CN113628212B - Defective polarizer identification method, electronic device, and storage medium - Google Patents
Defective polarizer identification method, electronic device, and storage medium Download PDFInfo
- Publication number
- CN113628212B CN113628212B CN202111186165.9A CN202111186165A CN113628212B CN 113628212 B CN113628212 B CN 113628212B CN 202111186165 A CN202111186165 A CN 202111186165A CN 113628212 B CN113628212 B CN 113628212B
- Authority
- CN
- China
- Prior art keywords
- area
- defect
- image
- block area
- transmission 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000002950 deficient Effects 0.000 title claims abstract description 35
- 238000003860 storage Methods 0.000 title claims abstract description 24
- 230000007547 defect Effects 0.000 claims abstract description 171
- 230000005540 biological transmission Effects 0.000 claims abstract description 91
- 230000001681 protective effect Effects 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000003709 image segmentation Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 16
- 238000007689 inspection Methods 0.000 abstract description 2
- 230000003287 optical effect Effects 0.000 description 10
- 239000011521 glass Substances 0.000 description 6
- 239000000758 substrate Substances 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 230000002085 persistent effect Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000001788 irregular Effects 0.000 description 2
- 239000010410 layer Substances 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 239000002355 dual-layer Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to a method for identifying a defective polarizer, an electronic device and a storage medium. The method comprises the following steps: acquiring a transmission image and a reflection image of a screen to be detected; the transmission image is formed by the area to be detected after light rays are transmitted from the screen to be detected; the reflected image is an image of the area to be detected after the light is reflected on the surface of the screen to be detected; carrying out binarization processing on the transmission image and the reflection image to respectively obtain a first defect area and a second defect area; calculating the center distance difference of the first defect area and the second defect area according to the coordinates of the center points of the first defect area and the second defect area; and judging the defect types corresponding to the first defect area and the second defect area according to the central distance difference. According to the method and the device, automatic detection and distinguishing of the polarizer bubbles and the protective film bubbles can be completed in an image recognition mode during screen quality inspection.
Description
Technical Field
The application relates to the technical field of machine vision detection, in particular to a bad polarizer identification method, electronic equipment and a storage medium.
Background
In the liquid crystal display module, the polaroids are attached to two sides of the glass substrate, and a backlight plate, a polarizer, liquid crystal, an optical filter and an analyzer are arranged in sequence in each liquid crystal display module, wherein the polarizer and the analyzer are both polaroids. After the liquid crystal and the optical filter are mounted on the glass substrate, the polarizer and the glass substrate need to be attached. In order to prevent bubbles from occurring between the polaroid and the screen, defoaming treatment needs to be carried out after the polaroid is attached, then quality detection of the polaroid bubbles is carried out, and the screen with the polaroid bubbles still existing after defoaming is prevented from flowing into a subsequent production line.
Meanwhile, after the lamination is completed, a protective film needs to be attached to the outer layer of the polaroid of the screen to protect the screen from being scratched.
In the actual production process, when the screen flows to the quality detection process, the protective film is already attached on the outer layer of the screen, so that the screen sequentially comprises the following components: protective film, polaroid and glass substrate. If the protective film is not well adhered, bubbles of the protective film exist between the protective film and the polaroid interlayer; if the polarizer is poorly adhered, polarizer bubbles may be present between the polarizer and the glass substrate.
Because the existing protective film attaching process has defects, protective film bubbles similar to the polarizer bubbles exist between the polarizer and the protective film. The polarizer bubbles (namely, the bubbles between the polarizer and the glass substrate) can cause adverse effects on the polarization performance of the polarizer, the protective film bubbles (namely, the bubbles between the protective film and the polarizer) are external bubbles, the protective film can be stripped in the subsequent production process, the display performance of a screen is not affected, and therefore the protective film bubbles do not need to be processed.
Therefore, in order to ensure the performance of the polarizer, the polarizer bubbles in the screen need to be detected. In the prior art, manual quality inspection needs to be arranged, the bubbles of the protective film and the bubbles of the polaroid are distinguished, and the efficiency is low.
Therefore, in order to improve the automatic detection level of polarizer bubbles in the screen and distinguish the polarizer bubbles from the protection film bubbles more quickly and accurately, it is necessary to provide an image detection method capable of distinguishing the polarizer bubbles from the protection film bubbles.
