CN111583225A - Defect detection method, device and storage medium - Google Patents

Defect detection method, device and storage medium Download PDF

Info

Publication number
CN111583225A
CN111583225A CN202010380877.3A CN202010380877A CN111583225A CN 111583225 A CN111583225 A CN 111583225A CN 202010380877 A CN202010380877 A CN 202010380877A CN 111583225 A CN111583225 A CN 111583225A
Authority
CN
China
Prior art keywords
defect
image
defect detection
detection method
brightness
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.)
Granted
Application number
CN202010380877.3A
Other languages
Chinese (zh)
Other versions
CN111583225B (en
Inventor
周乔珂
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BOE Technology Group Co Ltd
Beijing BOE Display Technology Co Ltd
Original Assignee
BOE Technology Group Co Ltd
Beijing BOE Display Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by BOE Technology Group Co Ltd, Beijing BOE Display Technology Co Ltd filed Critical BOE Technology Group Co Ltd
Priority to CN202010380877.3A priority Critical patent/CN111583225B/en
Publication of CN111583225A publication Critical patent/CN111583225A/en
Application granted granted Critical
Publication of CN111583225B publication Critical patent/CN111583225B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
    • G09G3/00—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes
    • G09G3/006—Electronic inspection or testing of displays and display drivers, e.g. of LED or LCD displays
    • G—PHYSICS
    • 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)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Quality & Reliability (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention discloses a defect detection method, a defect detection device and a storage medium. The defect detection method is used for a display device. The defect detection method comprises the following steps: acquiring an image of a display device in a display state; removing a noise signal of the image based on an empirical mode decomposition algorithm and extracting a characteristic signal; and processing the characteristic signals based on a support vector machine to detect the brightness defect of the image. According to the defect detection method provided by the embodiment of the invention, the characteristic signals of the image are extracted through the empirical mode decomposition algorithm and the characteristic signals are processed by the support vector machine, so that the brightness defect of the image of the display device in a display state can be automatically detected, the detection standard is uniform and objective, the reliable detection of the brightness defect can be realized, and the detection speed is higher.

