CN113570605B - Defect detection method and system based on liquid crystal display panel - Google Patents
Defect detection method and system based on liquid crystal display panel Download PDFInfo
- Publication number
- CN113570605B CN113570605B CN202111146109.2A CN202111146109A CN113570605B CN 113570605 B CN113570605 B CN 113570605B CN 202111146109 A CN202111146109 A CN 202111146109A CN 113570605 B CN113570605 B CN 113570605B
- Authority
- CN
- China
- Prior art keywords
- image
- integrated
- liquid crystal
- crystal display
- binary image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 199
- 239000004973 liquid crystal related substance Substances 0.000 title claims abstract description 136
- 238000001514 detection method Methods 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000012937 correction Methods 0.000 claims abstract description 27
- 238000005286 illumination Methods 0.000 claims abstract description 27
- 230000003287 optical effect Effects 0.000 claims abstract description 18
- 238000006243 chemical reaction Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 230000001678 irradiating effect Effects 0.000 claims abstract description 3
- 238000012545 processing Methods 0.000 claims description 44
- 238000004519 manufacturing process Methods 0.000 claims description 31
- 230000002950 deficient Effects 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000000877 morphologic effect Effects 0.000 description 14
- 230000006870 function Effects 0.000 description 10
- 230000011218 segmentation Effects 0.000 description 10
- 238000009825 accumulation Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000003860 storage Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000004931 aggregating effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000010339 dilation Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009466 transformation Effects 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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G02—OPTICS
- G02F—OPTICAL DEVICES OR ARRANGEMENTS FOR THE CONTROL OF LIGHT BY MODIFICATION OF THE OPTICAL PROPERTIES OF THE MEDIA OF THE ELEMENTS INVOLVED THEREIN; NON-LINEAR OPTICS; FREQUENCY-CHANGING OF LIGHT; OPTICAL LOGIC ELEMENTS; OPTICAL ANALOGUE/DIGITAL CONVERTERS
- G02F1/00—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics
- G02F1/01—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics for the control of the intensity, phase, polarisation or colour
- G02F1/13—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics for the control of the intensity, phase, polarisation or colour based on liquid crystals, e.g. single liquid crystal display cells
- G02F1/1306—Details
- G02F1/1309—Repairing; Testing
-
- 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
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- 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)
- Nonlinear Science (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Optics & Photonics (AREA)
- Quality & Reliability (AREA)
- Testing Of Optical Devices Or Fibers (AREA)
- Liquid Crystal (AREA)
Abstract
The invention provides a defect detection method and system based on a liquid crystal display panel, wherein the method comprises the following steps: positioning the liquid crystal display panel to be detected at a detection position, starting a light source and irradiating the liquid crystal display panel to be detected; collecting reflected light of a liquid crystal display panel to be detected through an optical module, focusing the reflected light on an image sensor, and carrying out image acquisition through the image sensor and carrying out photoelectric conversion and analog-to-digital conversion to form an original digital image; acquiring an original digital image from the image sensor by a preprocessing module, and carrying out image inclination correction and uneven illumination correction on the original digital image to generate a new digital image; and acquiring a new digital image by the computer, performing image identification and defect detection by adopting a preset defect detection algorithm, and outputting a defect detection result. The invention can realize the intelligent detection of the liquid crystal display panel and effectively improve the detection efficiency and accuracy.
Description
Technical Field
The invention relates to the technical field of defect detection, in particular to a defect detection method and system based on a liquid crystal display panel.
Background
In recent years, with the rapid development of global science and technology, the development scale of liquid crystal display and related industries is increasing worldwide, and the market and production manufacturer industries of TFT-LCD and related industries are also increasing. Initially, the TFT-LCD technology was world-oriented in japan, and subsequently, korea and taiwan gradually developed, and the annual rate of speed increased in these years is doubled. The TFT-LCD gradually occupies the leading position of the display with the advantages of low cost, superior volume advantage, high resolution, high brightness and the like, and is widely applied to the living and office fields of smart phones, desktop and notebook computers, multimedia conference terminal display screens, smart watches, vehicle-mounted multimedia terminals, household smart televisions and the like.
With the continuous development of the TFT-LCD industry, the quality requirement of the TFT-LCD is higher and higher, so that the quality inspection of the TFT-LCD is required in the manufacturing process of the TFT-LCD. The traditional detection mode is manual detection, however, the detection precision and the detection efficiency of the manual detection mode are not high, and the labor cost is additionally increased.
Disclosure of Invention
In order to solve at least one technical problem, the invention provides a defect detection method and system based on a liquid crystal display panel, which can realize intelligent detection of the liquid crystal display panel and effectively improve detection efficiency and accuracy.
The invention provides a defect detection method based on a liquid crystal display panel in a first aspect, which comprises the following steps:
respectively positioning the liquid crystal display panels to be detected, which are synchronously produced by a plurality of production lines, at detection positions on corresponding production lines, starting a light source and irradiating the liquid crystal display panels to be detected;
collecting reflected light of a liquid crystal display panel to be detected through an optical module, focusing the reflected light on an image sensor, and carrying out image acquisition through the image sensor and carrying out photoelectric conversion and analog-to-digital conversion to form an original digital image;
the method comprises the steps that a preprocessing module acquires original digital images corresponding to liquid crystal display panels to be detected from image sensors of a plurality of production lines, and performs image inclination correction and uneven illumination correction on each original digital image to generate new digital images;
respectively carrying out image recognition analysis processing on the plurality of new digital images by the computer to obtain serial numbers corresponding to the liquid crystal display panel to be detected;
carrying out binarization processing on the plurality of new digital images by a computer to obtain corresponding binarized images, and establishing a binding relationship between the plurality of binarized images and the serial numbers of the corresponding liquid crystal display panels to be tested;
combining a plurality of binary images according to a preset combination mode to form an integrated binary image, and performing calculation processing on the integrated binary image according to a preset defect detection algorithm to obtain defect points of the integrated binary image;
and determining a defect detection result corresponding to the liquid crystal display panel to be detected based on the defect points of the integrated binary image and the binding relationship between the plurality of binary images and the serial number of the corresponding liquid crystal display panel to be detected.
In this scheme, combine a plurality of binary image according to predetermined combination mode and form and integrate binary image, specifically include:
presetting a combined model, wherein the combined model comprises a plurality of combined areas, the plurality of combined areas are respectively in one-to-one correspondence with the plurality of production lines, and the number of the preset combined areas is G1;
and respectively filling a plurality of binary images synchronously obtained from a plurality of production lines into the corresponding combined areas, and obtaining an integrated binary image after the filling is finished.
In the scheme, the integrated binary image is calculated according to a preset defect detection algorithm to obtain defect points of the integrated binary image, and the method specifically comprises the following steps:
randomly selecting G2 binary images from the plurality of binary images of the integrated binary image as template binary images, wherein G2 is smaller than G1;
respectively copying each template binary image into G1 identical template binary images;
filling G1 identical template binary images of each template binary image into a combined area corresponding to the combined model respectively based on each template binary image to form G2 integrated template binary images respectively;
and respectively carrying out difference analysis processing on the integrated binary image and the G2 integrated template binary images to obtain defect points of the integrated binary image.