Disclosure of Invention
In the shooting process of the screen, if a shooting object is a polaroid bubble, in the transmission image and the reflection image, the refraction optical path of the light passing through the inside of the screen is the same, and the polaroid bubble is approximately superposed on the transmission image and the reflection image;
if the object to be photographed is a protective film bubble, the refractive optical paths through which light passes inside the screen are different between the transmission image and the reflection image, and the position of the protective film bubble on the transmission image and the reflection image is deviated.
Therefore, according to the principle that the positions of the polarizer bubbles on the transmission image and the reflection image are approximately overlapped, the image recognition detection of the polarizer bubbles of the screen can be realized.
The application provides a bad polarizer identification method in a first aspect, which comprises the following steps:
acquiring a transmission image and a reflection image of a screen to be detected; the transmission image is formed by the area to be detected after light rays are transmitted from the screen to be detected; the reflected image is an image of the area to be detected after the light is reflected on the surface of the screen to be detected;
carrying out binarization processing on the transmission image and the reflection image to respectively obtain a first defect area and a second defect area;
calculating the center distance difference of the first defect area and the second defect area according to the coordinates of the center points of the first defect area and the second defect area;
and judging the defect types corresponding to the first defect area and the second defect area according to the central distance difference.
In an embodiment, the determining the defect types corresponding to the first defective area and the second defective area according to the center distance difference includes:
if the difference between the central distances of the first defect area and the second defect area is smaller than or equal to a deviation threshold, determining that the defect types corresponding to the first defect area and the second defect area are polarizer bubbles;
the determining the defect types corresponding to the first defect area and the second defect area according to the center distance difference further includes:
and if the difference between the central distances of the first defective area and the second defective area is larger than the deviation threshold, determining that the defect types corresponding to the first defective area and the second defective area are protective film bubbles.
In one embodiment, the binarizing the transmission image and the reflection image to obtain a first defect area and a second defect area, respectively, includes:
carrying out image segmentation processing on the transmission image according to the gray value, and marking the transmission image as a first bright block area if the gray value is greater than a first preset threshold value; if the gray value is smaller than a second preset threshold value, marking the gray value as a first dark block area;
combining the adjacent first bright block area and the first dark block area to obtain the first defect area;
performing image segmentation processing on the reflection image according to the gray value, and marking the reflection image as a second bright block area if the gray value is greater than a third preset threshold value; if the gray value is smaller than a fourth preset threshold value, marking the gray value as a second dark block area;
and combining the second bright block area and the second dark block area which are adjacent to each other to obtain the second defect area.
In one embodiment of the method of the present invention,
the merging the adjacent first bright block area and the first dark block area comprises:
acquiring a center point coordinate of the first bright block area and a center point coordinate of at least one first dark block area adjacent to the first bright block area;
respectively calculating the distance difference of the first image to be merged of the center point coordinate of the first bright block area and the center point coordinate of the first dark block area, and selecting the first dark block area with the minimum distance difference of the first image to be merged to merge with the first bright block area;
the merging of the adjacent second bright block area and the second dark block area includes:
acquiring the center point coordinate of the second bright block area and the center point coordinate of at least one second dark block area adjacent to the second bright block area;
and respectively calculating the distance difference of the second image to be merged of the center point coordinate of the second bright block area and the center point coordinate of the second dark block area, and selecting the second dark block area with the minimum value of the distance difference of the second image to be merged to merge with the second bright block area.
In one embodiment, the calculating a difference in center distance between the first defective region and the second defective region according to coordinates of center points of the first defective region and the second defective region includes:
converting the pixel coordinates of the center points of the first and second defect areas into physical coordinates to respectively obtain the physical coordinates of the first center point of the first defect areaAnd physical coordinates of a second center point of the second defect region;
Calculating the center distance difference according to the physical coordinates of the first center point, the physical coordinates of the second center point and a center distance formula; the center distance is expressed by。
In one embodiment, after the obtaining the transmission image and the reflection image of the screen to be detected, the method further includes:
preprocessing the transmission image and the reflection image; the pretreatment comprises the following steps:
obtaining the transmission image, performing Gaussian filtering noise reduction on the transmission image, and removing background textures of the transmission image to obtain the transmission image after pretreatment;
and acquiring the reflection image, and carrying out mean value filtering and noise reduction on the reflection image to obtain the preprocessed reflection image.
In one embodiment, the removing the background texture of the transmission image comprises:
performing discrete Fourier transform on the transmission image to obtain a spectrogram;
acquiring the frequency distribution of the spectrogram;
processing the spectrogram through an image binarization algorithm and selecting texture frequency to obtain the texture frequency;
reserving the central frequency of the spectrogram, and removing the texture frequency to obtain the spectrogram of the texture-removed frequency;
and carrying out inverse Fourier transform on the frequency spectrogram of the de-textured frequency to obtain the preprocessed transmission image.
