CN115188304B - LCD and OLED screen defect repairing method and device - Google Patents
LCD and OLED screen defect repairing method and device Download PDFInfo
- Publication number
- CN115188304B CN115188304B CN202211089271.XA CN202211089271A CN115188304B CN 115188304 B CN115188304 B CN 115188304B CN 202211089271 A CN202211089271 A CN 202211089271A CN 115188304 B CN115188304 B CN 115188304B
- Authority
- CN
- China
- Prior art keywords
- repaired
- block
- pixel
- area
- lcd
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000007547 defect Effects 0.000 title claims abstract description 29
- 239000000428 dust Substances 0.000 claims abstract description 37
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 9
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 9
- 239000003086 colorant Substances 0.000 claims abstract description 6
- 230000008439 repair process Effects 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 238000011524 similarity measure Methods 0.000 claims description 3
- 238000011895 specific detection Methods 0.000 claims description 2
- 230000035876 healing Effects 0.000 claims 2
- 230000004044 response Effects 0.000 abstract description 9
- 238000001514 detection method Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G3/00—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes
- G09G3/006—Electronic inspection or testing of displays and display drivers, e.g. of LED or LCD displays
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
- G01M11/02—Testing optical properties
- G01M11/0242—Testing optical properties by measuring geometrical properties or aberrations
- G01M11/0278—Detecting defects of the object to be tested, e.g. scratches or dust
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G2320/00—Control of display operating conditions
- G09G2320/02—Improving the quality of display appearance
- G09G2320/0271—Adjustment of the gradation levels within the range of the gradation scale, e.g. by redistribution or clipping
- G09G2320/0276—Adjustment of the gradation levels within the range of the gradation scale, e.g. by redistribution or clipping for the purpose of adaptation to the characteristics of a display device, i.e. gamma correction
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G2320/00—Control of display operating conditions
- G09G2320/06—Adjustment of display parameters
- G09G2320/0673—Adjustment of display parameters for control of gamma adjustment, e.g. selecting another gamma curve
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Computer Hardware Design (AREA)
- Electroluminescent Light Sources (AREA)
- Devices For Indicating Variable Information By Combining Individual Elements (AREA)
- Control Of Indicators Other Than Cathode Ray Tubes (AREA)
Abstract
The invention discloses a method and a device for repairing LCD and OLED screen defects. According to the scheme of the invention, different corresponding brightness data are collected according to the Gray (32/64/128/192/224) requirements of three colors of RGB, the obtained brightness data and Gray scale are fitted, and the traditional exponential gamma response model is converted into a linear model, namely, the parameters of the linear gamma response model of different pixel points and a central pixel point can be distinguished, so that a dust area is detected, the fitting calculation complexity can be reduced, and the fitting accuracy is improved. And then repairing the dust area through an algorithm model based on texture synthesis without modeling training of a large amount of data.
Description
Technical Field
The invention relates to the field of screen display detection, in particular to a method and a device for repairing defects of LCD and OLED screens.
Background
When OLED, LCD, uLED and other display screens are used for detection and Demura, the conventional collected gray scale and color sequence is as follows:
in the prior art, a dust removal map is collected mainly by adopting a light-emitting scheme and is used for positioning a screen dust area, the dust position is marked manually, modeling analysis is carried out on a large amount of data by using a deep learning model, and a dust Mask is obtained through series of algorithm processing. Common models are RCNN, yolov5, yolov4, yolov3, etc. And after the dust Mask is detected, performing data restoration by adopting networks such as U-Net and the like. According to the scheme, a large amount of data needs to be collected for modeling training, the time consumption is long, the requirement on polishing is high, and a lot of difficulties are caused when the model is used in a workshop and is fallen to the ground.
For example, in the patent "grayscale picture detection method and detection device" of patent application No. 201410387161.0, grayscale pictures on an imaging screen need to be respectively acquired under a plurality of shooting conditions, and the method takes a long time for data acquisition; in the patent 'a method and a device for removing dust interference in Demura detection' with the application number of 201810698019.6, the position of dust on an OLED screen needs to be positioned in a side lighting mode, and the method has higher requirement on lighting; in the patent 'dust occlusion area identification method and external optical compensation data acquisition method' with the application number of 202111226486.7, after data acquisition, target identification is respectively performed on dust occlusion areas in module gray scale data and side light source data in display by using two trained deep neural networks, a large amount of data is needed for modeling training, and time is consumed.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a device for repairing the defects of LCD and OLED screens.