In the scheme, the integrated binary image and the G2 integrated template binary images are subjected to difference analysis processing of gray values to obtain defect points of the integrated binary image, and the method specifically comprises the following steps:
subtracting the gray value of the pixel point corresponding to the first integrated template binary image from the gray value of the first pixel point in the integrated binary image to obtain a first gray difference of the first pixel point;
calculating the absolute value of the first gray difference, judging whether the absolute value of the first gray difference is greater than a first threshold value, and if so, determining a first pixel point of the integrated binary image as a primary defect suspicious point;
respectively carrying out gray difference calculation on the gray value of a first pixel point in the integrated binary image and the gray value of a pixel point corresponding to the residual integrated template binary image, comparing the absolute value of the obtained gray difference with a first threshold value, and determining whether the first pixel point can be identified as a defect suspicious point or not according to the comparison result;
counting the total times of the first pixel points in the integrated binary image which are determined as suspected defect points;
judging whether the total times is greater than a second threshold value or not, and if so, marking a first pixel point in the integrated binary image as a defect point;
and respectively carrying out difference ratio analysis processing on the remaining pixel points of the integrated binary image and the gray values of the corresponding pixel points of the G2 integrated template binary images to obtain all defect points in the integrated binary image.
In this scheme, based on the defect point of integrating the binary image to combine the binding relationship between a plurality of binary images and the serial number of the corresponding liquid crystal display panel that awaits measuring, determine the defect detection result of the corresponding liquid crystal display panel that awaits measuring, specifically include:
splitting the integrated binary image into binary images marked by a plurality of defect points according to a plurality of combined areas;
matching the binary images of the plurality of defect point marks with the liquid crystal display panel to be tested corresponding to the serial number one by combining the binding relationship between the binary images of the plurality of defect point marks and the serial number of the liquid crystal display panel to be tested corresponding to the serial number;
and judging whether the marked defect points exist in advance based on the binary image marked by each defect point, if not, judging that the corresponding liquid crystal display panel to be detected is a non-defective product, if so, evaluating the marked defect points according to a preset evaluation mode, and judging whether the corresponding liquid crystal display panel to be detected is a qualified product according to the evaluation result.
In the scheme, the defect points of the marks are evaluated according to a preset evaluation mode, and whether the corresponding liquid crystal display panel to be tested is a qualified product or not is judged according to the evaluation result, and the method specifically comprises the following steps:
dividing the liquid crystal display panel to be tested into e areas, and presetting the influence weight of the defect points of different areas on the product qualityWherein;
Counting the number of the defective points of the binary image marked by a defective point and falling into e areas as;
Counting the number of defective points in each regionRespectively corresponding influence weightMultiplying to obtain the quality influence factor of each region;
Accumulating the quality influence factors of the regionsObtaining a global quality impact factor of;
Determining a global quality impact factor ofWhether or not to exceed the thirdAnd if so, judging that the corresponding liquid crystal display panel to be detected is a qualified product, and if not, judging that the corresponding liquid crystal display panel to be detected is an unqualified product.
The second aspect of the present invention further provides a defect detection system based on a liquid crystal display panel, the system comprising: the system comprises a light source, an optical module, an image sensor, a preprocessing module and a computer;
the light source is used for providing irradiation light for the liquid crystal display panel to be detected positioned at the detection position;
the optical module is used for collecting the reflected light of the liquid crystal display panel to be detected and focusing the reflected light on the image sensor;
the image sensor is used for collecting an optical image focused by the optical module and performing photoelectric conversion and analog-to-digital conversion to form an original digital image;
the preprocessing module is used for acquiring an original digital image from the image sensor, and performing image inclination correction and uneven illumination correction on the original digital image to generate a new digital image;
the computer is used for carrying out image recognition analysis processing on the plurality of new digital images to obtain serial numbers corresponding to the liquid crystal display panel to be detected; simultaneously carrying out binarization processing on the plurality of new digital images to obtain corresponding binarized images, and establishing a binding relationship between the plurality of binarized images and the serial numbers of the corresponding liquid crystal display panels to be tested; the integrated binary image processing device is also used for combining the plurality of binary images according to a preset combination mode to form an integrated binary image, and calculating the integrated binary image according to a preset defect detection algorithm to obtain defect points of the integrated binary image; and finally, determining a defect detection result of the corresponding liquid crystal display panel to be detected based on the defect points of the integrated binary image and the binding relationship between the plurality of binary images and the serial number of the corresponding liquid crystal display panel to be detected.
The defect detection method and system based on the liquid crystal display panel can realize intelligent detection of the liquid crystal display panel and effectively improve detection efficiency and accuracy.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flow chart of a defect detection method based on a liquid crystal display panel according to the present invention;
FIG. 2 is a schematic diagram of a defect detection system based on a liquid crystal display panel according to the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
FIG. 1 is a flow chart of a defect detection method based on a liquid crystal display panel according to the present invention.
As shown in fig. 1, a first aspect of the present invention provides a method for detecting defects based on a liquid crystal display panel, the method comprising:
s102, respectively positioning the liquid crystal display panels to be detected produced by a plurality of production lines synchronously at detection positions on corresponding production lines, and starting a light source to irradiate the liquid crystal display panels to be detected;
s104, collecting reflected light of the liquid crystal display panel to be detected through an optical module, focusing the reflected light on an image sensor, and carrying out image acquisition through the image sensor and carrying out photoelectric conversion and analog-to-digital conversion to form an original digital image;
s106, acquiring original digital images corresponding to the liquid crystal display panel to be detected from the image sensors of the multiple production lines by the preprocessing module, and performing image inclination correction and uneven illumination correction on each original digital image to generate a new digital image;
s108, respectively carrying out image recognition analysis processing on the plurality of new digital images by the computer to obtain serial numbers corresponding to the liquid crystal display panel to be detected;
s110, performing binarization processing on the new digital images by using a computer to obtain corresponding binarized images, and establishing a binding relationship between the binarized images and the serial numbers of the corresponding liquid crystal display panels to be tested;
s112, combining the multiple binary images according to a preset combination mode to form an integrated binary image, and performing calculation processing on the integrated binary image according to a preset defect detection algorithm to obtain defect points of the integrated binary image;
and S114, determining a defect detection result of the corresponding liquid crystal display panel to be detected based on the defect points of the integrated binary image and the binding relationship between the plurality of binary images and the serial number of the corresponding liquid crystal display panel to be detected.
It is understood that the Liquid Crystal Display panel (TFT-LCD) has many types of defects, and generally has some defects, line defects, Mura defects, uneven brightness and flicker, and the like.