In one embodiment, before the binarizing processing on the transmission image and the reflection image, the method includes:
acquiring at least M reflection images, and carrying out image block division on an ink area of the reflection images to obtain a reflection image training set, wherein M is an integer greater than two;
inputting the reflection image training set into a convolutional neural network for training to obtain a screen defect recognition neural network; the defect type corresponding to the classifier of the screen defect recognition neural network comprises the following steps: polarizer bubbles and protective film bubbles; the characteristic diagram extracted by the screen defect recognition neural network is as follows:(ii) a The above-mentionedFor the input said reflection image training set, saidFor the output characteristic diagram, connectionsAndhas a convolution kernel ofSaidFor the bias term in each of the filters,in order to be a two-dimensional discrete convolution operator,is a non-linear activation function.
A second aspect of the present application provides an electronic device, comprising: a processor; and a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform any of the methods of identifying an undesirable polarizer of the first aspect of the present application.
A third aspect of the present application provides a non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform any one of the bad polarizer identification methods described in the first aspect of the present application.
The technical scheme provided by the application can comprise the following beneficial effects:
the method comprises the steps of obtaining a transmission image and a reflection image of a screen to be detected, and extracting the areas to be detected on the transmission image and the reflection image respectively through an image segmentation algorithm to obtain a first defect area and a second defect area; calculating the center distance difference between the first defect area and the second defect area according to the coordinates of the center points of the first defect area and the second defect area; since the polarizer bubbles and the protective film bubbles cause different refraction optical paths of light rays passing through the inside of the screen in the transmission image and the reflection image, deviation occurs in the positions of the protective film bubbles on the transmission image and the reflection image; the positions of the polaroid bubbles on the transmission image and the reflection image are approximately the same, so that the types of the bubbles on the screen to be detected can be distinguished according to the central distance difference, and specifically, if the central distance difference accords with the characteristics of the polaroid bubbles, the defect type of the area to be detected can be judged to be the polaroid bubbles, and the polaroid is unqualified; otherwise, judging that the defect type of the region to be detected is the protective film bubble, and the polaroid is qualified. Compared with manual detection, the method and the device have the advantages that the transmission image and the reflection image of the screen to be detected are obtained, the defect type is judged according to the center distance difference between the first defect area of the transmission image and the second defect area of the reflection image, image identification and detection of the type of the bubbles on the screen to be detected are achieved, and the screen detection efficiency and accuracy are improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application, as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
FIG. 1 is a schematic flow chart illustrating a method for identifying a defective polarizer according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a shooting mode of the transmission image according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a shooting mode of the reflection image according to an embodiment of the present disclosure;
FIG. 4 is a flowchart illustrating a method for feature extraction of a potential defect according to an embodiment of the present application;
FIG. 5-1 is the transmission image shown in the embodiments of the present application;
FIG. 5-2 is the transmission image after the pre-processing shown in FIG. 5-1;
FIG. 5-3 is a first light patch area image of the transmission image shown in FIG. 5-1;
FIG. 5-4 is a first dark block area image of the transmission image shown in FIG. 5-1;
FIG. 5-5 is a first defect area image of the transmission image shown in FIG. 5-1;
FIG. 6-1 is the reflection image shown in an embodiment of the present application;
FIG. 6-2 is a second light block area image of the reflectance image shown in FIG. 6-1;
FIG. 6-3 is a second dark block area image of the reflectance image shown in FIG. 6-1;
FIG. 6-4 is a second defect area image of the reflectance image shown in FIG. 6-1;
FIG. 7 is a schematic flow chart of a neural network training for screen defect recognition according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Detailed Description
Preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Example one
The embodiment of the application provides a method for identifying a poor polarizer, as shown in fig. 1, comprising the following steps:
10. acquiring a transmission image and a reflection image of a screen to be detected;
further, the transmission image is an image of the area to be detected after the light is transmitted from the screen to be detected; the reflected image is an image of the area to be detected after the light is reflected on the surface of the screen to be detected;
illustratively, the transmission image and the reflection image are obtained by taking a bright field photograph of the screen to be detected with an industrial camera under the irradiation of a light source.
Specifically, as shown in fig. 2, the transmission image is captured in the following manner: the industrial camera is placed on one side face of the screen to be detected, and the light source is placed on the other opposite side face of the screen to be detected. The propagation path of the light is: and the line scanning light source reaches the screen to be detected and then refracts the screen to the industrial camera.
