CN112801947A - Visual detection method for dead pixel of LED display terminal - Google Patents
Visual detection method for dead pixel of LED display terminal Download PDFInfo
- Publication number
- CN112801947A CN112801947A CN202110046381.7A CN202110046381A CN112801947A CN 112801947 A CN112801947 A CN 112801947A CN 202110046381 A CN202110046381 A CN 202110046381A CN 112801947 A CN112801947 A CN 112801947A
- Authority
- CN
- China
- Prior art keywords
- image
- display terminal
- correction
- lamp
- led display
- 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.)
- Withdrawn
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 15
- 230000000007 visual effect Effects 0.000 title claims abstract description 10
- 239000011324 bead Substances 0.000 claims abstract description 62
- 238000003708 edge detection Methods 0.000 claims abstract description 14
- 238000003702 image correction Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims description 12
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 3
- 229910052704 radon Inorganic materials 0.000 claims description 3
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 238000011179 visual inspection Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 description 6
- 230000007547 defect Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/02—Affine transformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30121—CRT, LCD or plasma display
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a visual detection method for dead pixels of an LED display terminal, which comprises the steps of collecting images of the LED display terminal through a display terminal image, collecting images of the LED display terminal by using a camera, carrying out image correction, image enhancement, image edge detection, single-lamp image filling and lamp bead image centroid determination on the collected images, measuring and comparing fixed values of distances between centroids and lamp beads, and rapidly and accurately detecting the dead pixels according to the distance comparison. The visual detection method can quickly and accurately detect the dead pixel.
Description
Technical Field
The invention belongs to the technical field of visual image detection, and particularly relates to a visual detection method for dead pixels of an LED display terminal.
Background
The LED is a semiconductor light source based on a PN junction photoelectric effect, gradually becomes a mainstream light source due to high light efficiency and low energy consumption, and is widely applied to industries such as traffic indication, lighting and decoration, automobile direction indication, urban lighting engineering and the like. The display terminal with the LED chip as the core is generally formed by splicing LED unit modules, and requires high performance of display brightness, contrast, density, visual angle, color uniformity, and the like, and the dead point rate, defect rate, and the like of the display terminal must be strictly controlled.
At present, few methods for detecting the dead pixel of the LED display terminal are used, manual observation is basically relied on, time and labor are consumed, the detection efficiency is low, and accurate positioning cannot be realized.
Disclosure of Invention
The invention aims to provide a visual detection method for dead pixels of an LED display terminal, which can quickly and accurately detect the dead pixels.
In order to solve the technical problems, the invention adopts the following technical means:
a visual detection method for LED display terminal dead pixels comprises the following steps:
(1) acquiring an image of the display terminal, namely acquiring the image of the LED display terminal by using a camera;
(2) image correction, namely performing image correction on the image acquired in the step (1);
(3) enhancing the image, namely filtering out noise by adopting open operation of a binary morphological algorithm, corroding the image of the display terminal to remove noise of connected small white dots, and then performing expansion recovery, thereby improving the image identification degree of each lamp bead;
(4) image edge detection, namely, sharpening the image obtained in the step (3) and enhancing the edge and gray level jump part of the image so as to determine the boundaries of all LED lamp beads and position the lamp beads;
(5) filling single-lamp images, namely communicating and filling each lamp bead region, and performing binarization processing to obtain binary images with clear contrast;
(6) determining the centroid of the lamp bead image, wherein in the image obtained in the step (5), the edge contour of each lamp bead is an irregular closed contour line, but the centroid can be determined to be in the closed line, because the closed contour line is closer to a circle, each closed contour is subjected to circle fitting to obtain a regular circular contour, and the origin moment M of the image is utilized00The moment center can be calculated by a formula, and then the coordinates of the mass centers of all the lamp beads are obtained;
(7) and (4) determining dead spots, measuring a fixed value of the distance between the lamp beads of the LED display terminal and the lamp beads, calculating the centroid distance between the lamp beads in the image obtained in the step (6), comparing the centroid distance with the fixed value, if the centroid distance is close to or the same as the fixed value, no dead spots exist, and if the centroid distance is more than 2 times of the fixed value, dead spots exist.
Compared with the prior art, the outstanding characteristics are that:
according to the method, the image of the LED display terminal is acquired through the display terminal, the camera is used for acquiring the image of the LED display terminal, the acquired image is subjected to image correction, image enhancement, image edge detection, single lamp image filling and lamp bead image centroid determination, then the fixed value of the distance between the centroid distance and the lamp beads is measured and compared, and the dead pixel can be rapidly and accurately detected according to the comparison of the distances.
The further preferred technical scheme is as follows:
the step (2) of image correction comprises correction of trapezoidal distortion caused by deviation of a camera and a target in a vertical direction and correction of oblique distortion caused by deviation in a horizontal direction, and the image correction comprises the following steps:
correcting the keystone distortion, firstly, performing image enhancement of histogram equalization on an image of a display terminal, then performing edge detection, finally, solving an extreme value by utilizing Radon transformation to extract a straight line profile, and further, obtaining a detected straight line for correction;
correcting the tilt distortion, firstly intercepting an effective image in a background through an imcrop function, and enabling the image of a display terminal to fill the whole field of view; then, converting an image of the display terminal from an RGB (red, green and blue) image into a gray image, binarizing by using a threshold value method, determining a contour by adopting edge detection, extracting 4 vertex coordinates, and determining an angle between a rectangular side and a horizontal line; and extracting an ROI (region of interest), creating a white MASK template, and performing affine transformation rotation correction.
The distortion of the digital image is caused by the inconsistency of the vertical and horizontal angles of the target during the imaging process of the wide-angle lens of the camera, and generally needs to be corrected.
Drawings
FIG. 1 is a flow chart of the detection method of the present invention.
Fig. 2 is an image after image correction.
Fig. 3 is an image after image edge detection.
Fig. 4 is a histogram of the image of fig. 2.
Fig. 5 is a noise during single lamp image fill.
Fig. 6 is a binary image final fill result of an image.
FIG. 7 is a result of center of mass positioning amplification when the center of mass of the lamp bead image is determined.
Fig. 8 is an image after the center of mass of the lamp bead image is determined.
FIG. 9 is a schematic diagram of a bead image centroid distance.
Detailed Description
The present invention will be further described with reference to the following examples.
Referring to fig. 1 to 8, a visual inspection method for LED display terminal dead pixel according to the present invention includes the following steps: (1) acquiring an image of the display terminal, namely acquiring the image of the LED display terminal by using a camera;
the detected LED display terminal is a P4 cell board, the size is 320mm multiplied by 160mm, the resolution is 80 multiplied by 40dots, and the physical density is 62500 dots/square meter. When the camera collects images, a full-manual or shutter priority mode is adopted, the shutter speed is fixed or is lower than 1/160 seconds, and stable shooting pictures are guaranteed. In addition, the size of the viewfinder determines the definition of the lamp beads, and the display terminal is positioned in the center of the viewfinder and is fully filled by selecting a proper distance as far as possible, so that the actual size represented by a unit pixel is small, and an amplified image is clearer;
(2) image correction, namely performing image correction on the image acquired in the step (1);
image distortion may be caused due to inherent defects of the imaging system of the photographing camera and photographing control defects. The most obvious image distortion according to the acquisition condition of the module 1 is mainly trapezoidal distortion and oblique loss of body caused by shooting control. Firstly, an effective image is intercepted in a background through an imcrop function, so that the display terminal image is full of the whole field of view. Because the selected display terminal equipment is a very square rectangle with clear edges, the correction inclination can adopt a contour extraction method, firstly, an RGB image is converted into a gray image, edge detection is adopted to determine the contour after binarization by a threshold value method, 4 vertex coordinates are extracted, and the angle between the rectangular edge and the horizontal line is determined; and then extracting an ROI (region of interest), creating a white MASK template, and performing affine transformation rotation correction. The keystone distortion correction is implemented by firstly enhancing the image by histogram equalization and then performing edge detection, then solving an extreme value by using Radon transformation to extract a straight line profile, and further obtaining a detection straight line for correction, as shown in FIG. 1;
(3) and (3) after the image is enhanced and converted into a gray image, because the pixel point of the LED single-lamp image is small, the impulse noise is a main pollution source, and the noise is filtered out by adopting open operation of a binary morphological algorithm. Firstly, corroding a display terminal image, removing the noise of connected small white dots, and then performing expansion recovery, thereby improving the identification degree of each lamp bead image;
(4) image edge detection, namely, sharpening the image obtained in the step (3) and enhancing the edge and gray level jump part of the image so as to determine the boundaries of all LED lamp beads and position the lamp beads;
the edge detection, i.e. sharpening, of the image is to enhance the edge and the gray jump part of the image. The module has the main function of determining the boundaries of all the LED lamp beads so as to position the lamp beads. The extraction precision of the edge is related to the accurate positioning of the lamp bead, the error detection rate of the edge is required to be low, the edge position is located at the center of the actual edge as far as possible, and the false edge is restrained to ensure that the edge is as accurate as possible. Due to the fact thatThe brightness can be adjusted to 1000cd/m when the lamp beads are lighted2In the above, the gradient difference from the gray value of the central area to the gray value of the black background is large, the step type edge can be determined, and the Canny algorithm is selected for accurate image edge detection. Firstly, performing convolution by using a Gaussian kernel of 3 multiplied by 3 as a matrix template to complete Gaussian filtering; then, calculating the amplitude and the direction of the gradient by using finite difference of partial derivatives of a first-order function, if the oblique line direction is the gradient direction, comparing the value of the gradient direction with adjacent pixel points G1(X1, Y1), G2(X2, Y2), G3(X3, Y3) and G4(X4, Y4), judging whether the intensity of the point is the maximum value, and setting the gray value corresponding to the non-maximum value as 0; finally, determining a final edge point by using a double threshold value method, and processing the final edge point as shown in figure 2;
(5) filling single-lamp images, namely communicating and filling each lamp bead region, and performing binarization processing to obtain binary images with clear contrast;
all the lamp bead edges of the display terminal are found through the module 4, all the lamp beads need to be separated from the background in order to determine the positions of the lamp beads, and the adopted method is to connect and fill each lamp bead area. Since the gray values of the lighted lamp beads and the black background of the back plate are obviously compared, histogram observation is carried out, as shown in fig. 3, image segmentation can be carried out by taking 100-150 as a threshold value, connected regions are marked by 8 neighborhoods by using a bwleabel function, then all the connected regions are filled, binarization processing is carried out, namely, the values of elements inside the contour line are assigned to 255, and the values of elements outside the contour line are assigned to 0, and the two elements are converted into a binary image with clear comparison. In the filling process, some small-area connected regions of noise are also marked and identified, for example, a small target of amplified isolated points or burr noise is marked in a red circle of fig. 4, so that morphological opening operation is performed on a binary image, the small target is removed by using a function bweareaopen, by observing a data matrix corresponding to the connected regions, the light-emitting area of a normal lamp bead is about 300-350 pixels, the area of a noise region is relatively small, so that a structural element P is selected to be 100, all noise can be eliminated by comparison, and the final filling image is shown in fig. 5;
(6) determining the centroid of the image of the lamp bead, and determining the edge of each lamp bead in the image obtained in the step (5)The edge contour is an irregular closed contour line, but the centroid can be determined to be in the closed line, because the closed contour line is closer to a circle, each closed contour is subjected to circle fitting to obtain a regular circular contour, and the origin moment M of the image is utilized00The moment center can be calculated by a formula, and then the coordinates of the mass centers of all the lamp beads are obtained;
the center coordinates of the lamp beads are determined by adopting a centroid method, the distribution of light spot images is required to be uniform, otherwise, large errors can be generated, and because the closed contour lines are closer to a circle, each closed contour line is subjected to circle fitting to obtain a regular circular contour line. Using equations (1) - (3), i.e. the moment of origin M of the image00The moment center can be calculated by a formula, so that coordinates of the mass centers of all the lamp beads are obtained, as shown in fig. 6 and 7;
in the formula, i and j are horizontal and vertical coordinates of the image pixel, and M and N are the row number and the column number of the image pixel; f (i, j) is the gray value of coordinate (i, j), and p and q are the order of the image feature moment; m ispqIs the p + q order geometric moment of the image;
and
is the horizontal and vertical coordinates of the image centroid.
(7) And (4) determining dead spots, measuring a fixed value of the distance between the lamp beads of the LED display terminal and the lamp beads, calculating the centroid distance between the lamp beads in the image obtained in the step (6), comparing the centroid distance with the fixed value, if the centroid distance is close to or the same as the fixed value, no dead spots exist, and if the centroid distance is more than 2 times of the fixed value, dead spots exist.
At present, most of display terminals in market application have uniformly distributed lamp beads, so that the distance of each lamp bead is a fixed value with a small standard deviation, and after the center of mass of each lamp bead is determined, whether a dead pixel exists can be judged by calculating the center of mass distance. Setting the number of rows and columns of the detection display terminal lamp bead arrangement as M and N respectively, placing a centroid coordinate point of a connected region in a structure body S of MN x1, converting the S into a matrix C of 2 x MN through struct2cell and cell2mat functions, and converting the C into [2M, N ] through a reshape function, wherein the centroid coordinates of 100 lamp beads are intercepted as shown in table 1 due to the fact that the number of the lamp beads of the display device is large, each 2 rows of the matrix represent a row of the centroid coordinates of the lamp beads of the display device image, and whether a dead point exists in the middle is judged by detecting the distance between every two centroids according to the rows, as shown in fig. 8; for example, K2 in the figure is broken, the distance between the centers of mass of the lamp beads of K1 and K3 is doubled after the broken lamp beads are broken. If the dead pixel is at the edge, a column index is also needed. The number of dead pixels can be determined by sorting the distances, and the coordinates are indexed to determine the dead pixel position, as shown in table 2, the distance between the second centroid is 2 times the remaining distances, and dead pixels exist in the middle.
TABLE 1 Lamp bead barycenter coordinates
TABLE 2 calculated lamp spacing
The method can be applied to image processing software, the number and the positions of the dead pixels are determined within tens of seconds, the quality detection efficiency of the display terminal of hundreds of LEDs or more is greatly improved, in addition, the gray level average value of the gray level area of the lamp beads can be further calculated, probability statistics is carried out on all the gray level average values, the brightness level is obtained according to histogram distribution, the probability brightness value is already taken as a threshold value, the threshold value range of each lamp bead is judged, and further the brightness uniformity degree is obtained. And calculating the difference value between the brightness of each lamp bead and the standard value by solving the average value of all the brightnesses as the standard value, obtaining a difference value matrix of corresponding pixel points, and transmitting the difference value matrix to a control panel CPU for consistency control.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the scope of the present invention, which is defined in the appended claims.
Claims (2)
1. A visual detection method for LED display terminal dead pixels is characterized by comprising the following steps:
(1) acquiring an image of the display terminal, namely acquiring the image of the LED display terminal by using a camera;
(2) image correction, namely performing image correction on the image acquired in the step (1);
(3) enhancing the image, namely filtering out noise by adopting open operation of a binary morphological algorithm, corroding the image of the display terminal to remove noise of connected small white dots, and then performing expansion recovery, thereby improving the image identification degree of each lamp bead;
(4) image edge detection, namely, sharpening the image obtained in the step (3) and enhancing the edge and gray level jump part of the image so as to determine the boundaries of all LED lamp beads and position the lamp beads;
(5) filling single-lamp images, namely communicating and filling each lamp bead region, and performing binarization processing to obtain binary images with clear contrast;
(6) determining the centroid of the lamp bead image, wherein in the image obtained in the step (5), the edge contour of each lamp bead is an irregular closed contour line, but the centroid can be determined to be in the closed line, and as the closed contour lines are closer to a circle, each closed contour line is subjected to circle fitting to obtain a regular circular contour line, and the image is utilizedOrigin moment M of00The moment center can be calculated by a formula, and then the coordinates of the mass centers of all the lamp beads are obtained;
(7) and (4) determining dead spots, measuring a fixed value of the distance between the lamp beads, calculating the centroid distance between the lamp beads in the image obtained in the step (6), comparing the centroid distance with the fixed value, if the centroid distance is close to or the same as the fixed value, no dead spots exist, and if the centroid distance is more than 2 times of the fixed value, dead spots exist.
2. The visual inspection method of LED display terminal dead pixel as claimed in claim 1, wherein: the step (2) of image correction includes correction of keystone distortion caused by vertical deviation of the camera and the target and correction of tilt distortion caused by horizontal deviation, and the image correction includes the following steps:
correcting the keystone distortion, firstly, performing image enhancement of histogram equalization on an image of a display terminal, then performing edge detection, finally, solving an extreme value by utilizing Radon transformation to extract a straight line profile, and further, obtaining a detected straight line for correction;
correcting the tilt distortion, firstly intercepting an effective image in a background through an imcrop function, and enabling the image of a display terminal to fill the whole field of view; then, converting an image of the display terminal from an RGB (red, green and blue) image into a gray image, binarizing by using a threshold value method, determining a contour by adopting edge detection, extracting 4 vertex coordinates, and determining an angle between a rectangular side and a horizontal line; and extracting an ROI (region of interest), creating a white MASK template, and performing affine transformation rotation correction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110046381.7A CN112801947A (en) | 2021-01-14 | 2021-01-14 | Visual detection method for dead pixel of LED display terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110046381.7A CN112801947A (en) | 2021-01-14 | 2021-01-14 | Visual detection method for dead pixel of LED display terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112801947A true CN112801947A (en) | 2021-05-14 |
Family
ID=75810683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110046381.7A Withdrawn CN112801947A (en) | 2021-01-14 | 2021-01-14 | Visual detection method for dead pixel of LED display terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801947A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113539153A (en) * | 2021-07-27 | 2021-10-22 | 厦门大学 | Method for repairing four-primary-color display screen dead pixel |
| CN114140426A (en) * | 2021-11-29 | 2022-03-04 | 广州海谷电子科技有限公司 | Inclination correction algorithm for humidity sensor ceramic substrate printing carbon line image processing |
| CN114166849A (en) * | 2021-11-29 | 2022-03-11 | 广州海谷电子科技有限公司 | Method for detecting defects of printed carbon lines and moisture-sensitive film of humidity sensor |
| CN114202515A (en) * | 2021-11-29 | 2022-03-18 | 广州海谷电子科技有限公司 | Method for detecting defect of printed carbon line of humidity sensor |
| CN116758163A (en) * | 2023-08-15 | 2023-09-15 | 长春希达电子技术有限公司 | Optical information extraction method and device and spherical display screen correction method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120133816A1 (en) * | 2010-11-30 | 2012-05-31 | Canon Kabushiki Kaisha | System and method for user guidance of photographic composition in image acquisition systems |
| CN110070524A (en) * | 2019-04-03 | 2019-07-30 | 北京东舟技术股份有限公司 | A kind of intelligent terminal panel visual fault detection system |
| CN110490847A (en) * | 2019-07-31 | 2019-11-22 | 浙江大学山东工业技术研究院 | The LED chip quality determining method of view-based access control model |
-
2021
- 2021-01-14 CN CN202110046381.7A patent/CN112801947A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120133816A1 (en) * | 2010-11-30 | 2012-05-31 | Canon Kabushiki Kaisha | System and method for user guidance of photographic composition in image acquisition systems |
| CN110070524A (en) * | 2019-04-03 | 2019-07-30 | 北京东舟技术股份有限公司 | A kind of intelligent terminal panel visual fault detection system |
| CN110490847A (en) * | 2019-07-31 | 2019-11-22 | 浙江大学山东工业技术研究院 | The LED chip quality determining method of view-based access control model |
Non-Patent Citations (2)
| Title |
|---|
| 刘宁宁 等: ""基于扫描图像几何畸变的算法研究"", 《包装工程》 * |
| 谢欢 等: ""基于机器视觉的ＬＥＤ大屏亮度一致性检测与矫正"", 《南京大学学报（自然科学）》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113539153A (en) * | 2021-07-27 | 2021-10-22 | 厦门大学 | Method for repairing four-primary-color display screen dead pixel |
| CN113539153B (en) * | 2021-07-27 | 2023-06-09 | 厦门大学 | Method for repairing bad pixels of four-primary-color display screen |
| CN114140426A (en) * | 2021-11-29 | 2022-03-04 | 广州海谷电子科技有限公司 | Inclination correction algorithm for humidity sensor ceramic substrate printing carbon line image processing |
| CN114166849A (en) * | 2021-11-29 | 2022-03-11 | 广州海谷电子科技有限公司 | Method for detecting defects of printed carbon lines and moisture-sensitive film of humidity sensor |
| CN114202515A (en) * | 2021-11-29 | 2022-03-18 | 广州海谷电子科技有限公司 | Method for detecting defect of printed carbon line of humidity sensor |
| CN114166849B (en) * | 2021-11-29 | 2022-12-20 | 广州海谷电子科技有限公司 | Method for detecting defects of printed carbon lines and moisture-sensitive film of humidity sensor |
| CN116758163A (en) * | 2023-08-15 | 2023-09-15 | 长春希达电子技术有限公司 | Optical information extraction method and device and spherical display screen correction method and device |
| CN116758163B (en) * | 2023-08-15 | 2023-11-14 | 长春希达电子技术有限公司 | Optical information extraction method and device and spherical display screen correction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112801947A (en) | Visual detection method for dead pixel of LED display terminal | |
| WO2017157034A1 (en) | Method, device, and storage medium for identifying two-dimensional code | |
| CN112669394B (en) | Automatic calibration method for vision detection system | |
| CN109872309B (en) | Detection system, method, device and computer readable storage medium | |
| CN105338342B (en) | The detection method and device of a kind of dead pixel points of images | |
| CN106157286A (en) | Image processing method and screen light leak test method | |
| CN107256689A (en) | Uniformity restorative procedure after LED display gamma correction | |
| CN108257187B (en) | Camera-projector system calibration method | |
| CN115797775B (en) | Intelligent illegal building identification method and system based on near-to-ground video image | |
| CN111476712B (en) | Trolley grate image shooting and detecting method and system of sintering machine | |
| CN114267267A (en) | Bright and dark seam repairing method, device and system for virtual pixel LED display screen | |
| CN116563298B (en) | Cross line center sub-pixel detection method based on Gaussian fitting | |
| CN112634179B (en) | Camera shake prevention power transformation equipment image change detection method and system | |
| TWI465699B (en) | Method of water level measurement | |
| CN115880683B (en) | Urban waterlogging ponding intelligent water level detection method based on deep learning | |
| CN102885631B (en) | Distortion correction method applied to flat-panel charge coupling device (CCD) detector | |
| CN111738936A (en) | Image processing-based multi-plant rice spike length measuring method | |
| CN113916892B (en) | Multi-view vision-based brake disc gluing defect detection device and method | |
| CN116309417A (en) | Grid line detection method and device for solar cell | |
| CN115376131A (en) | Design and identification method of dot-shaped coding mark | |
| CN115035847A (en) | LED screen coefficient correction method, device and equipment | |
| CN114354622A (en) | Defect detection method, device, equipment and medium for display screen | |
| CN112085803B (en) | Multi-lens multi-detector spliced camera color consistency processing method | |
| CN114693656A (en) | Method for detecting display defects of LED display screen and method for calibrating camera and optical filter | |
| CN114359414A (en) | Lens smudge identification method and device, computer equipment and storage medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210514 |