CN109949725B - Image gray level standardization method and system for AOI system - Google Patents
Image gray level standardization method and system for AOI system Download PDFInfo
- Publication number
- CN109949725B CN109949725B CN201910169382.3A CN201910169382A CN109949725B CN 109949725 B CN109949725 B CN 109949725B CN 201910169382 A CN201910169382 A CN 201910169382A CN 109949725 B CN109949725 B CN 109949725B
- Authority
- CN
- China
- Prior art keywords
- gray
- detected
- picture
- image
- defect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses an AOI system image gray scale standardization method and a system, which comprises the following specific steps: establishing a simulated defect sample image for the picture to be detected, counting and comparing detection results of the defect sample in the picture to be detected under different image gray levels, and determining the optimal gray value I of the picture to be detected according to the detection results r (ii) a And calculating compensation parameters of the picture to be detected by using the overall gray average value and the optimal gray value of the picture to be detected and a preset image gray compensation formula, and compensating the gray value of each pixel point of the picture to be detected by using the calculated compensation parameters, thereby realizing the gray standardization of the picture to be detected.
Description
Technical Field
The invention belongs to the field of image detection, and particularly relates to an AOI system image gray level standardization method and system.
Background
AOI (Automatic optical Inspection, automated optical Inspection) is widely used in display defect detection. In the AOI detection process of the display screen, the display screen sequentially displays the pictures to be detected, the vision sensor synchronously shoots the pictures to be detected, and the defect detection process is started after the image capture is finished. Consistency of image quality is the basis for automatic optical inspection defect detection rates.
However, the following two main factors are the influence of the uniformity of the image gray levels on the detection: and evaluating the consistency of the image gray level and the target gray level value of the picture to be detected. Due to the fact that the display defect characteristic forms are various, when the image gray level fluctuates up and down, the contrast ratio and the defect area of the defect are affected, and the evaluation of the system on the defect grade of the display screen is directly affected; meanwhile, the defect display characteristics are varied due to the fact that the defect display characteristics are various in form and different image gray values. For example, a weak bright defect is weaker in a high gray scale image, and a weak dark defect is difficult to distinguish in a low gray scale image.
In an automatic production line of display screens, a Gamma curve of the display screen is a main reason of image gray scale fluctuation. The Gamma value of the display screen represents the relationship between the display gray scale value and the display brightness. Since the Gamma curves of different display screens are different, taking the L48 picture as an example, the brightness of the same gray-scale picture L48 displayed by different liquid crystal modules is not the same. After the liquid crystal module without Gamma correction enters the automatic optical detection station, when the exposure time of the visual sensor and the backlight brightness are kept unchanged, the overall gray scale of the image to be detected is abnormally fluctuated, and the evaluation of the detection system on the defect grade is interfered. The method can standardize the whole gray value of the picture to be detected by adopting hardware adjusting modes such as camera automatic exposure, self-adaptive backlight and the like, but the method can increase the time consumption of the system and has high hardware cost, and meanwhile, the evaluation of the gray value of the picture to be detected mainly gives an empirical value according to field repeated debugging, so that a standard evaluation method is lacked.
Disclosure of Invention
Aiming at the defects or improvement requirements in the prior art, the invention provides an AOI system image gray level standardization method and system, which establish a simulated defect sample image for a picture to be detected so as to determine the optimal gray level value of the picture to be detected, further calculate compensation parameters and compensate the gray level value of each pixel point of the picture to be detected, thereby realizing the gray level standardization of the picture to be detected.
In order to achieve the above object, according to an aspect of the present invention, there is provided an AOI system image gray level normalization method, including:
s1, establishing a simulated defect sample image for a picture to be detected, counting and comparing detection results of defect samples in the picture to be detected under different image gray scales, and determining the optimal gray value Ir of the picture to be detected according to the detection results;
s2, calculating compensation parameters of the picture to be detected by using the overall gray average value, the optimal gray value and a preset image gray compensation formula of the picture to be detected, and compensating the gray value of each pixel point of the picture to be detected by using the calculated compensation parameters, thereby realizing the gray level standardization of the picture to be detected.