Specifically, as shown in fig. 3, the reflected image is captured in the following manner: the industrial camera and the light source are arranged on the same side face of the screen to be detected, and the propagation path of light is that the line scanning light source is reflected to the screen to be detected and then reflected to the industrial camera.
20. Carrying out binarization processing on the transmission image and the reflection image to respectively obtain a first defect area and a second defect area;
specifically, the transmission image and the reflection image which are compared are images obtained by acquiring the same to-be-detected area in the to-be-detected screen in a transmission image shooting mode and a reflection image shooting mode respectively.
30. Calculating the center distance difference of the first defect area and the second defect area according to the coordinates of the center points of the first defect area and the second defect area;
specifically, the central point is a plane geometric center of the region to be measured.
Further, the calculating a center distance difference between the first defective area and the second defective area according to the coordinates of the center points of the first defective area and the second defective area specifically includes:
converting the pixel coordinates of the center points of the first and second defect areas into physical coordinates to respectively obtain the physical coordinates of the first center point of the first defect areaAnd physical coordinates of a second center point of the second defect region。
It can be understood that the center point pixel coordinates of the first defect region and the second defect region are obtained by an image pixel center locating algorithm. And then, obtaining the physical coordinate of the central point according to the pixel coordinate of the central point. And calculating the center distance difference according to the physical coordinates of the first center point, the physical coordinates of the second center point and a center distance formula.
It should be noted that, the reference coordinate systems of the transmission image and the reflection image are consistent, and the physical coordinate of the central point can display the position of the first defect region or the second defect region on the screen to be detected.
40. And judging the defect types corresponding to the first defect area and the second defect area according to the central distance difference.
Further, if the difference between the center distances of the first defect area and the second defect area is smaller than or equal to a deviation threshold, determining that the defect types corresponding to the first defect area and the second defect area are polarizer bubbles.
Further, if the difference between the center distances of the first defective area and the second defective area is greater than the deviation threshold, it is determined that the defect type corresponding to the first defective area and the second defective area is a protective film bubble.
Because the deviation of the central points of the polarizer bubble on the transmission image and the reflection image is small, the transmission image and the reflection image of the same region to be detected are subjected to image segmentation, the first defect region and the second defect region are extracted, the central point positions of the potential defects of the two images on the same region to be detected are respectively determined, the central distance difference of the potential defects on the two comparison images is calculated, and whether the potential defects are the polarizer bubble or not can be judged according to the numerical value of the central distance difference.
According to the method and the device, the transmission image and the reflection image of the screen to be detected are obtained, the area to be detected on the transmission image and the area to be detected on the reflection image are respectively extracted through an image segmentation algorithm, and the first defect area and the second defect area are obtained; calculating the center distance difference between the first defect area and the second defect area according to the coordinates of the center points of the first defect area and the second defect area; because the light rays pass through different refraction optical paths in the screen due to the polarizer bubbles and the protective film bubbles, the positions of the protective film bubbles on the transmission image and the reflection image are deviated; the positions of the polarizer bubbles on the transmission image and the reflection image are approximately the same, so that the types of the bubbles on the screen to be detected can be distinguished according to the central distance difference, specifically, if the central distance difference accords with the characteristics of the polarizer bubbles, the defect type of the region to be detected can be judged to be the polarizer bubbles, and the polarizer is unqualified; otherwise, judging that the defect type of the region to be detected is the protective film bubble, and the polaroid is qualified. Compared with manual detection, the method and the device have the advantages that the transmission image and the reflection image of the screen to be detected are obtained, the type of the defect is judged according to the central distance difference of the defect area on the transmission image and the reflection image, image identification and detection of the type of the bubble on the screen to be detected are achieved, and the screen detection efficiency and accuracy are improved.
Example two
Because the bubbles are irregular patterns, they can cause the bubbles on the reflected and transmitted images to appear as an irregular spread of light and dark blocks in nature. In the prior art, a bright block on the outer contour of a bubble is extracted, and the extracted defect image is internally filled to obtain a complete defect image, and the method can cause the deletion of partial defect areas, so that the geometric center of the defect is not accurately positioned, and whether the defect is a polarizer bubble or not can not be judged according to the coincidence of the geometric center of the defect.
Therefore, in order to completely extract the potential defects on the reflection image and the transmission image, before step 20 in embodiment one, the potential defects on the transmission image and the reflection image need to be extracted.
