CN109765245A - Large scale display screen defects detection localization method - Google Patents
Large scale display screen defects detection localization method Download PDFInfo
- Publication number
- CN109765245A CN109765245A CN201910139404.1A CN201910139404A CN109765245A CN 109765245 A CN109765245 A CN 109765245A CN 201910139404 A CN201910139404 A CN 201910139404A CN 109765245 A CN109765245 A CN 109765245A
- Authority
- CN
- China
- Prior art keywords
- screen
- display screen
- picture
- detected
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Testing Of Optical Devices Or Fibers (AREA)
- Liquid Crystal Display Device Control (AREA)
- Controls And Circuits For Display Device (AREA)
Abstract
The present invention relates to display screen technology fields, and in particular to a kind of large scale display screen defects detection localization method.Show that screen demarcates picture on reference display screen, acquisition screen demarcates picture image；The off-line calibration parameter for identifying reference position information is obtained from screen calibration picture image；Each detection picture is successively shown on display screen to be detected, is carried out online compensation using position of the off-line calibration parameter to display screen to be detected, is obtained the location parameter of display screen to be detected；Each detection picture of acquisition is analyzed, the image coordinate of defect is obtained；According to the location parameter of display screen to be detected, screen coordinate is converted by the image coordinate of defect.It no longer needs to display screen calibration picture and extracts sprite angle point information, first detection picture is compensated by the off-line calibration parameter, it can determine screen to be checked region of the panel in accurate positioning image, it is simple and fast, it can effectively save AOI station detection time.
Description
Technical field
The present invention relates to display screen technology fields, and in particular to a kind of large scale display screen defects detection localization method.
Background technique
In the new-type display screens detection field such as LCD, OLED, size is larger, as 4K (3840*2460), 8K (7680 ×
4320) display screen is large scale display screen.To be more clear testee shooting, 1 display screen pixels point is at least right
Screen pixels point defect could should be effectively shot in 9 camera pixel points.Therefore, the resolution ratio of single visual sensor
Large-scale LCD display screen cannot effectively be shot.Multiple visual sensors, which refer to, is divided into several area to be tested for display screen, often
A visual sensor corresponds to the region of photographed screen and detection, and detection obtains the testing result of each sensor.Testing result packet
Pixel coordinate containing defective place camera, the intensity of defect area and defect.In the present invention, defect location refers to defect
Image coordinate navigates to screen coordinate, and large scale display screen refers to that a visual sensor can not shoot the display screen of complete screen.
In the present invention, red (R), green (G), blue (B) are three primary colours, and adjustable range is respectively 0-255.Respectively RGB setting
Different values can arrange in pairs or groups out different pictures.
The value of W255:RGB is 255, RGB (255,0,0) picture；
R255: it is monochromatic red, and red value is 255, RGB (255,0,0) picture；
G255: it is monochromatic green, and the value of green is 255, RGB (0,255,0) picture；
B255: it is monochromatic blue, and the value of blue is 255, RGB (0,0,255) picture；
L0: black, the value of RGB are all 0；
L48:48 grey menu, the value of RGB are 48, RGB (48,48,48) picture；
Picture to be detected is divided into R255, G255, B255, L48, L0, L127, L255 etc..
In existing large scale display screen defects detection process, due to the point that panel enters detection station have it is subtle partially
It moves.As shown in figure 4, being required to shoot when each panel is detected to reach defect in the accuracy that people's inspection station is shown
One secondary screen positions pattern, and is positioned after pattern orients all angle points of each sprite of panel according to the screen, could switch
Picture is detected, subsequent defects detection is carried out.The corner location that panel sprite is relocated in each panel detection, increases
The detection time of AOI station is added.
In addition, defect coordinate is image coordinate in existing testing process, there is complicated, robustness in position fixing process
Not high disadvantage.
Summary of the invention
The purpose of the present invention is to the defects of the prior art, and it is aobvious to provide a kind of large scale that detection efficiency greatly improves
Display screen defects detection localization method.
The technical solution of the present invention is as follows: a kind of large scale display screen defects detection localization method, one piece of display screen is made
To be moved to detection station with reference to display screen, and this is referred into position of the display screen in detection station as reference position；
It shows that screen demarcates picture on the reference display screen, and demarcates picture using multiple visual sensors acquisition screen
Face image；
The off-line calibration parameter for identifying reference position information is obtained from screen calibration picture image；
Display screen to be detected is moved to detection station, each detection picture is successively shown on display screen to be detected, and
Multiple visual sensors are utilized to acquire each detection picture image, wherein after first detection picture image of acquisition, using described
Off-line calibration parameter carries out online compensation to the position of the display screen to be detected, obtains the location parameter of display screen to be detected；
Each detection picture of acquisition is analyzed, the image coordinate of defect is obtained；
According to the location parameter of the display screen to be detected, screen coordinate is converted by the image coordinate of defect.