As a further improvement of the present invention, step S1 specifically includes:
s1.1, simulating a point defect sample of each gray scale in a designated area of a picture image to be detected so as to generate a simulated point defect sample;
s1.2, collecting simulated point defect sample images under the mean value of the central gray scale of each image;
s1.3, detecting the simulated point defect sample image under the central gray level mean value of each image, and counting the defect data of the simulated point defect sample image under the central gray level mean value of each image.
As a further improvement of the present invention, step S1.3 specifically is: extracting the defects of the simulated point defect sample images under different image center gray level mean values by using a point defect detection method and the same detection parameters, and counting the number of the detected defects, the defect contrast and the defect area in the simulated point defect sample images under different image center gray level mean values; determining the optimal gray value I of the picture to be detected according to the defect data r 。
As a further improvement of the invention, the overall gray level mean value calculation formula of the picture to be detected is
In the formula, R is the area of the picture to be detected, the gray value of the pixel point (x, y) in R is f (x, y), and A is the area of the picture to be detected.
As a further improvement of the present invention, step S2 uses an iterative algorithm to calculate the compensation parameters of the picture to be examined, specifically:
a preset initial gray value I s And number of iterationsN, calculating an initial compensation coefficient gamma 0 ＝sqrt(I s /I c )；
Starting from n equal to 0, let γ n+1 ＝γ n +1, converting gamma n Substituting into preset image gray compensation formula I n (x,y)＝a γn *[f(x,y)] γn Obtaining the gray value I of the image to be detected after the pixel point with the coordinate (x, y) is compensated n (x, y), further calculating to obtain the integral gray average value of the image corresponding to the nth iteration, namely
Iteration end condition is | I n -I r If | is less than a preset threshold, γ at the end of iteration n The gray value compensation coefficient gamma is obtained;
wherein, γ n Is the gray value compensation coefficient in the nth iteration, and a is the coefficient of the preset image gray value compensation formula.
To achieve the above object, according to another aspect of the present invention, there is provided an AOI system image gray scale normalization system, which includes an analog defect processing module and a gray scale compensation processing module,
the analog defect processing module is used for establishing an analog defect sample image for the picture to be detected, counting and comparing detection results of the defect sample in the picture to be detected under different image gray scales, and determining the optimal gray value Ir of the picture to be detected according to the detection results;
the gray compensation processing module is used for calculating compensation parameters of the to-be-detected picture by using the overall gray average value, the optimal gray value Ir and a preset image gray compensation formula of the to-be-detected picture, and compensating the gray value of each pixel point of the to-be-detected picture by using the calculated compensation parameters, so that the gray standardization of the to-be-detected picture is realized.
As a further improvement of the invention, the simulated defect processing module comprises a simulated point defect generating module, an image acquisition module and a defect data processing module which are connected in sequence, wherein,
the simulation point defect generation module is used for simulating point defect samples of each gray scale in the designated area of the picture image to be detected so as to generate simulation point defect samples;
the image acquisition module is used for acquiring simulated point defect sample images under the central gray level mean value of each image;
the defect data processing module is used for detecting the simulated point defect sample images under the central gray level mean value of each image and counting the defect data of the simulated point defect sample images under the central gray level mean value of each image.
As a further improvement of the invention, the simulated defect processing module utilizes a point defect detection method and the same detection parameters to extract the defects of the simulated point defect sample images under different image central gray level mean values, and counts the number of the defects, the defect contrast and the defect area in the simulated point defect sample images under different image central gray level mean values; determining the optimal gray value I of the picture to be detected according to the defect data r 。
As a further improvement of the invention, the calculation formula of the overall gray level mean value of the picture to be detected is
In the formula, R is the area of the picture to be detected, the gray value of the pixel point (x, y) in R is f (x, y), and A is the area of the picture to be detected.