The invention uses optical instruments such as a CCD industrial camera to replace human eyes, a liquid crystal display panel displays images and collects the images through the industrial CCD industrial camera, then the images are converted into digital image information after being processed, and finally the digital image information is transmitted to a detection module of a computer and processed by a defect detection algorithm arranged in the computer to identify whether defects exist.
It should be noted that, in an embodiment, the liquid crystal display panel to be detected may be positioned at the detection position by using a manner that a conveyor belt or a manipulator is matched with the positioning device, specifically, the liquid crystal display panel to be detected is conveyed to the positioning device by using the conveyor belt or the manipulator, and a positioning fixture of the positioning device is started to fix the liquid crystal display panel to be detected at the detection position, so that the effects of automatic transportation and positioning are achieved, and the transportation cost of manpower is saved.
It can be understood that in the process of manufacturing the liquid crystal display panel to be detected, a plurality of production lines are usually provided and are synchronously produced, that is, each production line almost simultaneously produces one liquid crystal display panel, if each production line is provided with a computer and carries out defect analysis, the detection efficiency is not high, in the invention, one computer is used for collecting images collected by image sensors of a plurality of production lines and combining the images to form a global image, and then the global image is subjected to unified image defect analysis, so that the detection efficiency is improved, and the detection cost is saved.
It can be understood that the image acquired by the image sensor may be incorrect due to the inclination of the placement angle of the liquid crystal display panel to be detected, and if the inclination correction processing is not performed in time, the subsequent defect identification accuracy may be affected. In addition, due to different irradiation angles or irradiation distances of the light source on the liquid crystal display panel to be detected, uneven illumination brightness of the formed image can be caused, and the subsequent defect identification accuracy can be influenced. Based on the above, the invention optimizes the original digital image by image tilt correction and illumination unevenness correction processing in the preprocessing stage, thereby facilitating the improvement of the accuracy of the subsequent defect detection.
According to a specific embodiment of the present invention, after forming the primary digital image, the method further comprises:
the image is subjected to a deformity correction process.
Specifically, feature points in the original digital image are detected, internal and external parameters and distortion coefficients of the image sensor are obtained, and the internal and external parameters and the distortion coefficients of the image sensor are substituted into a distortion correction model to perform image deformity correction processing on the original digital image.
It will be appreciated that in image measurement processes and machine vision applications, in order to determine the correlation between the three-dimensional geometric position of a point on the surface of an object in space and its corresponding point in the image, it is necessary to build a geometric model of the image sensor image, and these geometric model parameters are the image sensor parameters. Under most conditions, the parameters are obtained through experiments and calculation, and the process of solving the parameters is called image sensor calibration. It can be understood that the accuracy of the calibration result of the image sensor and the stability of the algorithm directly affect the accuracy of the result generated by the operation of the camera.
According to an embodiment of the present invention, the image tilt correction specifically includes:
presetting a liquid crystal display panel to be tested to be a rectangle, and performing morphological closing operation processing and morphological opening operation processing on an original digital image to obtain a morphological optimization image;
finding out each Harris angular point of the liquid crystal display panel to be tested in the morphology optimization image through a Harris angular point function, wherein each Harris angular point surrounds the periphery of the liquid crystal display panel to be tested;
connecting each corner point by adopting a minimum external rectangle mode to detect the rectangular edge of the liquid crystal display panel to be detected, determining four edge corner points according to the rectangular edge, and acquiring coordinate information of the four edge corner points;
and calculating the inclination angle of the liquid crystal display panel to be detected in the target area according to the coordinate information of the four edge corner points, and rotating the target area according to the inclination angle so as to perform inclination correction.
It should be noted that a corner point can be simply regarded as an intersection of two edges, and a more strict definition is a feature point having two main directions in a neighborhood, that is, a gray scale changes violently in two directions.
The morphological opening operation steps of the invention are as follows: the first step is to carry out morphological corrosion operation on the image; the second step is to perform morphological expansion operation based on the first step. The morphological opening operation is used to smooth the contours of the liquid crystal display panel, eliminating small, prominent images. The morphological closing operation steps are as follows: the first step is to perform morphological dilation operation on the image; and the second step is to perform morphological erosion operation on the basis of the first step of processing, wherein the morphological erosion operation is used for repairing fine fractures in the image and fusing smaller holes in the image. The specific morphological corrosion algorithm flow is as follows: firstly, scanning each pixel in the image by using the structural element, carrying out AND operation on the structural element and the binary image covered by the structural element, judging whether the operation results are all 1, if so, the pixel in the image is 1, and if not, the pixel in the image is 0. The specific morphological dilation algorithm flow is as follows: firstly, scanning each pixel in the image by using the structural element, carrying out OR operation on the structural element and the binary image covered by the structural element, judging whether the operation results are all 0, if so, the pixel in the image is 0, and if not, the pixel in the image is 1.
The Harris angular point function is adopted in the invention, and the aim is to find out the angular point on the edge of the liquid crystal display panel to be detected. Due to the influence of holes inside the image, before the Harris corner detection algorithm is implemented, morphological processing needs to be performed on the image to prevent the detection of the corners inside the image. Firstly, the image is binarized, and then the image is subjected to closing operation processing and opening operation processing so as to eliminate holes in the image and prevent the edge contour of the image from being changed greatly, thereby being beneficial to further corner point detection.
It should be noted that, after the image is processed morphologically, when the Harris corner function is implemented, it is found that there is a white outline surrounding the periphery of the liquid crystal display panel to be tested, the outline is actually a plurality of discontinuous small circular rings which indicate that an image formed by four sides of the liquid crystal display panel has a plurality of discontinuous corner points, however, the discontinuous corner points can not determine specific four edge corner points, the invention finds out the corner points in the image by a Harris corner point function, then adopts a minimum external rectangle to connect the corner points, therefore, the edge of the liquid crystal display panel is detected, the coordinates of the four edge corner points of the edge of the liquid crystal display panel are easily obtained according to the edge, and the inclination angle of the liquid crystal display panel in the target area can be calculated according to the coordinates of the four edge corner points, so that the target area can be rotated and corrected to be in the horizontal and vertical directions.
According to an embodiment of the present invention, the uneven lighting correction processing specifically includes:
modeling a reflection imaging process according to an imaging principle to form an illumination reflection model, wherein the illumination reflection model has an expression as follows:whereinIn order to be the original digital image,as the component of the illumination, there is,is the reflection component of the surface of the liquid crystal display panel to be measured,representing pixel point coordinates;
respectively extracting illumination components by utilizing a Gaussian function under multiple scales, and then carrying out weighted synthesis to obtain final illumination components, wherein the calculation formula of the final illumination components is as follows:whereinWhereinIn order to be the total number of scales,is shown asThe weighting coefficients of the individual scales are,the sign of the dot product operation is represented,the expression of the function of gaussian is given,which represents a normalization constant, is shown,the function of the index is expressed in terms of,is a scale factor, and the scale factors of different scales are different;
expression for the illumination reflection modelIs transformed to obtainWhereinRepresenting a logarithmic function, dividing the original imageAnd final illumination component calculated under multiple scalesSubstitution intoObtaining the reflection component of the surface of the liquid crystal display panel to be measuredThe image is the image of the liquid crystal display panel to be measured after the uneven illumination correction processing.