Description

Defect detection method, device and storage medium
Technical Field
The present invention relates to the field of defect detection technologies, and in particular, to a defect detection method, a defect detection apparatus, and a storage medium.
Background
The TFT-LCD has many advantages of low power consumption, thin and easy use, high brightness and contrast, and high response speed, and is widely applied to display devices such as smart phones, tablet computers, notebook computers, televisions, and the like. In the production process of the display, white point Mura defects are often generated due to production processes and the like, and the Mura defects refer to the phenomenon that the brightness of the display is not uniform, so that various marks are caused. When the display generates the Mura defect, the display needs to be brightness compensated to make the display brightness uniform. How to detect the Mura defect is a difficult problem.
In the related art, a conventional manual visual inspection method is used to detect Mura defects of a display. However, the method is easily interfered by human subjective factors and external environment, and the Mura defect quantification lacks a uniform judgment standard, so that the reliable detection of the Mura defect is difficult to realize.
Disclosure of Invention
The embodiment of the invention provides a defect detection method, a defect detection device and a storage medium.
The defect detection method of the embodiment of the invention is used for a display device, and comprises the following steps:
acquiring an image of the display device in a display state;
removing noise signals of the image and extracting characteristic signals based on an empirical mode decomposition algorithm;
and processing the characteristic signals based on a support vector machine to detect the brightness defect of the image.
According to the defect detection method provided by the embodiment of the invention, the characteristic signals of the image are extracted through the empirical mode decomposition algorithm and the characteristic signals are processed by the support vector machine, so that the brightness defect of the image of the display device in a display state can be automatically detected, the detection standard is uniform and objective, the reliable detection of the brightness defect can be realized, and the detection speed is higher.
In some embodiments, removing noise signals and extracting feature signals of the image based on an empirical mode decomposition algorithm comprises:
gradually decomposing the image signal of the image based on the empirical mode decomposition algorithm to obtain a plurality of eigenmode components and remainder components;
and acquiring the plurality of eigenmode components as the characteristic signal, wherein the residual component is the noise signal.
In some embodiments, processing the feature signals to detect luminance defects of the image based on a support vector machine comprises:
performing feature extraction and feature fusion on the plurality of eigenmode components based on the support vector machine to generate feature vectors;
determining a plurality of fusion eigenvalues according to the eigenvectors;
and comparing the plurality of fusion characteristic values with a plurality of preset characteristic values to detect the brightness defect.
In some embodiments, the detecting the brightness defect includes detecting the brightness defect by comparing the fused feature values with preset feature values, where the detecting the brightness defect includes:
and comparing the plurality of fusion characteristic values with the plurality of preset characteristic values corresponding to each defect type to determine the type of the brightness defect.
In some embodiments, the plurality of preset feature values are obtained by training the support vector machine using an image containing the brightness defect.
In some embodiments, the support vector machine includes a kernel function parameter and a penalty parameter, the kernel function parameter and the penalty parameter optimized during a training process of the support vector machine.
In some embodiments, the defect detection method includes:
and marking the brightness defect.
The defect detecting apparatus of an embodiment of the present invention is a defect detecting apparatus for a display device, the defect detecting apparatus including:
the acquisition module is used for acquiring the image of the display device in a display state;
an extraction module for removing noise signals of the image and extracting characteristic signals based on an empirical mode decomposition algorithm;
a detection module for processing the feature signals based on a support vector machine to detect a brightness defect of the image.
The defect detection device of the embodiment of the invention can automatically detect the brightness defect of the image of the display device in the display state by extracting the characteristic signal of the image through the empirical mode decomposition algorithm and processing the characteristic signal by the support vector machine, has uniform and objective detection standard, can realize reliable detection of the brightness defect and has higher detection speed.
The defect detecting apparatus according to an embodiment of the present invention is used for a display device, and includes a memory in which a computer program is stored and a processor that implements the defect detecting method according to any one of the above embodiments when the processor executes the computer program.
The defect detection device of the embodiment of the invention can automatically detect the brightness defect of the image of the display device in the display state by extracting the characteristic signal of the image through the empirical mode decomposition algorithm and processing the characteristic signal by the support vector machine, has uniform and objective detection standard, can realize reliable detection of the brightness defect and has higher detection speed.
The computer readable storage medium of the embodiments of the present invention stores thereon a computer program, which when executed by a processor, implements the defect detection method of any of the above embodiments.
The computer-readable storage medium of the embodiment of the invention can automatically detect the brightness defect of the image of the display device in the display state by extracting the characteristic signal of the image through the empirical mode decomposition algorithm and processing the characteristic signal by the support vector machine, has uniform and objective detection standard, can realize reliable detection of the brightness defect, and has higher detection speed.
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
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow chart of a defect detection method according to an embodiment of the present invention;
FIG. 2 is a block diagram of a defect detection apparatus according to an embodiment of the present invention;