As a further improvement of the invention, the gray compensation processing module utilizes an iterative algorithm to calculate the compensation parameters of the picture to be detected, and specifically comprises the following steps:
a preset initial gray value I s And the number of iterations N, calculating an initial compensation coefficient gamma 0 ＝sqrt(I s /I c )；
Starting from n equal to 0, let γ n+1 ＝γ n +1, converting gamma n Substituting into preset image gray compensation formula I n (x,y)＝a γn *[f(x,y)] γn Obtaining the gray value I of the image to be detected after the pixel point with the coordinate (x, y) is compensated n (x, y), further calculating to obtain the integral gray average value of the image corresponding to the nth iteration, namely
Iteration end condition is | I n -I r If | is less than a preset threshold, γ at the end of iteration n The gray value compensation coefficient gamma is obtained;
wherein, γ n Is the gray value compensation coefficient in the nth iteration, and a is the coefficient of the preset image gray value compensation formula.
Generally, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects:
aiming at the problem of nonuniform images to be detected caused by Gamma curve difference between liquid crystal panels, the method and the system establish a simulated defect sample image for the image to be detected so as to determine the optimal gray value of the image to be detected, further calculate compensation parameters and compensate the gray value of each pixel point of the image to be detected, thereby realizing gray standardization of the image to be detected.
According to the AOI system image gray level standardization method and system, the defects of the simulation point defect sample images under different image center gray level mean values are extracted by using the point defect detection method and the same detection parameters, so that the accurate extraction of the information of the defects is facilitated, and the accuracy of the optimal gray level value of the to-be-detected picture is further improved.
According to the AOI system image gray level standardization method and system, the compensation parameters of the to-be-detected picture are calculated through the iterative algorithm to compensate the gray values of all the pixel points of the to-be-detected picture, so that the real information of the defects of the liquid crystal module can be extracted more favorably, and the evaluation defect level of the AOI image detection system is further improved.
Drawings
Fig. 1 is a schematic diagram of an AOI system image gray level normalization method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other. The present invention will be described in further detail with reference to specific embodiments.
Fig. 1 is a schematic diagram of an AOI system image gray level normalization method according to an embodiment of the present invention. As shown in fig. 1, the specific steps are as follows:
s1, establishing a simulated defect sample image for a picture to be detected, counting and comparing detection results of defect samples in the picture to be detected under different image gray scales, and determining the optimal gray value Ir of the picture to be detected according to the detection results;
the method specifically comprises the following steps:
s1.1, simulating a point defect sample of each gray scale in a designated area of a picture image to be detected, so as to generate a simulated point defect sample;
the method specifically comprises the following steps: generating simulation point defects in all central areas of the picture to be detected, wherein the areas comprise 256 sub-pixel point defects (minimum unit defects of a display screen), and the 256 defect gray scales are 0-255;
s1.2, acquiring simulated point defect sample images under the central gray level mean value of each image;
s1.3, detecting the simulated point defect sample image under the central gray level mean value of each image, and counting the defect data of the simulated point defect sample image under the central gray level mean value of each image.
The method specifically comprises the following steps: extracting the defects of the simulated point defect sample images under different image center gray level mean values by using a point defect detection method and the same detection parameters, and counting the number of the detected defects, the defect contrast and the defect area in the simulated point defect sample images under different image center gray level mean values; and determining the optimal gray value of the picture to be detected according to the defect data.
The number of detected defects can be obtained by counting the total number of the detected defects in the designed simulated defect area in the simulated point defect sample image under the central gray level mean value of each image; the defect contrast can be obtained by counting the mean value and variance of the contrast corresponding to the detected defect at the designed simulated defect area in the simulated point defect sample image under the mean value of the central gray scale of each image; the defect area can be obtained by counting the mean value and variance of the defect area corresponding to the detected defect at the designed simulated defect area in the simulated point defect sample image under different image center gray level mean values;
the defect data comprises the defect number, the defect contrast and the defect area, the image center gray mean value corresponding to the image with the largest detected defect number of the simulation point defect sample image under each image center gray mean value is preferably the optimal gray value, the image center gray mean value corresponding to the image with the highest detected defect contrast mean value of the simulation point defect sample image under each image center gray mean value is preferably the optimal gray value, and the image center gray mean value corresponding to the image with the largest detected defect area mean value of the simulation point defect sample image under each image center gray mean value is preferably the optimal gray value.