Referring to fig. 4, the method for extracting the features of the potential defects includes the following steps:
201. preprocessing the transmission image and the reflection image;
the preprocessing step for processing the transmission image comprises: and acquiring a transmission image, performing Gaussian filtering noise reduction on the transmission image, and removing background textures of the transmission image to obtain the transmission image after pretreatment.
Further, the removing the background texture of the transmission image includes:
performing discrete Fourier transform on the transmission image to obtain a spectrogram;
acquiring the frequency distribution of the spectrogram;
processing the spectrogram through an image binarization algorithm and selecting texture frequency to obtain the texture frequency;
reserving the central frequency of the spectrogram, and removing the texture frequency to obtain the spectrogram of the texture-removed frequency;
and carrying out inverse Fourier transform on the frequency spectrogram of the de-textured frequency to obtain the preprocessed transmission image.
The step of preprocessing the reflected image comprises: and acquiring the reflection image, and carrying out mean value filtering and noise reduction on the reflection image to obtain the preprocessed reflection image.
Specifically, before the transmission image is preprocessed, the transmission image is as shown in fig. 5-1; after pre-processing the transmission image, the transmission image is shown in fig. 5-2.
Specifically, before preprocessing the reflection image, the reflection image is as shown in fig. 6-1.
202. Carrying out image segmentation processing on the transmission image according to the gray value, and marking the transmission image as a first bright block area if the gray value is greater than a first preset threshold value; if the gray value is smaller than a second preset threshold value, marking the gray value as a first dark block area;
203. combining the adjacent first bright block area and the first dark block area to obtain the first defect area;
further, the merging the adjacent first bright block area and the first dark block area includes:
acquiring a center point coordinate of the first bright block area and a center point coordinate of at least one first dark block area adjacent to the first bright block area;
and respectively calculating the distance difference of the first image to be merged of the center point coordinate of the first bright block area and the center point coordinate of the first dark block area, and selecting the first dark block area with the minimum distance difference of the first image to be merged to merge with the first bright block area.
Specifically, the first bright block area of the transmission image is shown in fig. 5-3, the first dark block area of the transmission image is shown in fig. 5-4, and the first defect area is shown in fig. 5-5.
204. Performing image segmentation processing on the reflection image according to the gray value, and marking the reflection image as a second bright block area if the gray value is greater than a third preset threshold value; if the gray value is smaller than a fourth preset threshold value, marking the gray value as a second dark block area;
205. and combining the second bright block area and the second dark block area which are adjacent to each other to obtain the second defect area.
Further, after image segmentation processing is performed on the defective area of the reflection image, the center point coordinate of the second bright block area and the center point coordinate of at least one second dark block area adjacent to the second bright block area are obtained; and respectively calculating the distance difference of a second image to be merged of the center point coordinate of the second bright block area and the center point coordinate of the second dark block area, and selecting the second dark block area with the minimum distance difference of the image to be merged with the second bright block area.
Specifically, the second light block region of the reflection image is shown in fig. 6-2, the second dark block region of the reflection image is shown in fig. 6-3, and the second defect region is shown in fig. 6-4.
Acquiring the center point coordinate of the second bright block area and the center point coordinate of at least one second dark block area adjacent to the second bright block area; respectively calculating the distance difference between the center point coordinate of the second bright block area and the center point coordinate of the second dark block area, and selecting the second dark block area with the minimum distance difference value of the second image to be merged to merge with the second bright block area, so as to obtain the second defective area of the reflected image shown in fig. 6-4.
In the embodiment of the present application, by preprocessing the transmission image and the reflection image, a latent defect (polarizer bubble or protective film bubble) is composed of a bright block defect that is significantly higher than a background gray value and a dark block defect that is significantly lower than the background gray value on the transmission image or the reflection image. Performing threshold segmentation on the transmission image or the reflection image for two times, and respectively extracting the bright block defect and the dark block defect; therefore, a bright block defect part and a dark block defect part of a potential defect can be obtained by dividing through two times of binarization algorithm processing, and the bright block defect part and the dark block defect part of the same potential defect are adjacent on an image, so that the dark block defect closest to the bright block defect is found according to the central point coordinate of the bright block defect, and the bright block defect and the dark block defect are integrated through a region merging algorithm, so that the same potential defect can be completely extracted.
In the process of image segmentation and extraction of potential defects, if the potential defects cannot be completely extracted, deviation occurs in the positioning of the central point of the potential defects, and when the image segmentation and extraction of the potential defects are performed by using a binarization algorithm, the image segmentation is performed on the regions with different gray values for multiple times respectively according to the characteristics that the potential defects have at least two gray values on the image, and then the extracted defect regions are combined, so that the first defect region of the transmission image and the second defect region of the reflection image can be more completely extracted, and the central point of the potential defects can be accurately positioned.
