CN109765245B - Large-size display screen defect detection and positioning method - Google Patents
Large-size display screen defect detection and positioning method Download PDFInfo
- Publication number
- CN109765245B CN109765245B CN201910139404.1A CN201910139404A CN109765245B CN 109765245 B CN109765245 B CN 109765245B CN 201910139404 A CN201910139404 A CN 201910139404A CN 109765245 B CN109765245 B CN 109765245B
- Authority
- CN
- China
- Prior art keywords
- screen
- display screen
- picture
- detected
- image
- 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.)
- Active
Links
Images
Landscapes
- Controls And Circuits For Display Device (AREA)
- Testing Of Optical Devices Or Fibers (AREA)
- Liquid Crystal Display Device Control (AREA)
Abstract
The invention relates to the technical field of display screens, in particular to a large-size display screen defect detection and positioning method. Displaying a screen calibration picture on a reference display screen, and collecting a screen calibration picture image; acquiring an offline calibration parameter for identifying reference position information from a screen calibration picture image; sequentially displaying each detection picture on a display screen to be detected, and performing online compensation on the position of the display screen to be detected by using an offline calibration parameter to obtain a position parameter of the display screen to be detected; analyzing each collected detection picture to obtain image coordinates of the defects; and converting the image coordinates of the defects into screen coordinates according to the position parameters of the display screen to be detected. The screen calibration picture is not required to be displayed and the angle point information of the sub-picture is not required to be extracted, the first detection picture is compensated through the offline calibration parameters, the screen to-be-detected area of the panel in the accurately-positioned image can be determined, the method is simple and rapid, and the AOI work station detection time can be effectively saved.
Description
Technical Field
The invention relates to the technical field of display screens, in particular to a large-size display screen defect detection and positioning method.
Background
In the field of novel display screen detection of LCDs, OLEDs and the like, the display screen is large in size, for example, 4K (3840 × 2460) and 8K (7680 × 4320) display screens are large-size display screens. For the measured object to be shot more clearly, 1 display screen pixel point at least corresponds to 9 camera pixel points, and then the screen pixel point defect can be shot effectively. Therefore, the resolution of a single vision sensor cannot effectively photograph a large-sized LCD display screen. The plurality of vision sensors divide the display screen into a plurality of areas to be detected, each vision sensor correspondingly shoots the area of the screen and detects the area, and the detection result of each sensor is obtained through detection. The detection result includes the pixel coordinate of the camera where the defect is located, the defect area and the defect intensity. In the invention, the defect positioning refers to positioning the image coordinates of the defects to the screen coordinates, and the large-size display screen refers to a display screen of which the visual sensor cannot shoot a complete screen.
In the invention, red (R), green (G) and blue (B) are three primary colors, and the adjusting ranges are respectively 0-255. Different values are set for RGB respectively, so that different pictures can be matched.
W255, RGB values are 255, RGB (255,0,0) picture;
r255: monochrome red, with a red value of 255, RGB (255,0,0) picture;
g255: monochrome green, and the value of green is 255, RGB (0,255,0) picture;
b255: monochrome blue, and the value of blue is 255, RGB (0, 255) picture;
l0: black, RGB values are all 0;
l48: 48 gray scale pictures, wherein the RGB values are all 48, and the RGB (48,48,48) pictures are obtained;
the pictures to be detected are divided into R255, G255, B255, L48, L0, L127, L255 and the like.
In the existing defect detection process of the large-size display screen, the point of the panel entering the detection station has slight deviation. As shown in fig. 4, in order to achieve the accuracy of displaying defects at the human inspection station, when each panel is inspected, a screen positioning pattern needs to be shot once, and after all corner points of each sub-picture of the panel are positioned according to the screen positioning pattern, the inspection picture can be switched to perform subsequent defect inspection. The corner positions of the sub-pictures of the panel are repositioned during the detection of each panel, so that the detection time of the AOI work station is prolonged.
In addition, in the existing detection process, the defect coordinates are image coordinates, and the defect coordinates have the defects of complexity and low robustness in the positioning process.