S2, calculating compensation parameters of the picture to be detected by using the overall gray average value, the optimal gray value and a preset image gray compensation formula of the picture to be detected, and compensating the gray value of each pixel point of the picture to be detected by using the calculated compensation parameters, thereby realizing the gray level standardization of the picture to be detected.
Calculating the overall gray average value of the to-be-detected picture, namely collecting the to-be-detected picture, namely, enabling the to-be-detected picture to enter a detection carrying platform and displaying the to-be-detected picture one by one, and shooting the to-be-detected picture displayed by the panel by a visual sensor; calculating the integral gray average value I of the to-be-detected picture after collecting the to-be-detected picture c And recording R as the image area to be detected, wherein the gray value of the pixel point (x, y) in R is f (x, y), A is the area of the image to be detected, and the calculation formula of the overall gray average value of the image to be detected is
The method for calculating the compensation parameters of each sub-pixel point of the to-be-detected picture by using the optimal gray value and a preset image gray compensation formula specifically comprises the following steps: presetting an image gray level compensation formula as I (x, y) -a γ *[f(x,y)] γ In the formula, I (x, y) is a gray value after the image coordinate is compensated for the (x, y) pixel, f (x, y) is an actual gray value of the image coordinate is compensated for the (x, y) pixel, γ is a gray value compensation coefficient, and a is a coefficient of a preset image gray value compensation formula.
The standardization of the overall gray value of the picture to be detected means that the overall gray average value of the same picture to be detected among all the panels is unified into the optimal gray value I of the picture to be detected r . Taking the L48 inspection picture image as an example, the L48 inspection picture image of each inspection display screen has the uniform optimal gray value I of the inspection picture after pretreatment r 。
In order to achieve the uniform gray average value, the gray compensation coefficient gamma of the picture to be detected needs to be determined, and the specific process of calculating and determining the gray compensation coefficient gamma of the picture to be detected by utilizing an iterative algorithm is as follows:
a preset initial gray value I s And the number of iterations N, calculating an initial compensation coefficient gamma 0 ＝sqrt(I s /I c ) (ii) a Starting from n equal to 0, let γ n+1 ＝γ n +1, converting gamma n Substituting into preset image gray compensation formula I n (x,y)＝a γn *[f(x,y)] γn Obtaining the gray value I of the image to be detected after the pixel point with the coordinate (x, y) is compensated n (x, y), further calculating to obtain the integral gray average value of the image corresponding to the nth iteration, namely
The iteration termination condition is | I n -I r If | is less than a preset threshold, gamma at the end of iteration n Namely the calculated gray value compensation coefficient gamma.
And (4) after the gray value of the image to be detected is standardized, entering a defect detection flow.
An AOI system image gray scale standardization system comprises an analog defect processing module and a gray scale compensation processing module, wherein,
the analog defect processing module is used for establishing an analog defect sample image for the picture to be detected, counting and comparing detection results of the defect sample in the picture to be detected under different image gray scales, and determining the optimal gray value Ir of the picture to be detected according to the detection results;
the simulated defect processing module comprises a simulated point defect generating module, an image acquisition module and a defect data processing module which are connected in sequence, wherein,
the simulation point defect generation module is used for simulating point defect samples of all gray scales in the appointed area of the picture image to be detected so as to generate a simulation point defect sample image. In the central area of all the pictures to be detected, generating simulation point defects, wherein the area comprises 256 sub-pixel point defects (the minimum unit defect of a display screen), and the gray scales of the 256 defects are 0-255.