EXAMPLE III
The detection methods of the first and second embodiments can detect polarizer bubbles in the transparent area of the screen to be detected. For the ink area on the screen to be detected, because the transmission image of the ink area cannot be obtained, the detection of polarizer bubbles needs to be performed through the screen defect recognition neural network in the embodiment of the present application.
As shown in fig. 7, the training process of the screen defect recognition neural network includes the following steps:
301. acquiring at least M reflection images, and carrying out image block division on an ink area of the reflection images to obtain a reflection image training set, wherein M is an integer greater than two;
302. and inputting the reflection image training set into a convolutional neural network for training to obtain a screen defect recognition neural network.
Further, the defect type corresponding to the classifier of the screen defect recognition neural network comprises: polarizer bubbles and protective film bubbles; the characteristic diagram extracted by the screen defect recognition neural network is as follows:(ii) a The above-mentionedFor the input said reflection image training set, saidFor the output characteristic diagram, connectionsAndhas a convolution kernel ofSaidFor the bias term in each of the filters,in order to be a two-dimensional discrete convolution operator,is a non-linear activation function.
In the embodiment of the application, a reflection image training set is obtained by dividing the ink area of the reflection image, and the reflection image training set is input into a convolutional neural network for training to obtain a screen defect recognition neural network. And the screen defect identification neural network is used for carrying out characteristic identification on the polaroid bubbles in the ink area of the screen to be detected and outputting a detection result.
Example four
An embodiment of the present application further provides an electronic device, as shown in fig. 8, fig. 8 is a schematic structural diagram of the electronic device shown in the embodiment of the present application.
Referring to fig. 8, the electronic device 1000 includes a memory 1010 and a processor 1020.
The Processor 1020 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 1010 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions that are needed by the processor 1020 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, among others. In some embodiments, memory 1010 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 1010 has stored thereon executable code that, when processed by the processor 1020, may cause the processor 1020 to perform some or all of the methods described above.
EXAMPLE five
Corresponding to the foregoing application function implementation method embodiments, the present application further provides a non-transitory machine-readable storage medium having stored thereon executable code, which, when executed by a processor of an electronic device, causes the processor to perform any one of the method embodiments one to three.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
The aspects of the present application have been described in detail hereinabove with reference to the accompanying drawings. In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. Those skilled in the art should also appreciate that the acts and modules referred to in the specification are not necessarily required in the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application may be sequentially adjusted, combined, and deleted according to actual needs, and the modules in the device of the embodiment of the present application may be combined, divided, and deleted according to actual needs.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform part or all of the various steps of the above-described method according to the present application.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the applications disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (9)
1. A method for identifying a defective polarizer, comprising the steps of:
acquiring a transmission image and a reflection image of a screen to be detected;
the transmission image is formed by the area to be detected after light rays are transmitted from the screen to be detected;
the reflected image is an image of the area to be detected after the light is reflected on the surface of the screen to be detected;
carrying out image segmentation processing on the transmission image according to the gray value, and marking the transmission image as a first bright block area if the gray value is greater than a first preset threshold value; if the gray value is smaller than a second preset threshold value, marking the gray value as a first dark block area;
combining the adjacent first bright block area and the first dark block area to obtain a first defect area;
performing image segmentation processing on the reflection image according to the gray value, and marking the reflection image as a second bright block area if the gray value is greater than a third preset threshold value; if the gray value is smaller than a fourth preset threshold value, marking the gray value as a second dark block area;
combining the second bright block area and the second dark block area which are adjacent to each other to obtain a second defect area;
calculating the center distance difference of the first defect area and the second defect area according to the coordinates of the center points of the first defect area and the second defect area;
and judging the defect types corresponding to the first defect area and the second defect area according to the central distance difference.
2. The method for identifying a defective polarizer according to claim 1, wherein the determining the defect type corresponding to the first defect region and the second defect region according to the center-to-center distance difference comprises:
if the difference between the central distances of the first defect area and the second defect area is smaller than or equal to a deviation threshold, determining that the defect types corresponding to the first defect area and the second defect area are polarizer bubbles;
the determining the defect types corresponding to the first defect area and the second defect area according to the center distance difference further includes:
and if the difference between the central distances of the first defective area and the second defective area is larger than the deviation threshold, determining that the defect types corresponding to the first defective area and the second defective area are protective film bubbles.