Disclosure of Invention
The invention aims to provide a method for detecting and positioning defects of a large-size display screen, which greatly improves the detection efficiency aiming at the defects of the prior art.
The technical scheme of the invention is as follows: a defect detection and positioning method for a large-size display screen comprises the steps of taking a display screen as a reference display screen to move to a detection station, and taking the position of the reference display screen on the detection station as a reference position;
displaying a screen calibration picture on the reference display screen, and acquiring a screen calibration picture image by utilizing a plurality of visual sensors;
acquiring an offline calibration parameter for identifying reference position information from the screen calibration picture image;
moving a display screen to be detected to a detection station, sequentially displaying detection pictures on the display screen to be detected, and acquiring detection picture images by using a plurality of visual sensors, wherein after a first detection picture image is acquired, online compensation is performed on the position of the display screen to be detected by using the offline calibration parameters to obtain position parameters of the display screen to be detected;
analyzing each collected detection picture to obtain image coordinates of the defects;
and converting the image coordinates of the defects into screen coordinates according to the position parameters of the display screen to be detected.
Preferably, the screen calibration picture of the display screen is an equally divided picture, the number of sub-pictures in the equally divided picture is the same as the number of adopted visual sensors, and the shooting area of each visual sensor uniquely corresponds to one sub-picture.
Preferably, the offline calibration parameters include a sub-pixel coordinate position C _ SP1 corresponding to a screen zero point SP1 of the reference display screen in the image and a screen area width G exceeding a corresponding detection area in a visual field of the visual sensor in the reference display screen, and the position parameters of the display screen to be detected include a single-side width G' exceeding a shooting area of any visual sensor in the display screen to be detected.
Preferably, the online compensation of the position of the display screen to be detected by using the offline calibration parameter to obtain the position parameter of the display screen to be detected includes:
calculating the offset between the sub-pixel coordinate position C _ SP1 corresponding to the screen zero point SP1 of the reference display screen in the image and the sub-pixel coordinate position CC _ SP1 corresponding to the screen zero point SP1 of the display screen to be detected in the image;
and compensating the screen area width G exceeding the corresponding detection area in the visual field of the visual sensor in the reference display screen by using the offset to obtain the screen area width G' exceeding the corresponding detection area in the visual field of the visual sensor in the display screen to be detected.
Preferably, after the first detection picture image is acquired, the screen ROI region is extracted from the first detection picture image, and then the offline calibration parameter is used to perform online compensation on the position of the display screen to be detected.
Preferably, the step of converting the image coordinate of the defect into the screen coordinate according to the position parameter of the display screen to be detected includes:
subtracting G' from the ROI area of the screen to obtain an area to be detected of the image;
and converting the image coordinates of the defects into screen coordinates according to the mapping relation between the to-be-detected area of the image and the corresponding to-be-detected screen area.
Preferably, the extracting the screen ROI region from the first detection screen image includes:
roughly extracting a screen ROI (region of interest) through self-adaptive threshold segmentation;
judging the abnormality of the ROI area of the screen;
the root extracts the screen sub-pixel corner information from the screen ROI area.
Preferably, the resolution of the screen calibration picture is the same as the resolution of the display screen.
Preferably, the equally divided pictures are black-white spaced pictures, any one of the sub-pictures is a single black picture or a single white picture, and any one of the sub-pictures has a different color from the adjacent sub-pictures.
Preferably, in the process of extracting the sub-pixel corner information of the screen from the ROI area of the screen:
extracting sub-pixel corner information of a screen by using a Harris corner algorithm in the corner region;
and if the extraction fails, extracting the sub-pixel corner information of the screen by using a mode of solving intersection points by edge line fitting.
The invention has the beneficial effects that:
1. the method comprises the steps of utilizing a reference panel to obtain offline calibration parameters in advance, in the subsequent detection process, not displaying a screen calibration picture and extracting corner point information of a sub-picture, compensating a first detection picture through a screen zero point (namely a position anchor point) and G in the offline calibration parameters, determining a screen to-be-detected area of the panel in an accurate positioning image, and further accurately positioning the position of a defect in the screen. The method is simple and rapid, and can effectively save AOI (Automatic optical Inspection) station detection time.