The image acquisition module is used for acquiring simulated point defect sample images under the central gray level mean value of each image;
the defect data processing module is used for detecting the simulated point defect sample image under the central gray level mean value of each image, counting the defect data of the simulated point defect sample image under the central gray level mean value of each image, and determining the optimal gray level value I of the picture to be detected according to the defect data r 。
The method specifically comprises the following steps: extracting the defects of the simulated point defect sample images under different image center gray level mean values by using a point defect detection method and the same detection parameters, and counting the number of the detected defects, the defect contrast and the defect area in the simulated point defect sample images under different image center gray level mean values;
the number of detected defects can be obtained by counting the total number of the detected defects in the designed simulated defect area in the simulated point defect sample image under the central gray level mean value of each image; the defect contrast can be obtained by counting the mean value and variance of the contrast corresponding to the detected defect at the designed simulated defect area in the simulated point defect sample image under the mean value of the central gray scale of each image; the defect area can be obtained by counting the mean value and variance of the defect area corresponding to the detected defect at the designed simulated defect area in the simulated point defect sample image under different image center gray level mean values;
the defect data comprises the number of defects, defect contrast and defect area, preferably, the image center gray mean value corresponding to the image with the largest number of detected defects of the simulated point defect sample image under each image center gray mean value is the optimal gray value, preferably, the image center gray mean value corresponding to the image with the highest defect contrast mean value of the simulated point defect sample image under each image center gray mean value is the optimal gray value, and preferably, the image center gray mean value corresponding to the image with the largest defect area mean value of the simulated point defect sample image under each image center gray mean value is the optimal gray value.
The gray compensation processing module is used for calculating compensation parameters of the picture to be detected by using the overall gray average value, the optimal gray value and a preset image gray compensation formula of the picture to be detected, and compensating the gray value of each pixel point of the picture to be detected by using the calculated compensation parameters, so that the gray standardization of the picture to be detected is realized.
The gray compensation processing module calculates and determines a gray compensation coefficient gamma of the picture to be detected by using an iterative algorithm, and specifically comprises the following steps:
a preset initial gray value I s And the number of iterations N, calculating an initial compensation coefficient gamma 0 ＝sqrt(I s /I c ) (ii) a Starting from n equal to 0, let γ n+1 ＝γ n +1, converting gamma n Substituting into preset image gray compensation formula I n (x,y)＝a γn *[f(x,y)] γn Obtaining the gray value of the image to be detected after the pixel point coordinates are (x, y) compensated, and further calculating to obtain the integral gray average value of the image corresponding to the nth iteration, namely
The iteration termination condition is | I n -I r If | is less than a preset threshold, γ at the end of iteration n Namely the calculated gray value compensation coefficient gamma.
And (4) after the gray value of the image to be detected is standardized, entering a defect detection flow.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (4)
1. An AOI system image gray level standardization method is characterized by comprising the following specific steps:
s1, establishing a simulated defect sample image for the picture to be detected, counting and comparing the detection results of the defect sample in the picture to be detected under different image gray levels, and determining the optimal gray value of the picture to be detected according to the detection resultsI r ；
Specifically, a point defect sample of each gray scale is simulated in a designated area of a picture image to be detected, so that a simulated point defect sample is generated; collecting simulated point defect sample images under the central gray level mean value of each image; detecting simulated point defect sample images under the central gray level mean value of each image, and counting defect data of the simulated point defect sample images under the central gray level mean value of each image;
more specifically, the determining manner of the optimal gray value is as follows: extracting the defects of the simulated point defect sample images under different image center gray level mean values by using a point defect detection method and the same detection parameters, and counting the number of detected defects, defect contrast and defect area in the simulated point defect sample images under different image center gray level mean values; determining the optimal gray value of the picture to be detected according to the defect data;
s2, calculating compensation parameters of the picture to be detected by using the overall gray average value, the optimal gray value and a preset image gray compensation formula of the picture to be detected, and compensating the gray value of each pixel point of the picture to be detected by using the calculated compensation parameters, thereby realizing the gray standardization of the picture to be detected;
step S2, calculating the compensation parameters of the picture to be detected by using an iterative algorithm, specifically:
preset initial gray scale valueI S And the number of iterations n, calculating an initial compensation factorγ 0 ＝sqrt（I S /I C ）；I C To be examinedThe overall gray level mean value of the picture;
starting from n equal to 0, letγ n＋1 ＝γ n +1, willγ n Substituting into preset image gray compensation formula
Obtaining the coordinates of the image of the picture to be detected as (x,y) Gray value compensated by pixel pointI n (x,y)，f （x，y）Is an image coordinate ofx,y) The actual gray value of the pixel point is further calculated to obtain the integral gray average value of the image corresponding to the nth iteration, namely
A is the area of the picture to be detected;
the iteration end condition is
Less than a predetermined threshold, at the end of the iterationγ n I.e. the calculated gray value compensation coefficientγ；
Wherein, the first and the second end of the pipe are connected with each other,γ n is the gray value compensation coefficient at the nth iteration,athe coefficients of the preset image gray compensation formula are obtained.