It is more preferred, the split screen such as the screen calibration picture of the display screen is, the split screen neutron frame numbers such as described
Amount is identical as the visual sensor quantity used, and the shooting area of each visual sensor is uniquely corresponding with a sprite.
It is more preferred, the off-line calibration parameter include with reference to display screen screen zero point SP1 it is corresponding in the picture
Subpixel coordinates position C_SP1 and with reference to screen area beyond its correspondence detection zone in the visual sensor visual field in display screen
Width G, the location parameter of the display screen to be detected include in display screen to be detected any visual sensor beyond its shoot area
The unilateral width G in domain '.
It is more preferred, online compensation is carried out using position of the off-line calibration parameter to the display screen to be detected,
The location parameter for obtaining display screen to be detected includes:
Calculate the screen zero point SP1 corresponding subpixel coordinates position C_SP1 and to be detected in the picture with reference to display screen
The screen zero point SP1 of the display screen offset between corresponding subpixel coordinates position CC_SP1 in the picture；
Using the offset, to the screen for exceeding its correspondence detection zone in the visual sensor visual field in reference display screen
Peak width G is compensated, and obtains the screen for corresponding to detection zone in display screen to be detected in the visual sensor visual field beyond it
Peak width G '.
It is more preferred, after acquiring first detection picture image, screen first is extracted from first detection picture image
ROI region recycles the off-line calibration parameter to carry out online compensation to the position of the display screen to be detected.
It is more preferred, according to the location parameter of the display screen to be detected, screen is converted by the image coordinate of defect
Coordinate includes:
G ' is subtracted in screen ROI region, obtains the area to be tested of image；
According to the mapping relations between the area to be tested of image and corresponding screen area to be detected, by the image of defect
Coordinate transformation is screen coordinate.
More preferred, extracting screen ROI region from first detection picture image includes:
By adaptive threshold fuzziness, coarse extraction is carried out to screen ROI region；
Abnormal judgement is carried out to screen ROI region；
Root extracts screen sub-pix angle point information from screen ROI region.
More preferred, the resolution ratio of the screen calibration picture is identical as the resolution ratio of display screen.
More preferred, the split screen such as described are the picture at black and white interval, any one sprite is single black picture
Or white picture, any one sprite are different from adjacent sprite color.
It is more preferred, during extracting screen sub-pix angle point information from screen ROI region:
Screen sub-pix angle point information is extracted using Harris angle point algorithm in angle point region；
If extracting failure, screen sub-pix angle point information is extracted using the mode that edge line fitting solves intersection point.
The invention has the benefit that
1, off-line calibration parameter is obtained in advance using reference panel, during subsequent detection, no longer need to display screen mark
Determine picture and extract sprite angle point information, by the screen zero point (i.e. location anchors) and G in the off-line calibration parameter, to the
One detection picture compensates, that is, can determine screen to be checked region of the panel in accurate positioning image, further accurate
Position position of the defect in screen.This method is simple and fast, can effectively save AOI (Automatic Optic
Inspection automatic optics inspection) station detection time.
2, according to panel in the screen area information to be checked being accurately positioned in image, the image coordinate that defects detection is obtained
It is converted into screen coordinate, carries out artificial secondary detection convenient for subsequent.Which makes single intelligent measurement and artificial secondary detection
It effectively combines, saves station inspection pressure, while greatly promote display screen quality inspection efficiency and product quality control.
3, screen sub-pix angle point information is extracted using Harris angle point algorithm in angle point region；If extracting failure, make
Screen sub-pix angle point information is extracted with the mode that edge line is fitted solution intersection point, precision and the defect for improving defect location are fixed
The robustness of position.
Detailed description of the invention
Fig. 1 is flow chart of the present invention；
Fig. 2 is that detection process display screen of the present invention shows screen switching schematic diagram；
Fig. 3 is that screen of the present invention demarcates picture drawing；
Fig. 4 is that display screen shows screen switching schematic diagram when existing AOI is detected.
Specific embodiment
The following further describes the present invention in detail with reference to the accompanying drawings and specific embodiments, convenient for this hair is well understood
It is bright, but they limiting the invention.