2. And converting image coordinates obtained by defect detection into screen coordinates according to the information of the screen to-be-detected area of the panel in the accurately positioned image, so as to facilitate subsequent manual secondary detection. This mode makes single intellectual detection system effectively combine with artifical secondary detection, saves station detection pressure, makes display screen quality testing efficiency and product quality promote accuse greatly simultaneously.
3. Extracting sub-pixel corner information of a screen by using a Harris corner algorithm in the corner region; if the extraction fails, the screen sub-pixel angular point information is extracted by using a mode of solving intersection points through edge line fitting, so that the precision of defect positioning and the robustness of the defect positioning are improved.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram illustrating a display screen displaying image switching during a detection process according to the present invention;
FIG. 3 is a diagram illustrating a screen calibration screen according to the present invention;
fig. 4 is a schematic diagram illustrating a display screen switching during conventional AOI detection.
Detailed Description
The invention will be further described in detail with reference to the following drawings and specific examples, which are not intended to limit the invention, but are for clear understanding.
As shown in fig. 1, a flow of a method for detecting and positioning defects of a large-size display screen is illustrated, in this embodiment, a liquid crystal display is used for description:
1. and calibrating the multi-vision sensor off line.
And moving one liquid crystal screen as a reference liquid crystal screen (usually, the first liquid crystal screen to be detected is selected as the reference liquid crystal screen) to a detection station, and taking the position of the reference liquid crystal screen on the detection station as a reference position.
And displaying a screen calibration picture on the reference liquid crystal screen, and acquiring a screen calibration picture image by using a plurality of visual sensors. The screen calibration picture image is used for displaying the area of the screen corresponding to each specified sensor. The screen calibration picture is an equal division picture (usually a black and white interval picture, and a line can be drawn at the intersection of the areas for marking), the number of sub-pictures in the equal division picture is the same as the number of the adopted visual sensors, and the shooting area of each visual sensor uniquely corresponds to one sub-picture. The resolution of the screen calibration picture is the same as that of the liquid crystal screen. In this embodiment, the equally divided frames are black and white frames, any one of the sub-frames is a single black frame or a single white frame, and any one of the sub-frames has a different color from the adjacent sub-frames, which is shown in fig. 2 as a black and white frame.
And acquiring offline calibration parameters for identifying reference position information from the screen calibration picture image in the figure 2 by using a visual sensor. The method mainly comprises a sub-pixel coordinate position C _ SP1 corresponding to a screen zero point SP1 (the point is a coordinate anchor point selected by the scheme) of a reference liquid crystal screen in an image and a screen area width G exceeding a corresponding detection area in the visual field of a visual sensor in the reference liquid crystal screen. Besides, it also includes SP2, SP2 ', SP3, SP3 ', SP4 ' information, and the sub-pixel coordinates C _ SP2, C _ SP2 ', C _ SP3, C _ SP3 ', C _ SP4 ' of the points SP2, SP2 ', SP3, SP3 ', SP4 ' in the image. The significance of extracting the camera pixel coordinate where the zero point coordinate of the screen coordinate is located is to set the point coordinate as an anchor point, and when the panel enters the detection platform stage to slightly deviate during online detection, the coordinate difference between the panel and the calibration is calculated and compensated.
In this embodiment, the screen area width G exceeding its corresponding detection area in the field of view of the visual sensor in the liquid crystal panel is taken as the area between SP2 and SP2 ', i.e., G — C _ SP 2'. C _ SP2.x is a lateral coordinate value of the point C _ SP2 in the image coordinate system, and C _ SP2 'x is a lateral coordinate value of the point C _ SP 2' in the image coordinate system.
The regions SP2 and SP2 'correspond to the overlapping region between CAM2 and CAM1, and the regions SP3 and SP 3' correspond to the overlapping region between CAM2 and CAM 3. The black area in the figure corresponds to the area of the screen to be inspected of CAM 2. After image capture, extracting a sub-pixel coordinate C _ SP1 of an SP1 coordinate in an image; the sub-pixel coordinates of the points SP2, SP2 ', SP3, SP 3', SP4 'in the image C _ SP2, C _ SP 2', C _ SP3, C _ SP3 ', C _ SP 4' are extracted. The width of the overlapping region of CAM2 and CAM1 is defined as G ═ C _ SP 2'. C _ SP2.x is a lateral coordinate value of the point C _ SP2 in the image coordinate system.