2. The method of claim 1, wherein the overall gray level mean value of the inspected image is calculated according to the formula
Wherein R is the picture area to be inspected, and R is the pixel pointx,y) Has a gray value off(x,y) And A is the area of the picture to be detected.
3. An AOI system image gray level standardization system comprises an analog defect processing module and a gray level compensation processing module,
the analog defect processing module is used for establishing an analog defect sample image for the picture to be detected, counting and comparing detection results of the defect sample in the picture to be detected under different image gray scales, and determining the optimal gray value of the picture to be detected according to the detection resultsI r ；
The simulation defect processing module comprises a simulation point defect generating module, an image acquisition module and a defect data processing module which are connected in sequence,
the simulation point defect generation module is used for simulating point defect samples of various gray scales in the appointed area of the picture image to be detected so as to generate simulation point defect samples;
the image acquisition module is used for acquiring simulated point defect sample images under the central gray level mean value of each image;
the defect data processing module is used for detecting the simulated point defect sample images under the central gray level mean value of each image and counting the defect data of the simulated point defect sample images under the central gray level mean value of each image;
more specifically, the simulated defect processing module extracts the defects of the simulated point defect sample images under different image center gray level mean values by using a point defect detection method and the same detection parameters, and counts the number of detected defects, defect contrast and defect area in the simulated point defect sample images under different image center gray level mean values; determining the optimal gray value of the picture to be detected according to the defect data;
the gray compensation processing module is used for utilizing the integral gray mean value and the optimal gray value of the picture to be detectedI r Calculating compensation parameters of the to-be-detected picture by using a preset image gray compensation formula, and compensating the gray value of each pixel point of the to-be-detected picture by using the calculated compensation parameters so as to realize gray standardization of the to-be-detected picture;
the gray compensation processing module calculates the compensation parameters of the picture to be detected by using an iterative algorithm, and specifically comprises the following steps:
preset initial gray scale valueI S And the number of iterations n, calculating the initialCompensation factorγ 0 ＝sqrt（I S /I C ）；I C The average value of the integral gray scale of the picture to be detected is obtained;
starting from n being 0, letγ n＋1 ＝γ n +1, willγ n Substituting into preset image gray compensation formula
Obtaining the coordinates of the image of the picture to be detected as (x,y) Gray value of pixel point after compensationI n (x,y)，f （x，y）Is an image coordinate ofx,y) The actual gray value of the pixel point is further calculated to obtain the integral gray average value of the image corresponding to the nth iteration, namely
A is the area of the picture to be detected;
the iteration termination condition is
Less than a predetermined threshold, at the end of the iterationγ n I.e. the compensation coefficient of the determined gray valueγ；
Wherein the content of the first and second substances,γ n is the gray value compensation coefficient at the nth iteration,athe coefficients of the preset image gray compensation formula are obtained.