As shown in Figure 1 be a kind of large scale display screen defects detection localization method process, the present embodiment using liquid crystal display into
Row explanation:
1, multiple vision sensor off-line calibration.
Using one piece of liquid crystal display as with reference to liquid crystal display (generally selecting the liquid crystal display of first piece of detection as with reference to liquid crystal display)
It is moved to detection station, and this is referred into position of the liquid crystal display in detection station as reference position.
It shows that screen demarcates picture on reference liquid crystal display, and demarcates picture figure using multiple visual sensors acquisition screen
Picture.Screen calibration picture image is for showing the region for specifying the corresponding screen of each sensor.It is equal part that screen, which demarcates picture,
Picture (usually black and white interval picture, can also region intersection draw lines indicate), etc. split screen neutron number of pictures and use
Visual sensor quantity it is identical, the shooting area of each visual sensor is uniquely corresponding with a sprite.Screen calibration
The resolution ratio of picture and the resolution ratio of liquid crystal display are identical.In the present embodiment, etc. split screen be black and white interval picture, any one
Sprite is single black picture or white picture, any one sprite is different from adjacent sprite color, is illustrated in figure 2 three
Equal part black and white screen.
Using visual sensor from Fig. 2 screen calibration picture image in obtain for identify reference position information from
Line calibrating parameters.Its mainly include with reference to liquid crystal display screen zero point SP1 (point be this programme choose coordinate anchor point) scheming
As in corresponding subpixel coordinates position C_SP1 and with reference in the visual sensor visual field in liquid crystal display beyond its correspondence detection zone
Screen area width G.In addition to this, further include SP2, SP2 ', SP3, SP3 ', SP4 ' information, and point SP2, SP2 ',
SP3, SP3 ', SP4 ' subpixel coordinates C_SP2, C_SP2 in the picture ', C_SP3, C_SP3 ', C_SP4 '.Wherein, screen is extracted
The meaning of camera pixel coordinate where curtain co-ordinate zero point coordinate is to set the coordinate as anchor point, when on-line checking, panel
When faint offset occurs into detection microscope carrier position, will calculate it with calibration is anchor point coordinate difference, and is compensated by.
In the present embodiment, with reference to the screen area field width for corresponding to detection zone in liquid crystal display in the visual sensor visual field beyond it
Degree G take SP2, SP2 ' between region, i.e. G=C_SP2 ' .x-C_SP2.x.C_SP2.x is point C_SP2 in image coordinate system
Lateral coordinates value, C_SP2 ' .x are lateral coordinates value of the point C_SP2 ' in image coordinate system.
SP2, SP2 ' between region correspond to CAM2 and CAM1 overlapping region, SP3, SP3 ' between region correspond to CAM2 with
The overlapping region of CAM3.Black region corresponds to the screen area to be detected of CAM2 in figure.After capture, extracts SP1 coordinate and scheming
Subpixel coordinates C_SP1 as in；Extract point SP2, SP2 ', SP3, SP3 ', the subpixel coordinates C_SP2 of SP4 ' in the picture,
C_SP2 ', C_SP3, C_SP3 ', C_SP4 '.The overlapping region width of CAM2 and CAM1 is defined as G=C_SP2 ' .x-C_SP2.x.
C_SP2.x is lateral coordinates value of the point C_SP2 in image coordinate system.
2, multiple vision sensor online compensation.
Liquid crystal display to be detected is moved to detection station, as shown in figure 3, successively showing each inspection on liquid crystal display to be detected
Picture is surveyed, and acquires each detection picture image using multiple visual sensors.First detection picture is W255 picture screen
Brightness stability is not influenced by panel Gamma and is fluctuated, angle point grid error caused by excluding because of screen intensity fluctuation.It is acquiring
To after the image of the detection picture, anchor point extraction is carried out to the image, screen ROI region (screen area-of-interest) is extracted and figure
As detection pretreatment and enhancing processing.
Anchor point extract be liquid crystal display panel to be detected SP1 picture subpixel coordinates CC_SP1 extract, coordinate be (x',
y')。
Screen ROI region extraction process includes extracting screen area-of-interest sub-pix angle to detection picture (W255 picture)
Point, process include:
Adaptive threshold fuzziness, screen area-of-interest extract roughly；
Screen area judges extremely: including rectangular degree judgement and effective area judgement, showing abnormal conditions to exclude screen；
According to coarse positioning information, screen sub-pix angle point information is extracted using Harris angle point algorithm in angle point region；If
Failure is extracted, extracts screen sub-pix angle point information using the mode that edge line is fitted solution intersection point；
Angle point result is extracted in output.
Then, online compensation is carried out using position of the off-line calibration parameter to liquid crystal display to be detected, obtains liquid crystal to be detected
The location parameter of screen.The location parameter includes unilateral side width of any visual sensor beyond its shooting area in liquid crystal display to be detected
G ' is spent, is SP2, region between SP2 ' in the present embodiment.Online compensation process is as follows:
Calculate the screen zero point SP1 corresponding subpixel coordinates position C_SP1 and to be detected in the picture with reference to liquid crystal display
The screen zero point SP1 of the liquid crystal display offset between corresponding subpixel coordinates position CC_SP1 in the picture.C_SP1 image is sat
Mark is defined as (x, y), and CC_SP1 coordinate is defined as (x', y'), and coordinate shift amount is defined as (Δ x, Δ y)=(x-x', y-
y')。
Using offset to the screen area for exceeding its correspondence detection zone in the visual sensor visual field in reference liquid crystal display
Width G compensates, and obtains the screen area for corresponding to detection zone in liquid crystal display to be detected in the visual sensor visual field beyond it
Width G '.G '=C_SP2 ' .x+ Δ x-C_SP2.x.In CAM2, C_SP2.x 0, then overlapping region width is G '=C_
SP2’.x+Δx。
3, transformation of the image coordinate system where defect to screen coordinate system.
Each detection picture of acquisition is analyzed, the image coordinate of defect is obtained.It is subtracted in screen ROI region
G ' obtains the area to be tested of image；
According to the mapping relations between the area to be tested of image and corresponding screen area to be detected, by the image of defect
Coordinate transformation is screen coordinate.
In Cam2, screen area to be tested is black region, when pattern is demarcated in production, angle point in screen coordinate system
SP2 ' and SP3 ' is known.Sp2 ' coordinate is set as (x'2,y'2), Sp3 ' coordinate is set as (x'3,y'3), Sp4 ' coordinate is set as (x'4,y
'4).Defect coordinate is set as (xd,yd).Coordinate in Cam2 where defect in screen are as follows:
According to above-mentioned geometric proportion reduction formula, the coordinate position in image where defect in screen can be solved.
The content that this specification is not described in detail belongs to the prior art well known to professional and technical personnel in the field.
Claims (10)
1. a kind of large scale display screen defects detection localization method, it is characterised in that:
It is moved to detection station using one piece of display screen as with reference to display screen, and this is referred into position of the display screen in detection station
It sets as reference position；
It shows that screen demarcates picture on the reference display screen, and demarcates picture figure using multiple visual sensors acquisition screen
Picture；
The off-line calibration parameter for identifying reference position information is obtained from screen calibration picture image；
Display screen to be detected is moved to detection station, each detection picture is successively shown on display screen to be detected, and utilize
Multiple visual sensors acquire each detection picture image, wherein after first detection picture image of acquisition, using it is described offline
Calibrating parameters carry out online compensation to the position of the display screen to be detected, obtain the location parameter of display screen to be detected；
Each detection picture of acquisition is analyzed, the image coordinate of defect is obtained；
According to the location parameter of the display screen to be detected, screen coordinate is converted by the image coordinate of defect.
2. a kind of large scale display screen defects detection localization method according to claim 1, it is characterised in that: the display
Screen screen calibration picture be etc. split screen, the visual sensor quantity phase of the split screen neutron number of pictures such as described and use
Together, the shooting area of each visual sensor is uniquely corresponding with a sprite.
3. a kind of large scale display screen defects detection localization method according to claim 1, it is characterised in that: described offline
Calibrating parameters include the screen zero point SP1 corresponding subpixel coordinates position C_SP1 and with reference to aobvious in the picture with reference to display screen
Correspond to the screen area width G of detection zone, the position of the display screen to be detected in display screen in the visual sensor visual field beyond it
Setting parameter includes the unilateral width G that any visual sensor exceeds its shooting area in display screen to be detected '.
4. a kind of large scale display screen defects detection localization method according to claim 3, it is characterised in that: described in utilization
Off-line calibration parameter carries out online compensation to the position of the display screen to be detected, obtains the location parameter packet of display screen to be detected
It includes:
Calculate screen zero point SP1 corresponding subpixel coordinates position C_SP1 and the display to be detected in the picture for referring to display screen
The screen zero point SP1 of the screen offset between corresponding subpixel coordinates position CC_SP1 in the picture；
Using the offset, to the screen area for exceeding its correspondence detection zone in the visual sensor visual field in reference display screen
Width G compensates, and obtains the screen area for corresponding to detection zone in display screen to be detected in the visual sensor visual field beyond it
Width G '.
5. a kind of large scale display screen defects detection localization method according to claim 3, which is characterized in that acquisition first
After a detection picture image, screen ROI region is first extracted from first detection picture image, and the off-line calibration is recycled to join
Several positions to the display screen to be detected carry out online compensation.
6. a kind of large scale display screen defects detection localization method according to claim 5, which is characterized in that according to described
The location parameter of display screen to be detected, converting screen coordinate for the image coordinate of defect includes:
G ' is subtracted in screen ROI region, obtains the area to be tested of image；
According to the mapping relations between the area to be tested of image and corresponding screen area to be detected, by the image coordinate of defect
It is converted into screen coordinate.
7. a kind of large scale display screen defects detection localization method according to claim 5, which is characterized in that from first
Extracting screen ROI region in detection picture image includes:
By adaptive threshold fuzziness, coarse extraction is carried out to screen ROI region；
Abnormal judgement is carried out to screen ROI region；
Root extracts screen sub-pix angle point information from screen ROI region.
8. a kind of large scale display screen defects detection localization method according to claim 1, it is characterised in that: the screen
The resolution ratio for demarcating picture is identical as the resolution ratio of display screen.
9. a kind of large scale display screen defects detection localization method according to claim 2, it is characterised in that: the equal part
Picture is the picture at black and white interval, any one sprite is single black picture or white picture, any one sprite and phase
Adjacent sprite color is different.
10. a kind of large scale display screen defects detection localization method according to claim 5, which is characterized in that from screen
During extracting screen sub-pix angle point information in ROI region:
Screen sub-pix angle point information is extracted using Harris angle point algorithm in angle point region；
If extracting failure, screen sub-pix angle point information is extracted using the mode that edge line fitting solves intersection point.
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 true CN109765245A (en) | 2019-05-17 |
| CN109765245B 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) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110213664A (en) * | 2019-07-05 | 2019-09-06 | 四川长虹电器股份有限公司 | The adjustment device and method of display panel driving parameter |
| CN110987926A (en) * | 2019-11-13 | 2020-04-10 | 上海大学 | Automatic display screen defect detection method based on machine vision |
| CN111292302A (en) * | 2020-01-21 | 2020-06-16 | 上海悦易网络信息技术有限公司 | Screen detection method and device |
| CN111325716A (en) * | 2020-01-21 | 2020-06-23 | 上海悦易网络信息技术有限公司 | Screen scratch fragmentation detection method and equipment |
| CN111325717A (en) * | 2020-01-21 | 2020-06-23 | 上海悦易网络信息技术有限公司 | Mobile phone defect position identification method and equipment |
| CN111473957A (en) * | 2020-03-24 | 2020-07-31 | 深圳同兴达科技股份有限公司 | Display screen partition detection method |
| CN111563883A (en) * | 2020-04-22 | 2020-08-21 | 惠州旭鑫智能技术有限公司 | Screen visual positioning method, positioning device and storage medium |
| 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 |
| CN113237888A (en) * | 2021-05-21 | 2021-08-10 | 哈尔滨工业大学 | Large-caliber optical element damage point online and offline dark field image matching method |
| CN113269762A (en) * | 2021-05-31 | 2021-08-17 | 苏州华兴源创科技股份有限公司 | Screen defect detection method, system and computer storage medium |
| WO2022126871A1 (en) * | 2020-12-15 | 2022-06-23 | Vomma (Shanghai) Technology Co., Ltd. | Defect layer detection method and system based on light field camera and detection production line |
| 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 |
| CN116245950A (en) * | 2023-05-11 | 2023-06-09 | 合肥高维数据技术有限公司 | Screen corner positioning method for full screen or single corner deletion |
| WO2024001495A1 (en) * | 2022-06-29 | 2024-01-04 | 京东方科技集团股份有限公司 | Fault detection method and device for display screen, and inspection robot |
Citations (10)
| 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 element 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 |
| US20190057498A1 (en) * | 2017-08-16 | 2019-02-21 | 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 (10)
| 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 element 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 |
| US20190057498A1 (en) * | 2017-08-16 | 2019-02-21 | Siemens Energy, Inc. | Method and system for detecting line defects on surface of object |
Non-Patent Citations (2)