2. The multi-vision sensor compensates online.
Moving the liquid crystal screen to be detected to a detection station, as shown in fig. 3, sequentially displaying each detection picture on the liquid crystal screen to be detected, and acquiring each detection picture image by using a plurality of visual sensors. The first detection picture is a W255 picture, the screen brightness is stable, fluctuation caused by the influence of panel Gamma is avoided, and corner extraction errors caused by the fluctuation of the screen brightness are eliminated. After the image of the detection picture is acquired, anchor point extraction, screen ROI (region of interest) extraction, image detection preprocessing and enhancement processing are carried out on the image.
And (3) extracting an anchor point, namely extracting the picture sub-pixel coordinate CC _ SP1 of SP1 of the liquid crystal panel to be detected, wherein the coordinate is (x ', y').
The process of extracting the ROI area of the screen comprises the steps of extracting sub-pixel corners of the ROI area of the screen from a detection picture (W255 picture), wherein the process comprises the following steps:
self-adaptive threshold segmentation and rough extraction of a screen region of interest;
judging the abnormality of the screen area: the method comprises rectangle degree judgment and effective area judgment to eliminate abnormal conditions of screen display;
extracting sub-pixel corner information of a screen by using a Harris corner algorithm in the corner region according to the coarse positioning information; if the extraction fails, extracting the sub-pixel angular point information of the screen in a mode of solving an intersection point by edge line fitting;
and outputting a corner point extraction result.
And then, performing online compensation on the position of the liquid crystal screen to be detected by using the offline calibration parameters to obtain the position parameters of the liquid crystal screen to be detected. The position parameters include the single-side width G 'of any visual sensor in the liquid crystal panel to be detected beyond the shooting area, which is the area between SP2 and SP 2' in this embodiment. The online compensation process is as follows:
and calculating the offset between the corresponding sub-pixel coordinate position C _ SP1 of the screen zero point SP1 of the reference liquid crystal screen and the corresponding sub-pixel coordinate position CC _ SP1 of the screen zero point SP1 of the liquid crystal screen to be detected in the image. The C _ SP1 image coordinates are defined as (x, y), the CC _ SP1 coordinates are defined as (x ', y'), and the coordinate shift amount thereof is defined as (Δ x, Δ y) ═ x-x ', y-y').
And compensating the screen area width G exceeding the corresponding detection area in the visual field of the visual sensor in the reference liquid crystal screen by using the offset to obtain the screen area width G' exceeding the corresponding detection area in the visual field of the visual sensor in the liquid crystal screen to be detected. G ═ C _ SP 2'. x + Δ x-C _ sp2. x. In CAM2, when C _ sp2.x is 0, the overlapping region width is G '═ C _ SP 2'. x + Δ x.
3. And (4) transforming the image coordinate system where the defect is located into a screen coordinate system.
And analyzing each collected detection picture to obtain the image coordinates of the defects. Subtracting G' from the ROI area of the screen to obtain an area to be detected of the image;
and converting the image coordinates of the defects into screen coordinates according to the mapping relation between the to-be-detected area of the image and the corresponding to-be-detected screen area.
In Cam2, the area to be detected on the screen is a black area, and the corner points SP2 'and SP 3' in the screen coordinate system are known when the calibration pattern is made. Sp2 'coordinate is set to (x'2,y'2) Sp3 'coordinate is set to (x'3,y'3) Sp4 'coordinate is set to (x'4,y'4). The defect coordinate is set to (x)d,yd). The coordinates in the screen where the defect in Cam2 is located are:
according to the geometric scaling formula, the coordinate position of the defect in the image in the screen can be solved.
Details not described in this specification are within the skill of the art that are well known to those skilled in the art.