4. The system according to claim 3, wherein the overall gray level mean value of the inspected image is calculated by the following formula
Wherein R is the picture area to be inspected, and R is the pixel pointx,y) Has a gray value off(x,y) And A is the area of the picture to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910169382.3A CN109949725B (en) | 2019-03-06 | 2019-03-06 | Image gray level standardization method and system for AOI system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910169382.3A CN109949725B (en) | 2019-03-06 | 2019-03-06 | Image gray level standardization method and system for AOI system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109949725A CN109949725A (en) | 2019-06-28 |
| CN109949725B true CN109949725B (en) | 2022-09-20 |
Family
ID=67009226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910169382.3A Active CN109949725B (en) | 2019-03-06 | 2019-03-06 | Image gray level standardization method and system for AOI system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109949725B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798420A (en) * | 2020-06-28 | 2020-10-20 | 苏州精濑光电有限公司 | Point screen position positioning method, device, equipment and storage medium |
| CN112130355B (en) * | 2020-09-21 | 2023-03-24 | 深圳同兴达科技股份有限公司 | Method for acquiring defective liquid crystal display module |
| CN114519714B (en) * | 2022-04-20 | 2022-07-26 | 中导光电设备股份有限公司 | Method and system for judging smudgy defect of display screen |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5517234A (en) * | 1993-10-26 | 1996-05-14 | Gerber Systems Corporation | Automatic optical inspection system having a weighted transition database |
| JP2004239733A (en) * | 2003-02-05 | 2004-08-26 | Seiko Epson Corp | Defect detection method and apparatus of screen |
| WO2014140522A2 (en) * | 2013-03-14 | 2014-09-18 | The University Court Of The University Of Edinburgh | A method of generating predetermined luminance levels across an electronic visual display |
| CN104217684A (en) * | 2014-09-11 | 2014-12-17 | 西安诺瓦电子科技有限公司 | LED (light emitting diode) defective point processing method and detection method and LED display control method |
| CN104424904A (en) * | 2013-09-11 | 2015-03-18 | 三星显示有限公司 | Method of driving a display panel,display apparatus performing the same, method of determining a correction value applied to the same, and method of correcting grayscale data |
| KR20170106527A (en) * | 2016-03-10 | 2017-09-21 | 삼성디스플레이 주식회사 | Inspection apparatus of inspecting mura defects, method of driving the inspection apparatus and display apparatus having correction value of mura defects |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007047122A (en) * | 2005-08-12 | 2007-02-22 | Tokyo Seimitsu Co Ltd | Image defect inspection device, defect classification device, and image defect inspection method |
| US20070106416A1 (en) * | 2006-06-05 | 2007-05-10 | Griffiths Joseph J | Method and system for adaptively controlling a laser-based material processing process and method and system for qualifying same |
| CN101667406B (en) * | 2009-08-14 | 2011-08-31 | 西安龙腾微电子科技发展有限公司 | Backlight dynamical adjusting method of TFT-LCD |
| CN102509300B (en) * | 2011-11-18 | 2014-07-30 | 深圳市宝捷信科技有限公司 | Defect detection method and system |
| KR102175702B1 (en) * | 2013-12-30 | 2020-11-09 | 삼성디스플레이 주식회사 | Method of compensating mura of display apparatus and vision inspection apparatus performing the method |
| CN104332421B (en) * | 2014-09-01 | 2017-05-03 | 上海华力微电子有限公司 | Performance detection method of scanning machine |
| CN105911724B (en) * | 2016-05-23 | 2018-05-25 | 京东方科技集团股份有限公司 | Determine the method and apparatus of the intensity of illumination for detection and optical detecting method and device |
| CN106127779B (en) * | 2016-06-29 | 2018-12-11 | 上海晨兴希姆通电子科技有限公司 | The defect inspection method and system of view-based access control model identification |
| CN106444105A (en) * | 2016-10-18 | 2017-02-22 | 凌云光技术集团有限责任公司 | Method, device and system for detecting defects of liquid crystal screen |
| CN206740664U (en) * | 2017-03-03 | 2017-12-12 | 重庆恒讯联盛实业有限公司 | A kind of AOI detecting and controlling systems of pcb board |
| CN107025891B (en) * | 2017-03-23 | 2019-05-10 | 武汉精测电子集团股份有限公司 | A kind of display module defect fast repairing method and system |
| US10453366B2 (en) * | 2017-04-18 | 2019-10-22 | Samsung Display Co., Ltd. | System and method for white spot mura detection |
| CN108596226A (en) * | 2018-04-12 | 2018-09-28 | 武汉精测电子集团股份有限公司 | A kind of defects of display panel training method and system based on deep learning |