3. The method of identifying a defective polarizer according to claim 1,
the merging the adjacent first bright block area and the first dark block area comprises:
acquiring a center point coordinate of the first bright block area and a center point coordinate of at least one first dark block area adjacent to the first bright block area;
respectively calculating the distance difference of the first image to be merged of the center point coordinate of the first bright block area and the center point coordinate of the first dark block area, and selecting the first dark block area with the minimum distance difference of the first image to be merged to merge with the first bright block area;
the merging of the adjacent second bright block area and the second dark block area includes:
acquiring the center point coordinate of the second bright block area and the center point coordinate of at least one second dark block area adjacent to the second bright block area;
and respectively calculating the distance difference of the second image to be merged of the center point coordinate of the second bright block area and the center point coordinate of the second dark block area, and selecting the second dark block area with the minimum value of the distance difference of the second image to be merged to merge with the second bright block area.
4. The method of identifying a defective polarizer according to claim 1,
the calculating a center distance difference between the first defect area and the second defect area according to the coordinates of the center points of the first defect area and the second defect area includes:
converting the pixel coordinates of the center points of the first and second defect areas into physical coordinates to obtain the physical coordinates (x) of the first center point of the first defect areaa,ya) And physical coordinates (x) of a second center point of the second defect regionb,yb);
5. The method of identifying a defective polarizer according to claim 1,
after the transmission image and the reflection image of the screen to be detected are obtained, the method further comprises the following steps:
preprocessing the transmission image and the reflection image; the pretreatment comprises the following steps:
obtaining the transmission image, performing Gaussian filtering noise reduction on the transmission image, and removing background textures of the transmission image to obtain the transmission image after pretreatment;
and acquiring the reflection image, and carrying out mean value filtering and noise reduction on the reflection image to obtain the preprocessed reflection image.
6. The method of identifying a defective polarizer according to claim 5,
the removing the background texture of the transmission image comprises:
performing discrete Fourier transform on the transmission image to obtain a spectrogram;
acquiring the frequency distribution of the spectrogram;
processing the spectrogram through an image binarization algorithm and selecting texture frequency to obtain the texture frequency;
reserving the central frequency of the spectrogram, and removing the texture frequency to obtain the spectrogram of the texture-removed frequency;
and carrying out inverse Fourier transform on the frequency spectrogram of the de-textured frequency to obtain the preprocessed transmission image.
7. The method of identifying a defective polarizer according to claim 1,
before the image segmentation processing is performed on the transmission image according to the gray value, the method comprises the following steps:
acquiring at least M reflection images, and carrying out image block division on an ink area of the reflection images to obtain a reflection image training set, wherein M is an integer greater than two;
inputting the reflection image training set into a convolutional neural network for training to obtain a screen defect recognition neural network; the defect type corresponding to the classifier of the screen defect recognition neural network comprises the following steps: polarizer bubbles and protective film bubbles; the characteristic diagram extracted by the screen defect recognition neural network is as follows: y isj=f(bj+∑iwij*xi) (ii) a Said xiFor the input training set of reflection images, yjFor the output profile, connect xiAnd yjHas a convolution kernel of wijSaid b isjFor the bias term in each filter, is a two-dimensional discrete convolution operator, and f (-) is a nonlinear activation function.
8. An electronic device, comprising:
a processor (1020); and the number of the first and second groups,
a memory (1010) having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any of claims 1-7.