Claims (8)
1. A method for detecting and positioning defects of a large-size display screen is characterized by comprising the following steps:
moving one display screen serving as a reference display screen to a detection station, and taking the position of the reference display screen on the detection station as a reference position;
displaying a screen calibration picture on the reference display screen, and acquiring a screen calibration picture image by utilizing a plurality of visual sensors;
acquiring an offline calibration parameter for identifying reference position information from the screen calibration picture image;
moving a display screen to be detected to a detection station, sequentially displaying detection pictures on the display screen to be detected, and acquiring detection picture images by using a plurality of visual sensors, wherein after a first detection picture image is acquired, online compensation is performed on the position of the display screen to be detected by using the offline calibration parameters to obtain position parameters of the display screen to be detected;
analyzing each collected detection picture to obtain image coordinates of the defects;
converting the image coordinates of the defects into screen coordinates according to the position parameters of the display screen to be detected;
the offline calibration parameters comprise a sub-pixel coordinate position C _ SP1 corresponding to a screen zero point SP1 of a reference display screen in an image and a screen area width G exceeding a corresponding detection area in the visual field of a visual sensor in the reference display screen, and the position parameters of the display screen to be detected comprise a single-side width G' exceeding a shooting area of any visual sensor in the display screen to be detected;
the online compensation of the position of the display screen to be detected by using the offline calibration parameters to obtain the position parameters of the display screen to be detected comprises the following steps:
calculating the offset between the sub-pixel coordinate position C _ SP1 corresponding to the screen zero point SP1 of the reference display screen in the image and the sub-pixel coordinate position CC _ SP1 corresponding to the screen zero point SP1 of the display screen to be detected in the image;
and compensating the screen area width G exceeding the corresponding detection area in the visual field of the visual sensor in the reference display screen by using the offset to obtain the screen area width G' exceeding the corresponding detection area in the visual field of the visual sensor in the display screen to be detected.
2. The method for detecting and positioning the defects of the large-size display screen as claimed in claim 1, wherein: the screen calibration picture of the display screen is an equally divided picture, the number of sub-pictures in the equally divided picture is the same as that of the adopted visual sensors, and the shooting area of each visual sensor uniquely corresponds to one sub-picture.
3. The method as claimed in claim 1, wherein after the first inspection image is captured, the ROI area of the screen is extracted from the first inspection image, and then the offline calibration parameters are used to perform online compensation on the position of the display screen to be inspected.
4. The method as claimed in claim 3, wherein the step of converting the image coordinates of the defect into screen coordinates according to the position parameters of the display to be detected comprises:
subtracting G' from the ROI area of the screen to obtain an area to be detected of the image;
and converting the image coordinates of the defects into screen coordinates according to the mapping relation between the to-be-detected area of the image and the corresponding to-be-detected screen area.
5. The method as claimed in claim 3, wherein the step of extracting the ROI area of the screen from the first inspection image comprises:
roughly extracting a screen ROI (region of interest) through self-adaptive threshold segmentation;
judging the abnormality of the ROI area of the screen;
and extracting the sub-pixel corner information of the screen from the ROI area of the screen.
6. The method for detecting and positioning the defects of the large-size display screen as claimed in claim 1, wherein: the resolution of the screen calibration picture is the same as the resolution of the display screen.
7. The method for detecting and positioning the defects of the large-size display screen as claimed in claim 2, wherein: the equally divided pictures are pictures with black and white intervals, any one sub-picture is a single black picture or a single white picture, and the color of any one sub-picture is different from that of the adjacent sub-pictures.