It should be noted that the illumination reflection model is formed according to the Retinex theory, that is, the original digital image obtained by the image sensor is formed under the combined action of the illumination component and the reflection component, the reflection component represents the inherent property of the liquid crystal display panel to be measured, and the illumination component determines the dynamic range size that the inherent property of the liquid crystal display panel to be measured can represent.
It should be noted that, based on the Retinex theoretical assumption, the illumination component mainly exists in the low-frequency part of the image, and is distributed more uniformly and the transformation is gentle. The multi-scale Gaussian function can effectively compress the dynamic range to estimate the illumination component in the image, so that the illumination component can be obtained by performing convolution operation on the Gaussian function and the original image.
According to the method, the illumination components are extracted and integrated under multiple scales, the original digital image and the illumination components are subjected to differential compensation correction, the uneven illumination is obviously reduced before correction compared with the correction result, and the image details are not influenced.
According to the embodiment of the invention, the method for combining the multiple binary images into the integrated binary image according to the preset combination mode specifically comprises the following steps:
presetting a combined model, wherein the combined model comprises a plurality of combined areas, the plurality of combined areas are respectively in one-to-one correspondence with the plurality of production lines, and the number of the preset combined areas is G1;
and respectively filling a plurality of binary images synchronously obtained from a plurality of production lines into the corresponding combined areas, and obtaining an integrated binary image after the filling is finished.
The method and the device have the advantages that the liquid crystal display panel is synchronously produced by the production lines, namely, each production line can produce the binary image of the liquid crystal display panel within the synchronous time, the binary images of the production lines are integrated through the combined model, so that the integrated binary image is formed, a computer can conveniently perform image analysis processing on the integrated binary image, the detection efficiency is improved, the investment of detection and calculation resources is reduced, and the detection cost is saved.
According to the embodiment of the invention, the integrated binary image is calculated according to a preset defect detection algorithm to obtain the defect points of the integrated binary image, and the method specifically comprises the following steps:
randomly selecting G2 binary images from the plurality of binary images of the integrated binary image as template binary images, wherein G2 is smaller than G1;
respectively copying each template binary image into G1 identical template binary images;
filling G1 identical template binary images of each template binary image into a combined area corresponding to the combined model respectively based on each template binary image to form G2 integrated template binary images respectively;
and respectively carrying out difference analysis processing on the integrated binary image and the G2 integrated template binary images to obtain defect points of the integrated binary image.
It can be understood that G2 binarized images are randomly selected from the plurality of binarized images as template binarized images in a random manner, so that the interference of the defects of the liquid crystal display panels of individual production lines is avoided, the influence of the defects of the liquid crystal display panels of the individual production lines can be ignored by the G2 integrated template binarized images generated randomly, and the inspection accuracy is further improved.
Meanwhile, the invention is based on G2 template binary images to copy, and each template binary image is used to generate an integrated template binary image which is used as a defect detection template for the integrated binary image.
According to the embodiment of the invention, the difference analysis processing is performed on the gray values of the integrated binary image and the G2 integrated template binary images to obtain the defect points of the integrated binary image, and the method specifically comprises the following steps:
subtracting the gray value of the pixel point corresponding to the first integrated template binary image from the gray value of the first pixel point in the integrated binary image to obtain a first gray difference of the first pixel point;
calculating the absolute value of the first gray difference, judging whether the absolute value of the first gray difference is greater than a first threshold value, and if so, determining a first pixel point of the integrated binary image as a primary defect suspicious point;
respectively carrying out gray difference calculation on the gray value of a first pixel point in the integrated binary image and the gray value of a pixel point corresponding to the residual integrated template binary image, comparing the absolute value of the obtained gray difference with a first threshold value, and determining whether the first pixel point can be identified as a defect suspicious point or not according to the comparison result;
counting the total times of the first pixel points in the integrated binary image which are determined as suspected defect points;
judging whether the total times is greater than a second threshold value or not, and if so, marking a first pixel point in the integrated binary image as a defect point;
and respectively carrying out difference ratio analysis processing on the remaining pixel points of the integrated binary image and the gray values of the corresponding pixel points of the G2 integrated template binary images to obtain all defect points in the integrated binary image.
It can be understood that the integrated binary image and the G2 integrated template binary images include pixel points that are in one-to-one correspondence, and specifically, in the gray scale difference calculation, the calculation is performed based on the pixel points at the same position. The method comprises the steps that a certain pixel point of an integrated binary image is compared with pixel points at the same positions of G2 integrated template binary images for G2 times respectively, the total times that the pixel point is determined to be a suspected defect point is counted, if the number of times is larger than a second threshold value, the gray value difference of the two images at the same pixel point is larger, at least one of the two images at the pixel point is a defect point, the probability that the defect occurs in a product is usually very small, and if the gray value difference of the integrated binary image and the gray value difference of the G2 integrated template binary images at the same pixel point are very large, the pixel point of the integrated binary image can be determined to be a defect point.
According to a specific embodiment of the present invention, after obtaining all the defective points in the integrated binarized image, the method further comprises:
selecting a plurality of binary images without defect point marks from the integrated binary images as verification binary images, and presetting G3 verification binary images;
respectively copying each verification binary image into G3 identical verification binary images;
based on each check binary image, respectively filling G3 check binary images into a combined area corresponding to the combined model to respectively form G3 integrated check binary images;
performing difference calculation on the gray value of a certain defect point in the integrated binary image and the gray values of the corresponding pixel points of the G3 integrated check binary images one by one to obtain G3 difference values;
and judging whether the absolute value of the difference value exceeding the preset proportion is larger than a first threshold value or not according to the G3 difference values, finishing the verification of the defect point if the absolute value of the difference value exceeding the preset proportion is larger than the first threshold value, judging the defect point to be an abnormal defect point if the absolute value of the difference value does not exceed the preset proportion, and handing the abnormal defect point to a detector for defect detection.
It is understood that the preset ratio is preferably 1/2, 2/3, but is not limited thereto. The invention further screens the binarized images without defect point marks through the integrated binarized images marked with defect points, and checks the defect detection results of the integrated binarized images by the binarized images without defect point marks, thereby further improving the precision of defect detection.
According to the embodiment of the invention, based on the defect points of the integrated binary image and the binding relationship between the plurality of binary images and the serial numbers of the corresponding liquid crystal display panels to be detected, the defect detection result of the corresponding liquid crystal display panel to be detected is determined, and the method specifically comprises the following steps:
splitting the integrated binary image into binary images marked by a plurality of defect points according to a plurality of combined areas;
matching the binary images of the plurality of defect point marks with the liquid crystal display panel to be tested corresponding to the serial number one by combining the binding relationship between the binary images of the plurality of defect point marks and the serial number of the liquid crystal display panel to be tested corresponding to the serial number;
and judging whether the marked defect points exist in advance based on the binary image marked by each defect point, if not, judging that the corresponding liquid crystal display panel to be detected is a non-defective product, if so, evaluating the marked defect points according to a preset evaluation mode, and judging whether the corresponding liquid crystal display panel to be detected is a qualified product according to the evaluation result.