9. A non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111186165.9A CN113628212B (en) | 2021-10-12 | 2021-10-12 | Defective polarizer identification method, electronic device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111186165.9A CN113628212B (en) | 2021-10-12 | 2021-10-12 | Defective polarizer identification method, electronic device, and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113628212A CN113628212A (en) | 2021-11-09 |
CN113628212B true CN113628212B (en) | 2022-03-11 |
Family
ID=78391087
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111186165.9A Active CN113628212B (en) | 2021-10-12 | 2021-10-12 | Defective polarizer identification method, electronic device, and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113628212B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116997927A (en) * | 2022-03-01 | 2023-11-03 | 京东方科技集团股份有限公司 | Curved substrate bubble detection method and detection system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW200416728A (en) * | 2003-01-08 | 2004-09-01 | Tdk Corp | Defect detection method of disc substrate, apparatus for the same, and method for manufacturing substrate for optical disc |
CN102081047A (en) * | 2009-11-27 | 2011-06-01 | 法国圣-戈班玻璃公司 | Method and system for distinguishing defects of substrate |
CN104568990A (en) * | 2015-01-10 | 2015-04-29 | 浙江大学 | Method for detecting bubble defect inside glass based on Mie scattering |
CN109297971A (en) * | 2017-07-24 | 2019-02-01 | 住友化学株式会社 | Defect inspecting system and defect detecting method |
CN113015901A (en) * | 2018-11-21 | 2021-06-22 | 日本电气硝子株式会社 | Method for producing glass plate and apparatus for producing glass plate |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103217436B (en) * | 2013-03-06 | 2015-05-20 | 京东方科技集团股份有限公司 | Backlight module group defect detection method and equipment |
US9518934B2 (en) * | 2014-11-04 | 2016-12-13 | Kla-Tencor Corp. | Wafer defect discovery |
-
2021
- 2021-10-12 CN CN202111186165.9A patent/CN113628212B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW200416728A (en) * | 2003-01-08 | 2004-09-01 | Tdk Corp | Defect detection method of disc substrate, apparatus for the same, and method for manufacturing substrate for optical disc |
CN102081047A (en) * | 2009-11-27 | 2011-06-01 | 法国圣-戈班玻璃公司 | Method and system for distinguishing defects of substrate |
CN104568990A (en) * | 2015-01-10 | 2015-04-29 | 浙江大学 | Method for detecting bubble defect inside glass based on Mie scattering |
CN109297971A (en) * | 2017-07-24 | 2019-02-01 | 住友化学株式会社 | Defect inspecting system and defect detecting method |
CN113015901A (en) * | 2018-11-21 | 2021-06-22 | 日本电气硝子株式会社 | Method for producing glass plate and apparatus for producing glass plate |
Non-Patent Citations (1)
Title |
---|
基于DM6446的LCD偏光片贴附缺陷检测***的研究与应用;王胜 等;《数学技术与应用》;20131231;第31-32页 * |
Also Published As
Publication number | Publication date |
---|---|
CN113628212A (en) | 2021-11-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112858318B (en) | Method for distinguishing screen foreign matter defect from dust, electronic equipment and storage medium | |
CN112767398B (en) | Method and device for detecting wafer defects | |
US7162073B1 (en) | Methods and apparatuses for detecting classifying and measuring spot defects in an image of an object | |
CN111627009A (en) | Screen detection method and device and head-mounted display equipment | |
CN101464418B (en) | Flaw detection method and apparatus | |
TW201337839A (en) | Segmentation for wafer inspection | |
CN115020267B (en) | Semiconductor surface defect detection method | |
CN112701060B (en) | Method and device for detecting bonding wire of semiconductor chip | |
CN113160161B (en) | Method and device for detecting defects at edge of target | |
CN112798613B (en) | LCD foreign matter defect color imaging detection method, electronic equipment and storage medium | |
CN113628212B (en) | Defective polarizer identification method, electronic device, and storage medium | |
KR20200086812A (en) | System for inspecting substrate defects by bubbles and Method for inspecting substrate defects by bubbles | |
CN117152165B (en) | Photosensitive chip defect detection method and device, storage medium and electronic equipment | |
CN110706224A (en) | Optical element weak scratch detection method, system and device based on dark field image | |
CN117197527A (en) | Defect detection classification method and device for glass substrate of liquid crystal display screen | |
CN115170501A (en) | Defect detection method, system, electronic device and storage medium | |
CN112802022B (en) | Method for intelligently detecting defective glass image, electronic device and storage medium | |
CN115631190A (en) | Glass substrate defect identification warning method and system, electronic device and storage medium | |
CN116071304A (en) | Article edge line positioning method and device and electronic equipment | |
CN115049643A (en) | Near-to-eye display module interlayer foreign matter detection method, device, equipment and storage medium | |
TWI821506B (en) | Computerized system and method for obtaining information about a region of an object | |
CN113077431A (en) | Laser chip defect detection method, system, equipment and storage medium based on deep learning | |
CN114219758A (en) | Defect detection method, system, electronic device and computer readable storage medium | |
CN112163586A (en) | Feature extraction method and device of target object and computer readable medium | |
CN112987356A (en) | Method and device for false detection and filtering of foreign matters at bottom of liquid crystal panel |
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 | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: 215129 Rooms 101, 102, 901, 902, Floor 9, Building 11, No. 198, Jialing River Road, High tech Zone, Suzhou City, Jiangsu Province Patentee after: Gaoshi Technology (Suzhou) Co.,Ltd. Address before: 215011 rooms 101, 102, 901 and 902, floor 1, building 11, 198 Jialingjiang Road, high tech Zone, Suzhou, Jiangsu Province Patentee before: Gaoshi Technology (Suzhou) Co.,Ltd. |