8. The method for detecting and positioning the defects of the large-size display screen as claimed in claim 5, wherein in the process of extracting the sub-pixel corner information of the screen from the ROI area of the screen:
extracting sub-pixel corner information of a screen by using a Harris corner algorithm in the corner region;
and if the extraction fails, extracting the sub-pixel corner information of the screen by using a mode of solving intersection points by edge line fitting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910139404.1A CN109765245B (en) | 2019-02-25 | 2019-02-25 | Large-size display screen defect detection and positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910139404.1A CN109765245B (en) | 2019-02-25 | 2019-02-25 | Large-size display screen defect detection and positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109765245A CN109765245A (en) | 2019-05-17 |
| CN109765245B true CN109765245B (en) | 2021-08-13 |
Family
ID=66457252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910139404.1A Active CN109765245B (en) | 2019-02-25 | 2019-02-25 | Large-size display screen defect detection and positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109765245B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110213664B (en) * | 2019-07-05 | 2021-06-22 | 四川长虹电器股份有限公司 | Device and method for adjusting driving parameters of display panel |
| CN110987926A (en) * | 2019-11-13 | 2020-04-10 | 上海大学 | Automatic display screen defect detection method based on machine vision |
| CN111292302B (en) * | 2020-01-21 | 2022-12-27 | 上海万物新生环保科技集团有限公司 | Screen detection method and device |
| CN111325716B (en) * | 2020-01-21 | 2023-09-01 | 上海万物新生环保科技集团有限公司 | Screen scratch and fragmentation detection method and equipment |
| CN111325717B (en) * | 2020-01-21 | 2023-08-29 | 上海万物新生环保科技集团有限公司 | Mobile phone defect position identification method and equipment |
| CN111473957B (en) * | 2020-03-24 | 2022-03-22 | 深圳同兴达科技股份有限公司 | Display screen partition detection method |
| CN111563883B (en) * | 2020-04-22 | 2023-05-05 | 惠州旭鑫智能技术有限公司 | Screen vision positioning method, positioning equipment and storage medium |
| CN114693583A (en) * | 2020-12-15 | 2022-07-01 | 奕目(上海)科技有限公司 | Defect layering detection method and system based on light field camera and detection production line |
| CN112858331A (en) * | 2021-02-20 | 2021-05-28 | 歌尔光学科技有限公司 | VR screen detection method and detection system |
| CN113237888B (en) * | 2021-05-21 | 2022-06-14 | 哈尔滨工业大学 | Large-caliber optical element damage point online and offline dark field image matching method |
| CN113269762B (en) * | 2021-05-31 | 2024-01-09 | 苏州华兴源创科技股份有限公司 | Screen defect detection method, system and computer storage medium |
| CN115018815A (en) * | 2022-06-29 | 2022-09-06 | 京东方科技集团股份有限公司 | Fault detection method and device of display screen and inspection robot |
| CN115456956A (en) * | 2022-08-19 | 2022-12-09 | 浙江华周智能装备有限公司 | Method and device for detecting scratches of liquid crystal display and storage medium |
| CN116245950B (en) * | 2023-05-11 | 2023-08-01 | 合肥高维数据技术有限公司 | Screen corner positioning method for full screen or single corner deletion |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002140713A (en) * | 2000-11-02 | 2002-05-17 | Omron Corp | Image processing method and image processor |
| CN1614551A (en) * | 2003-11-04 | 2005-05-11 | 威达电股份有限公司 | Computer system and method for correcting digital plate without correcting software |
| CN102109963A (en) * | 2011-03-25 | 2011-06-29 | 威盛电子股份有限公司 | Method for cursor positioning on screen |
| CN103559857A (en) * | 2013-10-31 | 2014-02-05 | 桂林机床电器有限公司 | Method and device for OLED screen pixel defect detection |
| CN104359402A (en) * | 2014-11-17 | 2015-02-18 | 南京工业大学 | Detection method for rectangular pin component visual positioning |
| DE102013109915B4 (en) * | 2013-09-10 | 2015-04-02 | Thyssenkrupp Steel Europe Ag | Method and device for checking an inspection system for detecting surface defects |
| CN104613957A (en) * | 2015-01-30 | 2015-05-13 | 广东威创视讯科技股份有限公司 | Stage laser positioning calibration device and stage laser positioning calibration method |
| CN106442560A (en) * | 2016-08-23 | 2017-02-22 | 汕头大学 | Positioning measurement and defect detection method of display screen |