| Title |
|---|
| 章为川等: "图像的角点检测研究综述", 《电子学报》 * |
| 简慧杰等: "用于大视场三维探测的人工复眼系统几何标定", 《光学学报》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110213664A (en) * | 2019-07-05 | 2019-09-06 | 四川长虹电器股份有限公司 | The adjustment device and method of display panel driving parameter |
| 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 |
| CN111292302A (en) * | 2020-01-21 | 2020-06-16 | 上海悦易网络信息技术有限公司 | Screen detection method and device |
| CN111325716A (en) * | 2020-01-21 | 2020-06-23 | 上海悦易网络信息技术有限公司 | Screen scratch fragmentation detection method and equipment |
| CN111325717A (en) * | 2020-01-21 | 2020-06-23 | 上海悦易网络信息技术有限公司 | Mobile phone defect position identification 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 |
| 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 |
| CN111473957A (en) * | 2020-03-24 | 2020-07-31 | 深圳同兴达科技股份有限公司 | Display screen partition detection method |
| CN111563883A (en) * | 2020-04-22 | 2020-08-21 | 惠州旭鑫智能技术有限公司 | Screen visual positioning method, positioning device and storage medium |
| 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 |
| WO2022126871A1 (en) * | 2020-12-15 | 2022-06-23 | Vomma (Shanghai) Technology Co., Ltd. | Defect layer 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 |
| CN113237888A (en) * | 2021-05-21 | 2021-08-10 | 哈尔滨工业大学 | Large-caliber optical element damage point online and offline dark field image matching method |
| CN113269762A (en) * | 2021-05-31 | 2021-08-17 | 苏州华兴源创科技股份有限公司 | Screen defect detection method, system and computer storage medium |
| 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 |
| WO2024001495A1 (en) * | 2022-06-29 | 2024-01-04 | 京东方科技集团股份有限公司 | Fault detection method and device for 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 |
| CN115456956B (en) * | 2022-08-19 | 2024-05-28 | 浙江华周智能装备有限公司 | Method, equipment and storage medium for detecting scratches of liquid crystal display |
| CN116245950A (en) * | 2023-05-11 | 2023-06-09 | 合肥高维数据技术有限公司 | Screen corner positioning method for full screen or single corner deletion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109765245B (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109765245A (en) | Large scale display screen defects detection localization method | |
| CN106548467B (en) | The method and device of infrared image and visual image fusion | |
| CN108760767A (en) | Large-size LCD Screen defect inspection method based on machine vision | |
| EP3171588B1 (en) | Image processing method and image processing apparatus executing that image processing method | |
| CN108682365A (en) | A kind of detection of OLED color spots with repair integral system, method | |
| JP2011196685A (en) | Defect detection device, defect repairing device, display panel, display device, defect detection method and program | |
| DE102015210440A1 (en) | Image inspection device, image inspection method, image inspection program, computer readable recording medium and recording device | |
| CN109471276B (en) | Method and device for detecting color cast defect of liquid crystal display | |
| CN110428762B (en) | OLED panel aging test luminescence characteristic detection method based on pixel brightness | |
| CN105911724B (en) | Determine the method and apparatus of the intensity of illumination for detection and optical detecting method and device | |
| CN108416765A (en) | A kind of character defect automatic testing method and system | |
| US20230410369A1 (en) | Method and apparatus for adjusting an image acquisition apparatus, compensation method of a display panel, device and medium | |
| CN112885289B (en) | Display screen calibration method and device | |
| CN102622739A (en) | Image non-uniformity correction method for Bayer filter array color camera | |
| CN109949725B (en) | Image gray level standardization method and system for AOI system | |
| CN110769229A (en) | Method, device and system for detecting color brightness of projection picture | |
| CN108986721B (en) | Detection graph generation method for display panel detection | |
| CN109596054A (en) | The size detection recognition methods of strip workpiece | |
| US6256066B1 (en) | High-resolution image pickup method and apparatus therefor | |
| CN114299070A (en) | Method and related device for detecting mura defects of display screen | |
| CN110060625B (en) | LED display screen acquisition vignetting compensation method | |
| CN106405894B (en) | A kind of liquid crystal display panel defect automatic positioning method | |
| CN115980012A (en) | Medical detection circuit board gluing multi-angle detection system and detection method thereof | |
| CN108205210A (en) | LCD defect detecting systems and method based on Fourier plum forests and characteristic matching | |
| CN207283689U (en) | A kind of dead pixels of image sensor surveys means for correcting |
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 |