A LCD and OLED screen defect repairing method based on an algorithm model of texture synthesis comprises the following steps:
s11: detecting an area where dust is located; the specific detection method comprises the following steps:
s111: acquiring different corresponding brightness data according to Gray (32/64/128/192/224) requirements of three colors of RGB;
s112: performing gamma model fitting by combining the gray scale and the brightness data by adopting a least square method to obtain a linear gamma function corresponding to each pixel point of the screen and fitting parameters thereof;
s113: fitting and distinguishing the fitting parameters corresponding to each acquired pixel point and the fitting parameters of the central area of the screen, so as to detect and acquire a dust area;
s12: traversing the edge of the dust area, dividing blocks to be repaired, and calculating the filling priority of the blocks to be repaired;
s13: searching a pixel block which is most similar to the block to be repaired with the highest priority in the intact area, and replacing the block to be repaired with the highest priority by the pixel block;
s14: updating the confidence coefficient of the replaced block to be repaired;
s15: judging whether all the dust on the screen is repaired, if so, completing the repair, and if not, repeating the steps S11-S14;
the calculation formula of the filling priority of the block to be repaired is as follows: p (P) = C (P) D (P), wherein C (P) isThe confidence coefficient item represents the number of known pixel points contained in the block to be repaired, and the larger the C (p) is, the more psi is shown p The larger the proportion of the known information contained in the data is, namely the higher the confidence coefficient is, the prior repair is needed; d (p) is a data item for representing the complexity of image structure information, and the larger D (p) is, the more complex the surface linear structure is, and the priority should be given to repair; c (p) and D (p) are defined as follows:
where | Ψ p L represents the area of the block to be repaired; α is a normalization factor, q represents a pixel point located in the region to be repaired in the block to be repaired, and initially, the calculation formula of C (p) is as follows:
through the calculation of the priority, the block Ψ to be repaired with the maximum priority value can be obtained p 。
As a further improvement of the present invention, step S13 includes: searching for the most likely matching block Ψ within the sound region q Block Ψ to be repaired p And matching block Ψ q The matching criteria are:
wherein d (Ψ) p ，Ψ q ) For block Ψ to be repaired p And matching block Ψ q The distance between the two is a similarity measure function, i.e. the distance to the block Ψ to be repaired p The matching block with the minimum distance is the most similar matching block, and after the most similar matching block is found, the most similar matching block is used for treating the block Ψ to be repaired p And (6) updating.
As a further improvement of the present invention, step S14 includes: when the block to be repaired with the highest priority is repaired and filled, the block to be repaired psi p The unknown area in (1) becomes a known area, and the unknown pixels become known pixels, so the confidence degrees of the pixel points change, and the confidence degrees of the pixel points need to be updated in time, so the confidence degrees of the pixel points are updated as follows: c (p) = C (q), wherein p ∈ Ψ q And d, n omega, and completing the one-time restoration after updating the confidence value.
As a further improvement of the present invention, the judgment of whether all the dusts on the screen are completely repaired in step S15 is made by
And determining whether the measured value is equal to phi or not, if so, completing the repair, and otherwise, repeating the steps S11-S14.
An LCD and OLED screen defect repairing device is used for realizing the LCD and OLED screen defect repairing method, and comprises the following steps:
the computing module is used for computing the filling priority of the pixel points at the edge of the pixel block to be repaired;
the searching module is used for searching for a perfect pixel block which is most similar to the pixel block to be repaired in the perfect area;
the updating module is used for updating the confidence coefficient of the pixel block to be repaired;
and the judging module is used for judging whether the defects on the screen are completely repaired.
The invention has the beneficial effects that:
1. according to the invention, different corresponding brightness data can be acquired only by acquiring Gray (32/64/128/192/224) of three colors of RGB, and the difference can be judged through gamma response parameters of different pixel points and a central pixel point, so that a dust area is detected, and a large amount of data acquisition work is avoided.
2. The method repairs the dust area based on the algorithm model of texture synthesis, and modeling training is not needed to be carried out on a large amount of data.
3. The gamma response index model of the screen brightness and the gray scale is converted into the linear model, so that the fitting calculation complexity can be reduced, and the fitting accuracy is improved.