| CN106815808A (en) * | 2017-01-20 | 2017-06-09 | 长沙全度影像科技有限公司 | A kind of image split-joint method of utilization piecemeal computing |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10192301B1 (en) * | 2017-08-16 | 2019-01-29 | Siemens Energy, Inc. | Method and system for detecting line defects on surface of object |
-
2019
- 2019-02-25 CN CN201910139404.1A patent/CN109765245B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002140713A (en) * | 2000-11-02 | 2002-05-17 | Omron Corp | Image processing method and image processor |
| CN1614551A (en) * | 2003-11-04 | 2005-05-11 | 威达电股份有限公司 | Computer system and method for correcting digital plate without correcting software |
| CN102109963A (en) * | 2011-03-25 | 2011-06-29 | 威盛电子股份有限公司 | Method for cursor positioning on screen |
| DE102013109915B4 (en) * | 2013-09-10 | 2015-04-02 | Thyssenkrupp Steel Europe Ag | Method and device for checking an inspection system for detecting surface defects |
| CN103559857A (en) * | 2013-10-31 | 2014-02-05 | 桂林机床电器有限公司 | Method and device for OLED screen pixel defect detection |
| CN104359402A (en) * | 2014-11-17 | 2015-02-18 | 南京工业大学 | Detection method for rectangular pin component visual positioning |
| CN104613957A (en) * | 2015-01-30 | 2015-05-13 | 广东威创视讯科技股份有限公司 | Stage laser positioning calibration device and stage laser positioning calibration method |
| CN106442560A (en) * | 2016-08-23 | 2017-02-22 | 汕头大学 | Positioning measurement and defect detection method of display screen |
| CN106815808A (en) * | 2017-01-20 | 2017-06-09 | 长沙全度影像科技有限公司 | A kind of image split-joint method of utilization piecemeal computing |
Non-Patent Citations (2)
| Title |
|---|
| 图像的角点检测研究综述;章为川等;《电子学报》;20151130;第43卷(第11期);第2315-2321页 * |
| 用于大视场三维探测的人工复眼系统几何标定;简慧杰等;《光学学报》;20170228;第37卷(第2期);第0215002-1至9页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109765245A (en) | 2019-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109765245B (en) | Large-size display screen defect detection and positioning method | |
| CN108760767B (en) | Large-size liquid crystal display defect detection method based on machine vision | |
| CN108682365B (en) | OLED color spot detection and repair integrated system and method | |
| EP3171588B1 (en) | Image processing method and image processing apparatus executing that image processing method | |
| WO2010146732A1 (en) | Defect inspection method and defect inspection device for display panel | |
| CN109471276B (en) | Method and device for detecting color cast defect of liquid crystal display | |
| WO2010146733A1 (en) | Defect inspection method and defect inspection device for display panel | |
| JP2011196685A (en) | Defect detection device, defect repairing device, display panel, display device, defect detection method and program | |
| CN107613229A (en) | A kind of dead pixels of image sensor surveys means for correcting and method | |
| CN112669394A (en) | Automatic calibration method for vision detection system | |
| CN112885289B (en) | Display screen calibration method and device | |
| CN114495803A (en) | Mura repairing method of display panel | |
| CN109993745A (en) | It is a kind of for detecting the detection method of OLED display module undesirable feature | |
| JP4534825B2 (en) | Defect inspection method and defect inspection apparatus | |
| JP2014164221A (en) | Defect detection method for display panel and defect detection device for display panel | |
| JP2009229197A (en) | Linear defect detecting method and device | |
| JP2002267574A (en) | Colorimetry device for color display device, colorimetry, image quality adjustment/inspection device, and image quality adjustment/inspection method | |
| CN110060625B (en) | LED display screen acquisition vignetting compensation method | |
| CN108986721B (en) | Detection graph generation method for display panel detection | |
| CN106405894A (en) | Automatic defect positioning method of liquid crystal panel | |
| CN207283689U (en) | A kind of dead pixels of image sensor surveys means for correcting | |
| CN113271460B (en) | Dynamic image detection method and detection system | |
| CN114937429A (en) | Method for detecting brightness uniformity of display | |
| KR102613416B1 (en) | Method For Processing Compensation Display Defect And Display Device Using The Same | |
| CN108803097A (en) | The detection method and detection device of pixel dark-state light leakage |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |