormal bright area, excess-three picture extract abnormal bright area with
Abnormal dark areas.
Step 5, the characteristic value for calculating each abnormal area, and defects detection is carried out according to the numberical range of characteristic value, in detail
Carefully it is shown in Table 1:
Table 1
Step 6 realizes single dim spot, two companies according to its coordinate information using recursive algorithm to bright spot and DSD dark spot defect
Secretly, three even dark, connect more dark, single bright spot, two connect bright, Duo Lianliang, it is bright it is dark side by side, point away from the defects of classification, as shown in figure 16.
To sum up, the present invention carries out two to tiny dots class defect using the optical texture of colored small camera and doubly telecentric camera lens
It is secondary to adopt figure judgement, it can be realized a precise classification for class defect, have the function that reduction AOI equipment crosses inspection rate and omission factor.
The display panel tiny flaw determination method and device that the invention proposes a kind of based on AOI can be quickly and effectively quasi-
It really carries out tiny flaw detection and determines work, improve the recall rate of AOI equipment, and can effectively replace manpower.
It should be noted last that the above specific embodiment is only used to illustrate the technical scheme of the present invention and not to limit it,
Although being described the invention in detail referring to example, those skilled in the art should understand that, it can be to the present invention
Technical solution be modified or replaced equivalently, without departing from the spirit and scope of the technical solution of the present invention, should all cover
In the scope of the claims of the present invention.
Claims (10)
1. a kind of display panel tiny flaw determination method based on AOI, which comprises the following steps:
Image Acquisition is carried out by whole region of the first camera to display panel, obtains the first image;
The location information of tiny flaw is obtained according to the first image;
According to the location information of the tiny flaw, Image Acquisition is carried out by defect area of the second camera to display panel,
Obtain the second image;
Detection classification processing is carried out to tiny flaw according to second image;
Wherein, the first camera is black and white camera, and the second camera is color camera, the high resolution of the first camera
In the second camera.
2. the display panel tiny flaw determination method according to claim 1 based on AOI, which is characterized in that described
Two images include the picture image of five modes of L255, R255, G255, B255, L0;The detection classification processing includes image rotation
Transfer to another school just, the segmentation of image segmentation, abnormal area, defects detection, defect classification.
3. the display panel tiny flaw determination method according to claim 2 based on AOI, which is characterized in that the figure
It just includes: the rotation angle of image to be obtained using blob analytic approach, and according to the rotation based on L255 picture image that image rotation, which is transferred to another school,
Gyration is corrected image.
4. the display panel tiny flaw determination method according to claim 2 based on AOI, which is characterized in that the figure
As segmentation includes: based on L255 picture image, the horizontal partition straight line group of analytical calculation liquid crystal unit and longitudinally split straight line group
Analytic equation, image is split according to parsing result.
5. the display panel tiny flaw determination method according to claim 2 based on AOI, which is characterized in that described different
Normal region segmentation includes: to extract abnormal dark areas based on L255, R255, G255, B255 picture image, based on L0, R255,
G255, B255 picture image extract abnormal bright area.
6. the display panel tiny flaw determination method according to claim 2 based on AOI, which is characterized in that described to lack
Sunken detection includes: to calculate the characteristic value of each abnormal area, and carry out defects detection according to the numberical range of the characteristic value.
7. the display panel tiny flaw determination method according to claim 2 based on AOI, which is characterized in that described to lack
Sunken classification includes: the coordinate information according to fleck defect and DSD dark spot defect respectively, is classified using recursive algorithm to defect, is lacked
Sunken classification include single dim spot, it is two even dark, three even dark, connect more dark, single bright spot, two connect bright, Duo Lianliang, it is bright it is dark side by side, point away from
Class defect.
8. a kind of display panel tiny flaw decision maker based on AOI, for realizing as described in claim 1-7 based on
The display panel tiny flaw determination method of AOI characterized by comprising phase unit and image acquisition and processing unit;
The phase unit includes first camera and second camera, and the first camera is black and white camera, and the second camera is coloured silk
Form and aspect machine, for the high resolution of the first camera in the second camera, the second camera has oneself of tri- directions x-y-z
By spending;
The first camera is used to carry out Image Acquisition to the whole region of display panel, obtains the first image, and according to described
The location information of first image acquisition tiny flaw;The second camera is used for the location information according to the tiny flaw to aobvious
Show that the defect area of panel carries out Image Acquisition, obtains the second image;
Described image acquisition process unit is used to obtain the location information of the tiny flaw according to the first image, is used for root
Detection classification processing is carried out to tiny flaw according to second image.
9. the display panel tiny flaw decision maker according to claim 8 based on AOI, which is characterized in that described
Two cameras use doubly telecentric camera lens.
10. the display panel tiny flaw decision maker based on AOI according to claim 8 or claim 9, which is characterized in that institute
The resolution ratio for stating first camera is 71M, and the resolution ratio of the second camera is 5M.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910060055.4A CN109856156A (en) | 2019-01-22 | 2019-01-22 | A kind of display panel tiny flaw determination method and device based on AOI |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910060055.4A CN109856156A (en) | 2019-01-22 | 2019-01-22 | A kind of display panel tiny flaw determination method and device based on AOI |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109856156A true CN109856156A (en) | 2019-06-07 |
Family
ID=66895594
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910060055.4A Pending CN109856156A (en) | 2019-01-22 | 2019-01-22 | A kind of display panel tiny flaw determination method and device based on AOI |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109856156A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110186938A (en) * | 2019-06-28 | 2019-08-30 | 笪萨科技(上海)有限公司 | Two-sided defect analysis equipment and defects detection and analysis system |
CN110458840A (en) * | 2019-10-12 | 2019-11-15 | 武汉精立电子技术有限公司 | A kind of method, system and terminal device for reducing panel defect and crossing inspection rate |
CN110490875A (en) * | 2019-10-16 | 2019-11-22 | 武汉精立电子技术有限公司 | A kind of screen defect filter method, device and storage medium |
CN111474181A (en) * | 2020-03-31 | 2020-07-31 | 成都数之联科技有限公司 | Panel defect detecting and classifying system in box forming process stage |
CN111735823A (en) * | 2020-07-17 | 2020-10-02 | 武汉精立电子技术有限公司 | Defect detection method and system for module |
CN112394064A (en) * | 2020-10-22 | 2021-02-23 | 惠州高视科技有限公司 | Point-line measuring method for screen defect detection |
CN112634258A (en) * | 2020-12-30 | 2021-04-09 | 凌云光技术股份有限公司 | Automatic classification and classification method and device for defect detection based on AOI |
CN112881419A (en) * | 2021-05-06 | 2021-06-01 | 惠州高视科技有限公司 | Chip detection method, electronic device and storage medium |
CN113592859A (en) * | 2021-09-26 | 2021-11-02 | 中导光电设备股份有限公司 | Deep learning-based classification method for defects of display panel |
CN113824827A (en) * | 2021-09-20 | 2021-12-21 | 苏州凯仕弘科技有限公司 | Visual detection system for mobile phone screen |
WO2022150986A1 (en) * | 2021-01-12 | 2022-07-21 | 深圳市艾比森光电股份有限公司 | Image quality inspection method and related product for led display screen |
CN115131327A (en) * | 2022-07-14 | 2022-09-30 | 电子科技大学 | Color feature fused display screen color line defect detection method |
CN117056148A (en) * | 2023-08-30 | 2023-11-14 | 昆山迈致治具科技有限公司 | Method for detecting abnormal display of screen |
CN117115147A (en) * | 2023-10-19 | 2023-11-24 | 山东华盛创新纺织科技有限公司 | Textile detection method and system based on machine vision |
CN115131327B (en) * | 2022-07-14 | 2024-04-30 | 电子科技大学 | Color line defect detection method for display screen with fused color features |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007121243A (en) * | 2005-10-31 | 2007-05-17 | Sharp Corp | Device and method for inspecting image display panel |
CN101241659A (en) * | 2007-02-05 | 2008-08-13 | 曹嘉灿 | Outdoor large screen display device |
CN103177235A (en) * | 2013-04-18 | 2013-06-26 | 河海大学常州校区 | Chinese-sensible code recognition device and Chinese-sensible code recognition method under complicated background |
KR20140082333A (en) * | 2012-12-24 | 2014-07-02 | 엘지디스플레이 주식회사 | Method and apparatus of inspecting mura of flat display |
KR20140082336A (en) * | 2012-12-24 | 2014-07-02 | 엘지디스플레이 주식회사 | Method and apparatus of inspecting mura of flat display |
CN103913461A (en) * | 2013-01-07 | 2014-07-09 | 北京兆维电子(集团)有限责任公司 | TFT-LCD lighting automatic optical inspection based image processing method |
CN104156724A (en) * | 2014-07-09 | 2014-11-19 | 宁波摩视光电科技有限公司 | Two-value image connected domain marking algorithm based on AOI bullet apparent defect detecting system |
CN104568989A (en) * | 2014-12-30 | 2015-04-29 | 湖北优尼科光电技术股份有限公司 | Glass substrate defect detecting method |
CN105548212A (en) * | 2016-02-03 | 2016-05-04 | 杭州晶耐科光电技术有限公司 | System and method for online automatically detecting defects on glass surface of touch screen |
CN106157310A (en) * | 2016-07-06 | 2016-11-23 | 南京汇川图像视觉技术有限公司 | The TFT LCD mura defect inspection method being combined with multichannel based on mixed self-adapting Level Set Models |
CN106770362A (en) * | 2016-12-27 | 2017-05-31 | 武汉精测电子技术股份有限公司 | Gross imperfection detection means and method based on AOI |
CN107024476A (en) * | 2016-03-10 | 2017-08-08 | 上海帆声图像科技有限公司 | Display panel detecting system and its detection means and detection method |
CN107154033A (en) * | 2016-03-03 | 2017-09-12 | 成都交大光芒科技股份有限公司 | A kind of high ferro contact net rotation ears vertical openings pin missing detection method and system |
CN107677679A (en) * | 2017-09-22 | 2018-02-09 | 武汉精测电子技术股份有限公司 | Sorting technique and device the defects of L0 pictures in a kind of AOI detection |
CN107843599A (en) * | 2017-10-24 | 2018-03-27 | 武汉精测电子集团股份有限公司 | The methods of a kind of panel detection based on AOI is sentenced and device |
CN108827970A (en) * | 2018-03-28 | 2018-11-16 | 武汉精测电子集团股份有限公司 | Adaptation different panels defect based on AOI system the methods of sentences automatically and system |
CN108961238A (en) * | 2018-07-02 | 2018-12-07 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
CN109167928A (en) * | 2018-09-06 | 2019-01-08 | 武汉精测电子集团股份有限公司 | Fast automatic exposure method and system based on defects of display panel detection |
-
2019
- 2019-01-22 CN CN201910060055.4A patent/CN109856156A/en active Pending
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007121243A (en) * | 2005-10-31 | 2007-05-17 | Sharp Corp | Device and method for inspecting image display panel |
CN101241659A (en) * | 2007-02-05 | 2008-08-13 | 曹嘉灿 | Outdoor large screen display device |
KR20140082333A (en) * | 2012-12-24 | 2014-07-02 | 엘지디스플레이 주식회사 | Method and apparatus of inspecting mura of flat display |
KR20140082336A (en) * | 2012-12-24 | 2014-07-02 | 엘지디스플레이 주식회사 | Method and apparatus of inspecting mura of flat display |
CN103913461A (en) * | 2013-01-07 | 2014-07-09 | 北京兆维电子(集团)有限责任公司 | TFT-LCD lighting automatic optical inspection based image processing method |
CN103177235A (en) * | 2013-04-18 | 2013-06-26 | 河海大学常州校区 | Chinese-sensible code recognition device and Chinese-sensible code recognition method under complicated background |
CN104156724A (en) * | 2014-07-09 | 2014-11-19 | 宁波摩视光电科技有限公司 | Two-value image connected domain marking algorithm based on AOI bullet apparent defect detecting system |
CN104568989A (en) * | 2014-12-30 | 2015-04-29 | 湖北优尼科光电技术股份有限公司 | Glass substrate defect detecting method |
CN105548212A (en) * | 2016-02-03 | 2016-05-04 | 杭州晶耐科光电技术有限公司 | System and method for online automatically detecting defects on glass surface of touch screen |
CN107154033A (en) * | 2016-03-03 | 2017-09-12 | 成都交大光芒科技股份有限公司 | A kind of high ferro contact net rotation ears vertical openings pin missing detection method and system |
CN107024476A (en) * | 2016-03-10 | 2017-08-08 | 上海帆声图像科技有限公司 | Display panel detecting system and its detection means and detection method |
CN106157310A (en) * | 2016-07-06 | 2016-11-23 | 南京汇川图像视觉技术有限公司 | The TFT LCD mura defect inspection method being combined with multichannel based on mixed self-adapting Level Set Models |
CN106770362A (en) * | 2016-12-27 | 2017-05-31 | 武汉精测电子技术股份有限公司 | Gross imperfection detection means and method based on AOI |
CN107677679A (en) * | 2017-09-22 | 2018-02-09 | 武汉精测电子技术股份有限公司 | Sorting technique and device the defects of L0 pictures in a kind of AOI detection |
CN107843599A (en) * | 2017-10-24 | 2018-03-27 | 武汉精测电子集团股份有限公司 | The methods of a kind of panel detection based on AOI is sentenced and device |
CN108827970A (en) * | 2018-03-28 | 2018-11-16 | 武汉精测电子集团股份有限公司 | Adaptation different panels defect based on AOI system the methods of sentences automatically and system |
CN108961238A (en) * | 2018-07-02 | 2018-12-07 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
CN109167928A (en) * | 2018-09-06 | 2019-01-08 | 武汉精测电子集团股份有限公司 | Fast automatic exposure method and system based on defects of display panel detection |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110186938A (en) * | 2019-06-28 | 2019-08-30 | 笪萨科技(上海)有限公司 | Two-sided defect analysis equipment and defects detection and analysis system |
CN110458840A (en) * | 2019-10-12 | 2019-11-15 | 武汉精立电子技术有限公司 | A kind of method, system and terminal device for reducing panel defect and crossing inspection rate |
CN110458840B (en) * | 2019-10-12 | 2020-01-14 | 武汉精立电子技术有限公司 | Method, system and terminal equipment for reducing panel defect over-detection rate |
CN110490875A (en) * | 2019-10-16 | 2019-11-22 | 武汉精立电子技术有限公司 | A kind of screen defect filter method, device and storage medium |
CN110490875B (en) * | 2019-10-16 | 2020-01-21 | 武汉精立电子技术有限公司 | Screen defect filtering method and device and storage medium |
CN111474181A (en) * | 2020-03-31 | 2020-07-31 | 成都数之联科技有限公司 | Panel defect detecting and classifying system in box forming process stage |
CN111735823A (en) * | 2020-07-17 | 2020-10-02 | 武汉精立电子技术有限公司 | Defect detection method and system for module |
CN112394064A (en) * | 2020-10-22 | 2021-02-23 | 惠州高视科技有限公司 | Point-line measuring method for screen defect detection |
CN112634258A (en) * | 2020-12-30 | 2021-04-09 | 凌云光技术股份有限公司 | Automatic classification and classification method and device for defect detection based on AOI |
WO2022150986A1 (en) * | 2021-01-12 | 2022-07-21 | 深圳市艾比森光电股份有限公司 | Image quality inspection method and related product for led display screen |
CN112881419A (en) * | 2021-05-06 | 2021-06-01 | 惠州高视科技有限公司 | Chip detection method, electronic device and storage medium |
CN112881419B (en) * | 2021-05-06 | 2024-01-30 | 高视科技(苏州)股份有限公司 | Chip detection method, electronic device and storage medium |
CN113824827A (en) * | 2021-09-20 | 2021-12-21 | 苏州凯仕弘科技有限公司 | Visual detection system for mobile phone screen |
CN113592859A (en) * | 2021-09-26 | 2021-11-02 | 中导光电设备股份有限公司 | Deep learning-based classification method for defects of display panel |
CN115131327A (en) * | 2022-07-14 | 2022-09-30 | 电子科技大学 | Color feature fused display screen color line defect detection method |
CN115131327B (en) * | 2022-07-14 | 2024-04-30 | 电子科技大学 | Color line defect detection method for display screen with fused color features |
CN117056148A (en) * | 2023-08-30 | 2023-11-14 | 昆山迈致治具科技有限公司 | Method for detecting abnormal display of screen |
CN117056148B (en) * | 2023-08-30 | 2024-02-09 | 昆山迈致治具科技有限公司 | Method for detecting abnormal display of screen |
CN117115147A (en) * | 2023-10-19 | 2023-11-24 | 山东华盛创新纺织科技有限公司 | Textile detection method and system based on machine vision |
CN117115147B (en) * | 2023-10-19 | 2024-01-26 | 山东华盛创新纺织科技有限公司 | Textile detection method and system based on machine vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109856156A (en) | A kind of display panel tiny flaw determination method and device based on AOI | |
US11774735B2 (en) | System and method for performing automated analysis of air samples | |
US11915407B2 (en) | Automated system and method for clarity measurements and clarity grading | |
CN110047073B (en) | X-ray weld image defect grading method and system | |
CN105335963A (en) | Edge defect detection method and apparatus | |
CN108355987A (en) | A kind of screen printing of battery quality determining method based on piecemeal template matches | |
CN103502801B (en) | Defect classification method and classification of defects system | |
CN112053318A (en) | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning | |
CN104484878B (en) | The automatic testing method of defects of display panel | |
CN110044405B (en) | Automatic automobile instrument detection device and method based on machine vision | |
CN108355981A (en) | A kind of battery connector quality determining method based on machine vision | |
WO2007074770A1 (en) | Defect inspection device for inspecting defect by image analysis | |
CN108764134A (en) | A kind of automatic positioning of polymorphic type instrument and recognition methods suitable for crusing robot | |
CN109886960A (en) | The method of glass edge defects detection based on machine vision | |
CN107664644A (en) | A kind of apparent automatic detection device of object based on machine vision and method | |
CN108416765A (en) | A kind of character defect automatic testing method and system | |
CN106872488A (en) | A kind of double surface defect visible detection methods of rapid large-area transparent substrate and device | |
CN109461156A (en) | The threaded closure plug assembly and detection method of view-based access control model | |
CN112129783A (en) | Transparent medicine bottle bottom defect detection device and detection method based on deep learning | |
CN114428110A (en) | Method and system for detecting defects of fluorescent magnetic powder inspection image of bearing ring | |
WO2021046726A1 (en) | Method and device for detecting mechanical equipment parts | |
CN106501278B (en) | Surface of the light tube defect classification method and system based on invariable rotary textural characteristics | |
CN107239743B (en) | automatic detection method for scale mark reading based on projection method | |
CN116091506B (en) | Machine vision defect quality inspection method based on YOLOV5 | |
CN113176275A (en) | Method, device and system for retesting display panel |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190607 |
|
RJ01 | Rejection of invention patent application after publication |