| CN108646445B (en) * | 2018-05-03 | 2021-03-16 | 武汉精测电子集团股份有限公司 | Defect detection device that self-adaptation is shaded |
| CN109167928B (en) * | 2018-09-06 | 2020-11-03 | 武汉精测电子集团股份有限公司 | Rapid automatic exposure method and system based on display panel defect detection |
| CN109406529B (en) * | 2018-09-28 | 2021-09-14 | 武汉精立电子技术有限公司 | Performance adjusting method of AOI defect detection system |
-
2019
- 2019-03-06 CN CN201910169382.3A patent/CN109949725B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5517234A (en) * | 1993-10-26 | 1996-05-14 | Gerber Systems Corporation | Automatic optical inspection system having a weighted transition database |
| JP2004239733A (en) * | 2003-02-05 | 2004-08-26 | Seiko Epson Corp | Defect detection method and apparatus of screen |
| WO2014140522A2 (en) * | 2013-03-14 | 2014-09-18 | The University Court Of The University Of Edinburgh | A method of generating predetermined luminance levels across an electronic visual display |
| CN104424904A (en) * | 2013-09-11 | 2015-03-18 | 三星显示有限公司 | Method of driving a display panel,display apparatus performing the same, method of determining a correction value applied to the same, and method of correcting grayscale data |
| CN104217684A (en) * | 2014-09-11 | 2014-12-17 | 西安诺瓦电子科技有限公司 | LED (light emitting diode) defective point processing method and detection method and LED display control method |
| KR20170106527A (en) * | 2016-03-10 | 2017-09-21 | 삼성디스플레이 주식회사 | Inspection apparatus of inspecting mura defects, method of driving the inspection apparatus and display apparatus having correction value of mura defects |
Non-Patent Citations (2)
| Title |
|---|
| Novel Outlier Filtering Method for AOI Image Databases;Tibor Takacs;《IEEE Transactions on Components, Packaging and Manufacturing Technology》;20120228;700-709 * |
| TFT-LCD面板光学检测自动对焦系统设计;肖磊等;《红外与激光工程》;20110925(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109949725A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109949725B (en) | Image gray level standardization method and system for AOI system | |
| CN101655614B (en) | Method and device for detecting cloud pattern defects of liquid crystal display panel | |
| Watson | 31.1: Invited paper: The spatial standard observer: A human vision model for display inspection | |
| CN110310596B (en) | GAMMA (GAMMA-GAMMA) adjustment initial value prediction method and system of OLED module | |
| CN109167928A (en) | Fast automatic exposure method and system based on defects of display panel detection | |
| CN110428762B (en) | OLED panel aging test luminescence characteristic detection method based on pixel brightness | |
| CN109655234B (en) | Automatic testing method for camera | |
| CN112505048B (en) | Testing device and method for calibrating hydrogen concentration | |
| KR100842616B1 (en) | Method and Apparatus For Detecting Flat Panel Display By Vision Model | |
| CN103927749A (en) | Image processing method and device and automatic optical detector | |
| CN108445010A (en) | Automatic optical detection method and device | |
| CN108871185B (en) | Method, device and equipment for detecting parts and computer readable storage medium | |
| CN111638042B (en) | DLP optical characteristic test analysis method | |
| JP4610656B2 (en) | Inspection device, inspection method, program, and recording medium | |
| CN108965749A (en) | Defect pixel detection and means for correcting and method based on texture recognition | |
| CN117252872A (en) | Mobile phone screen defect visual detection method and system | |
| CN117115610A (en) | Metal surface defect detection method and system based on multi-angle image exposure fusion | |
| CN105427315B (en) | Digital instrument image position testing method and device | |
| CN116819811A (en) | Method and system for measuring response time of liquid crystal display | |
| CN106713907B (en) | A kind of the HDR image display performance evaluating method and device of display | |
| CN115546140A (en) | Display panel detection method and system and electronic device | |
| US10852250B1 (en) | Quantitative test method for striae in optical materials | |
| CN111415611A (en) | Brightness compensation method, brightness compensation device and display device | |
| CN113724201B (en) | Image sensor correction effect quantitative evaluation method based on two-dimensional Fourier transform | |
| CN113703203B (en) | Automatic testing method for display uniformity of LCD screen |
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 |