Drawings
FIG. 1 is a flow chart of the LCD and OLED screen defect detection method of the present invention.
FIG. 2 is an exponential model diagram obtained by fitting the brightness data and the gray scale data of the central area of the screen according to the present invention.
FIG. 3 is a linear model diagram obtained by fitting logarithmic values of the brightness data and the gray-scale data of the central area of the screen according to the present invention.
FIG. 4 is a repair diagram of the texture synthesis algorithm of the present invention.
FIG. 5 is a flow chart of the LCD and OLED screen defect repairing method of the present invention.
FIG. 6 is a comparison graph of screen brightness before and after dedusting according to the present invention, with the left side before dedusting and the right side after dedusting.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
The embodiment of the invention takes an OLED screen as an example, at present, the detection of the OLED screen usually adopts Demura detection, and the Demura detection is to adjust the brightness of pixels point by point to make the gray levels of all the pixels consistent, thereby eliminating color spots. However, in the Demura detection process, if dust exists on the OLED screen, the dust affects the adjustment of the brightness of the pixels, some pixels can be too dark due to the shielding of the dust, and during Demura detection, the pixels can be adjusted due to the too dark pixels, but the situation that the brightness is too dark is that the pixels are not corrected by the dust, so the adjustment belongs to the error correction of the OLED screen. Therefore, the method for detecting and repairing the defects of the LCD and the OLED screen can shield the interference of dust in the process of Demura detection, so that the correction of the OLED screen is more accurate.
The method detects the dust area existing in the screen through gamma model fitting, and after detection, adopts an algorithm model based on texture synthesis to carry out image restoration on the brightness data in the dust area.
Referring to fig. 1, a method for detecting defects of LCD and OLED screens includes the steps of:
s01: acquiring different corresponding brightness data according to Gray (32/64/128/192/224) requirements of three colors of RGB;
s02: performing gamma model fitting by combining the gray scale and the brightness data by adopting a least square method to obtain a linear gamma function corresponding to each pixel point of the screen and fitting parameters thereof;
generally, the gamma response exists between the brightness and gray levels of the screen, and the data model is usually:
wherein, lum represents the module display brightness; lum max The display module displays the maximum brightness, namely the brightness corresponding to the gray scale 255; gray screen The representing module displays gray scale; gray max The representing module displays the maximum gray scale, and the value is 255; gamma represents a model parameter, namely a screen response characteristic value, and the value is 2.2 +/-0.2; a represents a model parameter.
The brightness and gray scale response model is an exponential model, the brightness data and gray scale data at the center of the screen are taken to draw an image, as shown in fig. 2, the image is a curve, and the error is larger along with the increase of the data in the data fitting process, so that in the embodiment of the invention, the exponential model is converted into a linear model, the fitting calculation complexity can be reduced, and the fitting accuracy is improved. The transformation process is as follows:
taking logarithm operation on two sides of the equation of the exponential model of the screen brightness and gray scale response:
finishing to obtain: log lum = gamma × log gray screen -gamma×log gray max +log a+log lum max ；
S023: let A = gamma, B = log a-gamma × log gray max +log lum max ，Lum＝log lum，
Gray＝log gray screen (ii) a The following can be obtained: lum = a × Gray + B; where Lum represents luminance, gray represents Gray scale, A, B is the fitting parameter.
Through the above transformation, the exponential model can be transformed into a linear model, and a linear response model image of the luminance data and the gray scale data in the central area of the screen is shown in fig. 3.
S03: fitting and distinguishing the fitting parameters corresponding to each acquired pixel point and the fitting parameters of the central area of the screen, so as to detect and acquire a dust area;
the invention also provides a device for detecting the defects of the LCD and OLED screens, which is used for realizing the method for detecting the defects of the LCD and OLED screens and comprises the following steps:
the acquisition module is used for acquiring Gray (32/64/128/192/224) of three colors of RGB and acquiring different corresponding brightness data;
the fitting module is used for performing gamma fitting on the collected screen center brightness data and the gray scale to obtain a linear gamma image and acquiring a fitting parameter corresponding to each pixel point of the screen;
and the detection module is used for performing fitting judgment on the fitting parameters corresponding to the acquired pixels and the fitting parameters of the central area of the screen, so as to detect and acquire the dust area.
And the storage module is used for storing a computer program for realizing the LCD and OLED screen defect detection method.
The invention also provides a method for repairing the defects of the LCD and OLED screens, which adopts an algorithm model based on texture synthesis to repair the brightness data in the dust area.
The texture synthesis algorithm selects a pixel point p with the highest priority on the edge of a region to be repaired, then constructs a pixel block with the size of n multiplied by n by taking p as the center, then searches a sample block which is most similar to the pixel block in a sound region, updates the information to be repaired in the pixel block by using the found sample block, and finally updates the repaired informationAnd (4) the confidence of the pixel points in the complex block, and starting the next iterative repair until the repair is completed. FIG. 4 is a schematic diagram of a repair algorithm for texture synthesis, where Φ represents a sound region, Ω represents a region to be repaired, δ Ω represents a boundary of the region to be repaired, Ψ p Representing a pixel block which is constructed by taking the pixel point p as a center, namely a block to be repaired; n is p Is the normal direction of the pixel point p on the edge,
the isoluminance direction of the point p on the edge represents the direction perpendicular to the gradient direction of the point p.
As shown in fig. 5, the image restoration process is as follows:
s11: the dust area detected by the LCD and OLED screen defect detection method;
s12: traversing the edge of the dust area, dividing blocks to be repaired, and calculating the filling priority of the blocks to be repaired;
the calculation formula of the filling priority of the block to be repaired is as follows: p (P) = C (P) D (P), where C (P) is a confidence term representing how many known pixel points are included in the block to be repaired, and the larger C (P), the more psi p The larger the proportion of the known information contained in the data is, namely the higher the confidence coefficient is, the prior repair is needed; d (p) is a data item for representing the complexity degree of image structure information, and the larger D (p) is, the more complex the surface linear structure is, and the priority should be given to repairing. C (p) and D (p) are defined as follows:
where | Ψ p I represents the area of the block to be repaired; α is a normalization factor (α =255 for a typical 8-bit gray image), q represents a pixel point in the block to be repaired, which is located in the region to be repaired, and initially, the calculation formula of C (p) is:
through the calculation of the priority, the block Ψ to be repaired with the maximum priority value can be obtained p 。
S13: searching a pixel block which is most similar to the block to be repaired with the highest priority in the intact area, and replacing the block to be repaired with the highest priority by the pixel block;
searching for the most likely matching block Ψ within the sound region q Block Ψ to be repaired p And matching block Ψ q The matching criteria are:
wherein d (Ψ) p ，Ψ q ) For block Ψ to be repaired p And matching block Ψ q The distance between the two is a similarity measure function, i.e. the distance to the block Ψ to be repaired p The matching block with the minimum distance is the most similar matching block, and after the most similar matching block is found, the most similar matching block is used for treating the block Ψ to be repaired p And (6) updating.
S14: updating the confidence coefficient of the replaced block to be repaired;
when the block to be repaired with the highest priority is repaired and filled, the block Ψ to be repaired is p The unknown area in (1) becomes a known area, and the unknown pixels become known pixels, so the confidence degrees of the pixel points change, and the confidence degrees of the pixel points need to be updated in time, so the confidence degrees of the pixel points are updated as follows: c (p) = C (q), wherein p ∈ Ψ q And d, n omega, and completing the one-time restoration after updating the confidence value.
S15: judging whether all the dust on the screen is repaired, i.e. judging
If the value is equal to phi, the repair is finished, and if not, the steps S11 to S14 are repeated.
The invention also provides a device for repairing the defects of the LCD and OLED screens, which is used for realizing the method for repairing the defects of the LCD and OLED screens, and comprises the following steps:
the computing module is used for computing the filling priority of the pixel points at the edge of the pixel block to be repaired;
the searching module is used for searching for a perfect pixel block which is most similar to the pixel block to be repaired in the perfect area;
the updating module is used for updating the confidence coefficient of the pixel block to be repaired;
and the judging module is used for judging whether the defects on the screen are completely repaired.
As shown in fig. 6, the left side is an original luminance graph without dust removal, and the right side is a dust removal luminance graph, so that it can be seen that the screen defect detecting and repairing method of the present invention has a significant dust removal effect.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (5)
1. A LCD and OLED screen defect repairing method is characterized in that: the method is based on an algorithm model of texture synthesis, and comprises the following steps:
s11: detecting an area where dust is located; the specific detection method comprises the following steps:
s111: collecting different corresponding brightness data according to the Gray (32/64/128/192/224) requirements of three colors of RGB;
s112: performing gamma model fitting by combining the gray scale and the brightness data by adopting a least square method to obtain a linear gamma function corresponding to each pixel point of the screen and fitting parameters thereof;
s113: fitting and distinguishing the fitting parameters corresponding to each acquired pixel point and the fitting parameters of the central area of the screen, so as to detect and acquire a dust area;
s12: traversing the edge of the dust area, dividing blocks to be repaired, and calculating the filling priority of the blocks to be repaired;
s13: searching a pixel block which is most similar to the block to be repaired with the highest priority in the intact area, and replacing the block to be repaired with the highest priority by the pixel block;
s14: updating the confidence coefficient of the replaced block to be repaired;
s15: judging whether all the dust on the screen is repaired, if so, completing the repair, and if not, repeating the steps S11-S14;
the calculation formula of the filling priority of the block to be repaired is as follows: p (P) = C (P) D (P),
wherein C (p) is a confidence term and represents the number of known pixel points contained in the block to be repaired, and the larger C (p) is, the more psi is shown p The larger the proportion of the known information contained in the database is, namely the higher the confidence coefficient is, the prior repair is required; d (p) is a data item for representing the complexity of image structure information, and the larger D (p) is, the more complex the surface linear structure is, and the priority should be given to repair; c (p) and D (p) are defined as follows:
where | Ψ p L represents the area of the block to be repaired; α is a normalization factor, q represents a pixel point located in the region to be repaired in the block to be repaired, and initially, the calculation formula of C (p) is as follows:
through the calculation of the priority, the block Ψ to be repaired with the maximum priority value can be obtained p 。
2. The LCD and OLED screen defect repair method of claim 1, wherein: step S13 bagComprises the following steps: searching for the most likely matching block Ψ within the sound region q Block Ψ to be repaired p And matching block Ψ q The matching criteria are:
wherein d (Ψ) p ，Ψ q ) For block Ψ to be repaired p And matching block Ψ q The distance between the two is a similarity measure function, i.e. the distance to the block Ψ to be repaired p The matching block with the minimum distance is the most similar matching block, and after the most similar matching block is found, the most similar matching block is used for treating the block psi to be repaired p And (4) updating.
3. The LCD and OLED screen defect healing process of claim 1, wherein: step S14 includes: when the block to be repaired with the highest priority is repaired and filled, the block Ψ to be repaired is p The unknown area in (1) becomes a known area, and the unknown pixels become known pixels, so the confidence degrees of the pixel points change, and the confidence degrees of the pixel points need to be updated in time, so the confidence degrees of the pixel points are updated as follows: c (p) = C (q), wherein p ∈ Ψ q And d, n omega, and completing the one-time restoration after updating the confidence value.
4. The LCD and OLED screen defect healing process of claim 1, wherein: the judgment of whether all the dusts on the screen are completely repaired in step S15
And determining whether the measured value is equal to phi or not, if so, completing the repair, and otherwise, repeating the steps S11-S14.
5. A LCD and OLED screen defect repair device which characterized in that: method for implementing the LCD and OLED screen defect repair according to any of claims 1 to 4, comprising:
the computing module is used for computing the filling priority of the pixel points at the edge of the pixel block to be repaired;
the searching module is used for searching for a perfect pixel block which is most similar to the pixel block to be repaired in the perfect area;
the updating module is used for updating the confidence coefficient of the pixel block to be repaired;
and the judging module is used for judging whether the defects on the screen are completely repaired.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211089271.XA CN115188304B (en) | 2022-09-07 | 2022-09-07 | LCD and OLED screen defect repairing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211089271.XA CN115188304B (en) | 2022-09-07 | 2022-09-07 | LCD and OLED screen defect repairing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115188304A CN115188304A (en) | 2022-10-14 |
| CN115188304B true CN115188304B (en) | 2023-01-03 |
Family
ID=83522471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211089271.XA Active CN115188304B (en) | 2022-09-07 | 2022-09-07 | LCD and OLED screen defect repairing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115188304B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117481A (en) * | 2011-03-17 | 2011-07-06 | 西安交通大学 | Automatic digital repair method of damaged images |
| CN109493272A (en) * | 2018-09-30 | 2019-03-19 | 南京信息工程大学 | A kind of Criminisi image repair method under the color space based on HSV |
| CN110246100A (en) * | 2019-06-11 | 2019-09-17 | 山东师范大学 | A kind of image repair method and system based on angle perception Block- matching |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105575326B (en) * | 2016-02-16 | 2018-11-23 | 深圳市华星光电技术有限公司 | The method for calibrating OLED display panel brightness disproportionation |
| CN107194919B (en) * | 2017-05-18 | 2021-07-30 | 南京大学 | Mobile phone screen defect detection method based on regular texture background reconstruction |
| CN107507571B (en) * | 2017-08-28 | 2019-09-27 | 哈尔滨工业大学深圳研究生院 | A kind of couple of AMOLED carries out the method and device of external optical compensation |
| CN109903717B (en) * | 2019-04-26 | 2022-06-21 | 京东方科技集团股份有限公司 | Identification method, compensation method and device for bright spot area of display panel |
| CN111210756B (en) * | 2020-02-25 | 2023-04-18 | 京东方科技集团股份有限公司 | Gamma compensation method, device and equipment, and medium |
| CN113744691A (en) * | 2021-09-10 | 2021-12-03 | 昇显微电子(苏州)有限公司 | Organic Light Emitting Diode (OLED) panel Demura method and device |
-
2022
- 2022-09-07 CN CN202211089271.XA patent/CN115188304B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117481A (en) * | 2011-03-17 | 2011-07-06 | 西安交通大学 | Automatic digital repair method of damaged images |
| CN109493272A (en) * | 2018-09-30 | 2019-03-19 | 南京信息工程大学 | A kind of Criminisi image repair method under the color space based on HSV |
| CN110246100A (en) * | 2019-06-11 | 2019-09-17 | 山东师范大学 | A kind of image repair method and system based on angle perception Block- matching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115188304A (en) | 2022-10-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109871895B (en) | Method and device for detecting defects of circuit board | |
| CN104484878B (en) | The automatic testing method of defects of display panel | |
| CN111474177A (en) | Liquid crystal screen backlight foreign matter defect detection method based on computer vision | |
| CN103020970B (en) | Corn ear image grain segmentation method | |
| CN111915704A (en) | Apple hierarchical identification method based on deep learning | |
| CN107239742B (en) | Method for calculating scale value of instrument pointer | |
| CN113724652B (en) | Compensation method and device for Mura of OLED display panel and readable medium | |
| CN116559183B (en) | Method and system for improving defect judging efficiency | |
| CN110110131B (en) | Airplane cable support identification and parameter acquisition method based on deep learning and binocular stereo vision | |
| CN113012096B (en) | Display screen sub-pixel positioning and brightness extraction method, device and storage medium | |
| CN114066857A (en) | Infrared image quality evaluation method and device, electronic equipment and readable storage medium | |
| CN114119591A (en) | Display screen picture quality detection method | |
| CN113160222A (en) | Production data identification method for industrial information image | |
| CN116612111B (en) | High-strength composite material processing quality detection method | |
| CN112560837A (en) | Reading method, device, equipment and storage medium of pointer instrument | |
| CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
| CN115188304B (en) | LCD and OLED screen defect repairing method and device | |
| CN113808104A (en) | Block-based metal surface defect detection method and system | |
| CN112862721A (en) | Underground pipeline image defogging method based on dark channel and Retinex | |
| CN116843618A (en) | Method for detecting shallow apparent appearance defects of metal parts | |
| CN113132693A (en) | Color correction method | |
| CN107492073B (en) | Digital image restoration method based on weight guide filtering | |
| CN110672631B (en) | Panel defect photographing method and panel defect photographing device | |
| CN114548250A (en) | Mobile phone appearance detection method and device based on data analysis | |
| CN113223098A (en) | Preprocessing optimization method for image color classification |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A defect repair method and device for LCD and OLED screens Granted publication date: 20230103 Pledgee: Bank of Communications Co.,Ltd. Suzhou Yangtze River Delta integration Demonstration Zone Branch Pledgor: SUZHOU JIAZHICAI OPTOELECTRONICS TECHNOLOGY Co.,Ltd. Registration number: Y2024980022945 |