According to the embodiment of the invention, the marked defect points are evaluated according to a preset evaluation mode, and whether the corresponding liquid crystal display panel to be tested is a qualified product or not is judged according to the evaluation result, which specifically comprises the following steps:
dividing the liquid crystal display panel to be tested into e areas, and presetting the influence weight of the defect points of different areas on the product qualityWherein;
Counting the number of the defective points of the binary image marked by a defective point and falling into e areas as;
Counting the number of defective points in each regionRespectively corresponding influence weightMultiplying to obtain the quality influence factor of each region;
Accumulating the quality influence factors of the regionsObtaining a global quality impact factor of;
Determining a global quality impact factor ofAnd whether the third threshold value is exceeded or not, if yes, judging that the corresponding liquid crystal display panel to be detected is a qualified product, and if not, judging that the corresponding liquid crystal display panel to be detected is an unqualified product.
The method and the device can analyze the influence weight of each region on the product quality and combine the number of the defect points of each region to calculate and obtain the comprehensive quality evaluation result of the liquid crystal display panel to be detected, thereby realizing the purpose of automatic detection of the liquid crystal display panel to be detected.
According to the specific embodiment of the present invention, the calculating process of the integrated binary image according to a preset defect detection algorithm specifically includes:
presetting a plurality of binary images to be arranged in an array shape, and performing criss-cross segmentation on the integrated binary images according to a preset period size Z, H to form M image sets, wherein Z is a transverse segmentation size, H is a longitudinal segmentation size, and M is more than or equal to 4;
concentrating the M imagesComparing the gray value of pixel point with that of pixel point of each image set and the gray value of the remaining image sets to calculate and obtain the first image setDefect accumulation map of individual image set,,WhereinIs the coordinates of the pixel points in a single image set, and,;is as followsEach image centralizes the pixel pointsThe gray value of (a);is as followsEach image centralizes the pixel pointsThe gray value of (a);segmenting a threshold for a preset defect;,and is and;
obtaining M defect cumulative graphs respectively by comparing gray values of M image sets, and splicing the M defect cumulative graphs to obtain an integrated binary image,WhereinTo integrate the coordinates of pixel points in the binary image, anCan be based onAnd is at presentConverting the position of each image set in the integrated binary image;
and aggregating the defective pixel points at adjacent positions in the integrated binary image, communicating the adjacent defective pixel points to form a defective area, and outputting the number of the defective areas and the position of each defective area to finish defect detection.
The method can effectively improve the defect detection speed by utilizing the characteristic that the integrated binary image has periodicity, segmenting the integrated binary image according to a certain period length to obtain each image set and then comparing the periodic gray values to determine whether the defect exists.
As can be appreciated, the first and second,andthe conversion process specifically comprises the following steps: if it is firstThe image set is the 1 st image set, i.e. the integrated binary imageThe image set at the upper left corner in the image set can be directly assigned with values,. If it is firstThe image set is the 2 nd image set, and the image sets corresponding to the first row and the second column after the segmentation can be assigned with values,. In this way, the conversion of the pixel point coordinates of each image set and the integrated binary image can be carried out.
In the present invention, the image sets are divided into rectangular image sets having the same size after being divided by criss-cross division according to the horizontal division size Z and the vertical division size H. First, theWhen the gray value comparison of pixel points and pixel points is respectively carried out on the image set and the residual image set, the gray value comparison is actually carried out based on the same positions of the two image setsAnd comparing the gray values of the pixel points.
It should be noted that, when image segmentation is performed, in order to ensure detection robustness, the greater the number of segments, the better the contrast effect, and the higher the detection accuracy, but to meet the high-speed detection requirement, the calculation time needs to be reduced, and the number of segments cannot be too large.
According to the specific embodiment of the present invention, the calculating process of the integrated binary image according to a preset defect detection algorithm specifically includes:
presetting a plurality of binary images to be arranged in an array shape, and performing criss-cross segmentation on the integrated binary images according to a preset period size Z, H to form M image sets, wherein Z is a transverse segmentation size, H is a longitudinal segmentation size, and M is more than or equal to 4;
concentrating the M imagesComparing the gray value of pixel point with that of pixel point of each image set and the gray value of the remaining image sets to calculate and obtain the first image setDefect accumulation map of individual image set,,WhereinIs the coordinates of the pixel points in a single image set, and,;is as followsEach image centralizes the pixel pointsThe gray value of (a);is as followsEach image centralizes the pixel pointsThe gray value of (a);segmenting a threshold for a preset defect;,and is and;
calculating defect accumulation value of each image setWherein the firstCumulative value of individual image setsThe calculation formula is as follows:;
taking the accumulated valueMinimum sizeThe image set is used as the selected image set andthe gray values of the mutual pixel points of every two image sets of each image set are differenced and averaged to generate an image set error templateError template for image setThe calculation formula is as follows:in the formulaThe coordinates of the pixel points in the error template of the image set,a grayscale map representing an image set error template;
error template for image setCarrying out Gaussian fuzzy processing to obtain a final image set error templateWhereinFor the coordinates of the pixel points in the final image set error template,a grayscale map representing the final image set error template;
error template based on final image setPerforming error elimination on each defect accumulation graph to generate a defect accumulation graph after error eliminationHere, theDefect accumulation graph for distinguishing before eliminating errorsIn particular, for defect accumulation mapsInIs checked and judgedWhether or not greater thanIf so, confirmAnd the defect point is determined to be true; if not, the method willAnd eliminating the defect point; whereinWeighting coefficients for the error template;
by comparing gray values of M image sets and based on the error template of the final image setEliminating errors of each defect accumulative graph to obtain M defect accumulative graphs after errors are eliminated respectively, and splicing the M defect accumulative graphs after errors are eliminated to obtain an integrated binary imageWhereinTo integrate the coordinates of pixel points in the binary image, anCan be based onAnd is at presentConverting the position of each image set in the integrated binary image;
and aggregating the defective pixel points at adjacent positions in the integrated binary image, communicating the adjacent defective pixel points to form a defective area, and outputting the number of the defective areas and the position of each defective area to finish defect detection.
It should be noted that, after combining a plurality of binarized images, gray value anomalies of a single line or several lines of pixels may occur near the edges of two adjacent binarized images. In this case, if gray-value contrast analysis between image sets is performed, the presence of the abnormality is highly likely to affect the defect detection result. When the abnormal gray difference is large or the defect segmentation threshold t is set to be low for detecting the defect with low gray contrast, the position is judged as a defect point by the algorithm, but actually the defect does not exist really, so that a great amount of error judgment of the edge defect of the binary image combination can be brought. It will be appreciated that in general the defect segmentation threshold t is less thanAccording to the method, firstly, defect points are preliminarily screened through the defect segmentation threshold t, and then the defect points which are mistakenly identified after preliminary screening are eliminated further based on the image set error template, so that the defect mistaken detection points can be effectively eliminated, and the detection gray level resolution is improved. In addition, the implementationExample different error template weighting coefficients may be usedThe error template of the image set eliminates the false detection points, and the weighting coefficient of the error template is matched with the false detection pointsThe false detection point elimination effect is improved, so that the main defects are extracted.
According to an embodiment of the present invention, evaluating the defect point of the mark according to a preset evaluation mode specifically includes:
the defect area of the binary image with a preset certain defect point mark isAnd performing grade evaluation on each defect area, wherein the grade evaluation formula is as follows:wherein, in the step (A),is shown asThe defect level of each of the defective areas,is shown asThe defect point accumulation number of each defective region,is shown asThe defective pixel points covered by each defective area,andweighting factors for rating the number of defect points and the area of the defect area,is shown asThe area of each of the defective regions is,;
determining the qualified condition of the corresponding liquid crystal display panel to be tested according to the grade evaluation result of each defect area, which specifically comprises the following steps: and if the binary image has a defect area exceeding the preset defect level, determining that the corresponding liquid crystal display panel to be detected is unqualified, and if not, determining that the corresponding liquid crystal display panel to be detected is qualified.
It can be understood that if the liquid crystal display panel to be tested has a defect, the liquid crystal display panel to be tested generally exists in the form of a defect region, and does not exist in the form of a single isolated defect pixel point, so that if the liquid crystal display panel to be tested has a defect, the corresponding binarized image also has a defect region, and after the defect region in the binarized image is obtained, the grade of each defect region can be obtained through an evaluation algorithm.
FIG. 2 is a schematic diagram of a defect detection system based on a liquid crystal display panel according to the present invention.
As shown in fig. 2, the second aspect of the present invention further provides a defect detection system based on a liquid crystal display panel, the system comprising:
the light source is used for providing irradiation light for the liquid crystal display panel to be detected positioned at the detection position;
the optical module is used for collecting the reflected light of the liquid crystal display panel to be detected and focusing the reflected light on the image sensor;
the image sensor is used for collecting an optical image focused by the optical module and performing photoelectric conversion and analog-to-digital conversion to form an original digital image;
the preprocessing module is used for acquiring an original digital image from the image sensor, and performing image inclination correction and uneven illumination correction on the original digital image to generate a new digital image;
the computer is used for carrying out image recognition analysis processing on the plurality of new digital images to obtain serial numbers corresponding to the liquid crystal display panel to be detected; simultaneously carrying out binarization processing on the plurality of new digital images to obtain corresponding binarized images, and establishing a binding relationship between the plurality of binarized images and the serial numbers of the corresponding liquid crystal display panels to be tested; the integrated binary image processing device is also used for combining the plurality of binary images according to a preset combination mode to form an integrated binary image, and calculating the integrated binary image according to a preset defect detection algorithm to obtain defect points of the integrated binary image; and finally, determining a defect detection result of the corresponding liquid crystal display panel to be detected based on the defect points of the integrated binary image and the binding relationship between the plurality of binary images and the serial number of the corresponding liquid crystal display panel to be detected.
According to the embodiment of the invention, the method for combining the multiple binary images into the integrated binary image according to the preset combination mode specifically comprises the following steps:
presetting a combined model, wherein the combined model comprises a plurality of combined areas, the plurality of combined areas are respectively in one-to-one correspondence with the plurality of production lines, and the number of the preset combined areas is G1;
and respectively filling a plurality of binary images synchronously obtained from a plurality of production lines into the corresponding combined areas, and obtaining an integrated binary image after the filling is finished.
According to the embodiment of the invention, the integrated binary image is calculated according to a preset defect detection algorithm to obtain the defect points of the integrated binary image, and the method specifically comprises the following steps:
randomly selecting G2 binary images from the plurality of binary images of the integrated binary image as template binary images, wherein G2 is smaller than G1;
respectively copying each template binary image into G1 identical template binary images;
filling G1 identical template binary images of each template binary image into a combined area corresponding to the combined model respectively based on each template binary image to form G2 integrated template binary images respectively;
and respectively carrying out difference analysis processing on the integrated binary image and the G2 integrated template binary images to obtain defect points of the integrated binary image.
According to the embodiment of the invention, the difference analysis processing is performed on the gray values of the integrated binary image and the G2 integrated template binary images to obtain the defect points of the integrated binary image, and the method specifically comprises the following steps:
subtracting the gray value of the pixel point corresponding to the first integrated template binary image from the gray value of the first pixel point in the integrated binary image to obtain a first gray difference of the first pixel point;
calculating the absolute value of the first gray difference, judging whether the absolute value of the first gray difference is greater than a first threshold value, and if so, determining a first pixel point of the integrated binary image as a primary defect suspicious point;
respectively carrying out gray difference calculation on the gray value of a first pixel point in the integrated binary image and the gray value of a pixel point corresponding to the residual integrated template binary image, comparing the absolute value of the obtained gray difference with a first threshold value, and determining whether the first pixel point can be identified as a defect suspicious point or not according to the comparison result;
counting the total times of the first pixel points in the integrated binary image which are determined as suspected defect points;
judging whether the total times is greater than a second threshold value or not, and if so, marking a first pixel point in the integrated binary image as a defect point;
and respectively carrying out difference ratio analysis processing on the remaining pixel points of the integrated binary image and the gray values of the corresponding pixel points of the G2 integrated template binary images to obtain all defect points in the integrated binary image.
The invention provides a defect detection method and system based on a liquid crystal display panel, which can realize intelligent detection of the liquid crystal display panel and effectively improve the detection efficiency and accuracy.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (4)
1. A defect detection method based on a liquid crystal display panel is characterized by comprising the following steps:
respectively positioning the liquid crystal display panels to be detected, which are synchronously produced by a plurality of production lines, at detection positions on corresponding production lines, starting a light source and irradiating the liquid crystal display panels to be detected;
collecting reflected light of a liquid crystal display panel to be detected through an optical module, focusing the reflected light on an image sensor, and carrying out image acquisition through the image sensor and carrying out photoelectric conversion and analog-to-digital conversion to form an original digital image;
the method comprises the steps that a preprocessing module acquires original digital images corresponding to liquid crystal display panels to be detected from image sensors of a plurality of production lines, and performs image inclination correction and uneven illumination correction on each original digital image to generate new digital images;
respectively carrying out image recognition analysis processing on the plurality of new digital images by the computer to obtain serial numbers corresponding to the liquid crystal display panel to be detected;
carrying out binarization processing on the plurality of new digital images by a computer to obtain corresponding binarized images, and establishing a binding relationship between the plurality of binarized images and the serial numbers of the corresponding liquid crystal display panels to be tested;
combining a plurality of binary images according to a preset combination mode to form an integrated binary image, and calculating the integrated binary image according to a preset defect detection algorithm to obtain defect points of the integrated binary image, wherein the combining of the plurality of binary images according to the preset combination mode to form the integrated binary image specifically comprises the following steps:
presetting a combined model, wherein the combined model comprises a plurality of combined areas, the plurality of combined areas are respectively in one-to-one correspondence with the plurality of production lines, and the number of the preset combined areas is G1;
respectively filling a plurality of binary images synchronously obtained from a plurality of production lines into corresponding combined areas, and obtaining an integrated binary image after filling is finished;
calculating the integrated binary image according to a preset defect detection algorithm to obtain defect points of the integrated binary image, wherein the method specifically comprises the following steps:
randomly selecting G2 binary images from the plurality of binary images of the integrated binary image as template binary images, wherein G2 is smaller than G1;
respectively copying each template binary image into G1 identical template binary images;
filling G1 identical template binary images of each template binary image into a combined area corresponding to the combined model respectively based on each template binary image to form G2 integrated template binary images respectively;
and respectively carrying out difference analysis processing on the gray values of the integrated binary image and the G2 integrated template binary images to obtain defect points of the integrated binary image, wherein the method specifically comprises the following steps:
subtracting the gray value of the pixel point corresponding to the first integrated template binary image from the gray value of the first pixel point in the integrated binary image to obtain a first gray difference of the first pixel point;
calculating the absolute value of the first gray difference, judging whether the absolute value of the first gray difference is greater than a first threshold value, and if so, determining a first pixel point of the integrated binary image as a primary defect suspicious point;
respectively carrying out gray difference calculation on the gray value of a first pixel point in the integrated binary image and the gray value of a pixel point corresponding to the residual integrated template binary image, comparing the absolute value of the obtained gray difference with a first threshold value, and determining whether the first pixel point can be identified as a defect suspicious point or not according to the comparison result;
counting the total times of the first pixel points in the integrated binary image which are determined as suspected defect points;
judging whether the total times is greater than a second threshold value or not, and if so, marking a first pixel point in the integrated binary image as a defect point;
respectively carrying out difference ratio analysis processing on the remaining pixel points of the integrated binary image and the gray values of the corresponding pixel points of the G2 integrated template binary images to obtain all defect points in the integrated binary image;
and determining a defect detection result corresponding to the liquid crystal display panel to be detected based on the defect points of the integrated binary image and the binding relationship between the plurality of binary images and the serial number of the corresponding liquid crystal display panel to be detected.
2. The method for detecting the defect of the liquid crystal display panel based on the claim 1 is characterized in that the defect detection result of the corresponding liquid crystal display panel to be detected is determined based on the defect points of the integrated binary image and the binding relationship between the plurality of binary images and the serial numbers of the corresponding liquid crystal display panels to be detected, and specifically comprises the following steps:
splitting the integrated binary image into binary images marked by a plurality of defect points according to a plurality of combined areas;
matching the binary images of the plurality of defect point marks with the liquid crystal display panel to be tested corresponding to the serial number one by combining the binding relationship between the binary images of the plurality of defect point marks and the serial number of the liquid crystal display panel to be tested corresponding to the serial number;
and judging whether the marked defect points exist in advance based on the binary image marked by each defect point, if not, judging that the corresponding liquid crystal display panel to be detected is a non-defective product, if so, evaluating the marked defect points according to a preset evaluation mode, and judging whether the corresponding liquid crystal display panel to be detected is a qualified product according to the evaluation result.
3. The method as claimed in claim 2, wherein the step of evaluating the marked defect points according to a preset evaluation method and determining whether the corresponding liquid crystal display panel to be tested is a qualified product according to the evaluation result comprises:
dividing the liquid crystal display panel to be tested into e areas, and presetting the influence weight of the defect points of different areas on the product qualityWherein;
Counting the number of the defective points of the binary image marked by a defective point and falling into e areas as;
Counting the number of defective points in each regionRespectively correspond toInfluence weight ofMultiplying to obtain the quality influence factor of each region;
Accumulating the quality influence factors of the regionsObtaining a global quality impact factor of;
Determining a global quality impact factor ofAnd whether the third threshold value is exceeded or not, if yes, judging that the corresponding liquid crystal display panel to be detected is a qualified product, and if not, judging that the corresponding liquid crystal display panel to be detected is an unqualified product.
4. A system for detecting defects based on a liquid crystal display panel, the system comprising: the system comprises a light source, an optical module, an image sensor, a preprocessing module and a computer;
the light source is used for providing irradiation light for the liquid crystal display panel to be detected positioned at the detection position;
the optical module is used for collecting the reflected light of the liquid crystal display panel to be detected and focusing the reflected light on the image sensor;
the image sensor is used for collecting an optical image focused by the optical module and performing photoelectric conversion and analog-to-digital conversion to form an original digital image;
the preprocessing module is used for acquiring an original digital image from the image sensor, and performing image inclination correction and uneven illumination correction on the original digital image to generate a new digital image;
the computer is used for carrying out image recognition analysis processing on the plurality of new digital images to obtain serial numbers corresponding to the liquid crystal display panel to be detected; simultaneously carrying out binarization processing on the plurality of new digital images to obtain corresponding binarized images, and establishing a binding relationship between the plurality of binarized images and the serial numbers of the corresponding liquid crystal display panels to be tested; the integrated binary image processing device is also used for combining the plurality of binary images according to a preset combination mode to form an integrated binary image, and calculating the integrated binary image according to a preset defect detection algorithm to obtain defect points of the integrated binary image; finally, determining a defect detection result of the corresponding liquid crystal display panel to be detected based on the defect points of the integrated binary images and the binding relationship between the plurality of binary images and the serial numbers of the corresponding liquid crystal display panels to be detected;
the method comprises the following steps of combining a plurality of binary images according to a preset combination mode to form an integrated binary image, and specifically comprises the following steps:
presetting a combined model, wherein the combined model comprises a plurality of combined areas, the plurality of combined areas are respectively in one-to-one correspondence with the plurality of production lines, and the number of the preset combined areas is G1;
respectively filling a plurality of binary images synchronously obtained from a plurality of production lines into corresponding combined areas, and obtaining an integrated binary image after filling is finished;
calculating the integrated binary image according to a preset defect detection algorithm to obtain defect points of the integrated binary image, wherein the method specifically comprises the following steps:
randomly selecting G2 binary images from the plurality of binary images of the integrated binary image as template binary images, wherein G2 is smaller than G1;
respectively copying each template binary image into G1 identical template binary images;
filling G1 identical template binary images of each template binary image into a combined area corresponding to the combined model respectively based on each template binary image to form G2 integrated template binary images respectively;
and respectively carrying out difference analysis processing on the gray values of the integrated binary image and the G2 integrated template binary images to obtain defect points of the integrated binary image, wherein the method specifically comprises the following steps:
subtracting the gray value of the pixel point corresponding to the first integrated template binary image from the gray value of the first pixel point in the integrated binary image to obtain a first gray difference of the first pixel point;
calculating the absolute value of the first gray difference, judging whether the absolute value of the first gray difference is greater than a first threshold value, and if so, determining a first pixel point of the integrated binary image as a primary defect suspicious point;
respectively carrying out gray difference calculation on the gray value of a first pixel point in the integrated binary image and the gray value of a pixel point corresponding to the residual integrated template binary image, comparing the absolute value of the obtained gray difference with a first threshold value, and determining whether the first pixel point can be identified as a defect suspicious point or not according to the comparison result;
counting the total times of the first pixel points in the integrated binary image which are determined as suspected defect points;
judging whether the total times is greater than a second threshold value or not, and if so, marking a first pixel point in the integrated binary image as a defect point;
and respectively carrying out difference ratio analysis processing on the remaining pixel points of the integrated binary image and the gray values of the corresponding pixel points of the G2 integrated template binary images to obtain all defect points in the integrated binary image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111146109.2A CN113570605B (en) | 2021-09-28 | 2021-09-28 | Defect detection method and system based on liquid crystal display panel |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111146109.2A CN113570605B (en) | 2021-09-28 | 2021-09-28 | Defect detection method and system based on liquid crystal display panel |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113570605A CN113570605A (en) | 2021-10-29 |
CN113570605B true CN113570605B (en) | 2021-12-31 |
Family
ID=78174904
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111146109.2A Active CN113570605B (en) | 2021-09-28 | 2021-09-28 | Defect detection method and system based on liquid crystal display panel |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113570605B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113674273B (en) * | 2021-09-16 | 2021-12-31 | 深圳市光明顶照明科技有限公司 | Optical detection method and system based on product defects and readable storage medium |
CN114187266B (en) * | 2021-12-13 | 2022-10-04 | 江苏鑫丰源机电有限公司 | Tooth surface gluing degree evaluation method based on artificial intelligence |
CN114211319B (en) * | 2022-02-17 | 2022-04-29 | 东莞飞元科技有限公司 | Control method and system for special grinding machine for multi-station cutter and storage medium |
CN114549448B (en) * | 2022-02-17 | 2023-08-11 | 中国空气动力研究与发展中心超高速空气动力研究所 | Complex multi-type defect detection evaluation method based on infrared thermal imaging data analysis |
CN115079045B (en) * | 2022-06-10 | 2023-05-02 | 郴州恒维电子股份有限公司 | Automatic detection short circuit breaking device for previous procedure image |
CN115061294A (en) * | 2022-06-28 | 2022-09-16 | Tcl华星光电技术有限公司 | Method and system for repairing defects of liquid crystal display panel and storage medium |
CN115082482B (en) * | 2022-08-23 | 2022-11-22 | 山东优奭趸泵业科技有限公司 | Metal surface defect detection method |
CN115951511B (en) * | 2023-03-03 | 2023-06-20 | 徐州荣欣网络科技有限公司 | Liquid crystal display manufacturing test analysis system |
CN116468726B (en) * | 2023-06-13 | 2023-10-03 | 厦门福信光电集成有限公司 | Online foreign matter line detection method and system |
CN117036357B (en) * | 2023-10-10 | 2023-12-22 | 无锡市方顺型钢科技有限公司 | Profile steel surface defect detection method based on visual characteristics |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
CN108460757A (en) * | 2018-02-11 | 2018-08-28 | 深圳市鑫信腾科技有限公司 | A kind of mobile phone TFT-LCD screens Mura defects online automatic detection method |
CN108760767A (en) * | 2018-05-31 | 2018-11-06 | 电子科技大学 | Large-size LCD Screen defect inspection method based on machine vision |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107248151B (en) * | 2017-04-20 | 2020-12-22 | 深圳市智能机器人研究院 | Intelligent liquid crystal display detection method and system based on machine vision |
CN107678192B (en) * | 2017-07-16 | 2020-09-25 | 中科院成都信息技术股份有限公司 | Mura defect detection method based on machine vision |
CN107845087B (en) * | 2017-10-09 | 2020-07-03 | 深圳市华星光电半导体显示技术有限公司 | Method and system for detecting uneven brightness defect of liquid crystal panel |
-
2021
- 2021-09-28 CN CN202111146109.2A patent/CN113570605B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104360501A (en) * | 2014-10-15 | 2015-02-18 | 西安交通大学 | Visual detection method and device for defects of liquid crystal display screen |
CN108460757A (en) * | 2018-02-11 | 2018-08-28 | 深圳市鑫信腾科技有限公司 | A kind of mobile phone TFT-LCD screens Mura defects online automatic detection method |
CN108760767A (en) * | 2018-05-31 | 2018-11-06 | 电子科技大学 | Large-size LCD Screen defect inspection method based on machine vision |
Also Published As
Publication number | Publication date |
---|---|
CN113570605A (en) | 2021-10-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113570605B (en) | Defect detection method and system based on liquid crystal display panel | |
CN111815630B (en) | Defect detection method and device for LCD screen | |
CN107543828B (en) | Workpiece surface defect detection method and system | |
CN105894036B (en) | A kind of characteristics of image template matching method applied to mobile phone screen defects detection | |
CN112651968B (en) | Wood board deformation and pit detection method based on depth information | |
CN113608378B (en) | Full-automatic defect detection method and system based on LCD (liquid crystal display) process | |
CN110675376A (en) | PCB defect detection method based on template matching | |
CN108520514B (en) | Consistency detection method for electronic elements of printed circuit board based on computer vision | |
CN116559183B (en) | Method and system for improving defect judging efficiency | |
CN116228780B (en) | Silicon wafer defect detection method and system based on computer vision | |
CN117132844B (en) | Classifying method for cracks and scratches of photovoltaic panel based on image processing | |
CN113538603B (en) | Optical detection method and system based on array product and readable storage medium | |
CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
CN116152242B (en) | Visual detection system of natural leather defect for basketball | |
CN112014407A (en) | Method for detecting surface defects of integrated circuit wafer | |
CN110426395B (en) | Method and device for detecting surface of solar EL battery silicon wafer | |
CN114719749A (en) | Metal surface crack detection and real size measurement method and system based on machine vision | |
CN117830415B (en) | Processing and positioning method for vehicle-mounted large-size photoelectric glass cover plate | |
CN115457541A (en) | Jewelry quality identification method and device based on image recognition | |
CN117557565B (en) | Detection method and device for lithium battery pole piece | |
CN114998333A (en) | Computer vision detection method and system for light source characteristics | |
CN108805854B (en) | Method for rapidly counting tablets and detecting completeness of tablets in complex environment | |
CN114612418A (en) | Method, device and system for detecting surface defects of mouse shell and electronic equipment | |
CN116908185A (en) | Method and device for detecting appearance defects of article, electronic equipment and storage medium | |
CN110874837B (en) | Defect automatic detection method based on local feature distribution |
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 |