FIG. 3 is another schematic flow chart of a defect detection method according to an embodiment of the invention;
FIG. 4 is a schematic flow chart of a defect detection method according to an embodiment of the invention;
FIG. 5 is a point Mura schematic diagram according to an embodiment of the present invention;
FIG. 6 is a schematic representation of a line Mura according to an embodiment of the present invention;
FIG. 7 is a schematic view of a face Mura of an embodiment of the present invention;
FIG. 8 is a diagram illustrating optimization results of kernel function parameters and penalty parameters according to an embodiment of the present invention;
FIG. 9 is a schematic block diagram of a defect detection apparatus according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the embodiments of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the embodiments of the present invention, "a plurality" means two or more unless specifically limited otherwise.
In the description of the embodiments of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as being fixedly connected, detachably connected, or integrally connected; may be mechanically connected, may be electrically connected or may be in communication with each other; either directly or indirectly through intervening media, either internally or in any other relationship. Specific meanings of the above terms in the embodiments of the present invention can be understood by those of ordinary skill in the art according to specific situations.
Referring to fig. 1, a defect detection method for a display device is provided in an embodiment of the present invention. The defect detection method comprises the following steps:
step S10: acquiring an image of a display device in a display state;
step S20: removing noise signals of the image and extracting characteristic signals based on an Empirical Mode Decomposition (EMD) algorithm;
step S30: the feature signals are processed based on a Support Vector Machine (SVM) to detect a luminance defect (Mura defect, luminance unevenness) of the image.
The defect detection method according to the embodiment of the present invention can be realized by the defect detection apparatus 100 according to the embodiment of the present invention. Specifically, referring to fig. 2, the defect detecting apparatus 100 includes an obtaining module 10, an extracting module 20, and a detecting module 30. The acquiring module 10 is used for acquiring an image of the display device in a display state. The extraction module 20 is configured to remove noise signals of the image and extract feature signals based on an empirical mode decomposition algorithm. The detection module 30 is used for processing the feature signals based on the support vector machine to detect the brightness defect of the image.
According to the defect detection method and the defect detection device 100, the characteristic signals of the image are extracted through the empirical mode decomposition algorithm, and the characteristic signals are processed by the support vector machine, so that the brightness defect of the image of the display device in the display state can be automatically detected, the detection standard is uniform and objective, the reliable detection of the brightness defect can be realized, and the detection speed is high.
It is understood that the defect detecting apparatus 100 is configured to detect a luminance defect of the display device using an image in a display state of the display device. Specifically, the defect detection apparatus 100 captures an image of the display surface of the display device in a display state by a camera. In some examples, the display devices may travel along a conveyor belt in a test or manufacturing facility, the camera may capture all or substantially all of the pixels of each display device in a display state, and the acquisition module 10 then acquires an image from the camera, which is analyzed by the extraction module 20 and the detection module 30 to detect the presence of brightness defects. The Display device may be a TFT-LCD (Thin Film Transistor-Liquid Crystal Display) Display device, an OLED (Organic Light-Emitting Diode) Display device, an AMOLED (Active-matrix Organic Light-Emitting Diode) Display device, or the like.
An image of the display device in a display state may or may not have a luminance defect. Therefore, the characteristic signals of the image of the display device in the display state are extracted through the empirical mode decomposition algorithm, and then the characteristic signals are analyzed and processed by using the support vector machine, so that whether the display device has brightness defects or not can be determined. The empirical mode decomposition algorithm is a self-adaptive signal time-frequency processing method, is particularly suitable for analyzing and processing nonlinear non-stationary signals, can quickly and effectively remove noise signals of images, and extracts characteristic signals of the images. The support vector machine is a supervised learning model in the field of machine learning, is usually used for pattern recognition, classification and regression analysis, and is very effective in detecting the brightness defects of the display device, simple in algorithm, high in real-time performance and easy to implement. The display device has brightness defect, which means that when the display device is in a display state, the display interface has brightness defect.
In some embodiments, a defect detection method includes: the brightness defect is marked.
The defect detection method of the present embodiment can be realized by the defect detection apparatus 100 of the present embodiment. Specifically, the defect detecting apparatus 100 includes a marking module 40, and the marking module 40 is used for marking the brightness defect.
It can be understood that after the brightness defect is detected, the positioning mark can be carried out so as to compensate the brightness defect, so that when the display device is in a display state, the display interface is displayed normally, and the brightness defect does not exist.
Referring to fig. 3, in some embodiments, step S20 includes:
step S22: gradually decomposing an image signal of the image based on an empirical Mode decomposition algorithm to obtain a plurality of eigenmode components (IMF) and remainder components;
step S24: and acquiring a plurality of eigenmode components as characteristic signals, wherein the residual component is a noise signal.
The defect detection method of the present embodiment can be realized by the defect detection apparatus 100 of the present embodiment. Specifically, the extraction module 20 is configured to gradually decompose the image signal of the image based on an empirical mode decomposition algorithm to obtain a plurality of eigenmode components and remainder components, and is configured to obtain a plurality of eigenmode components as the feature signal. Wherein the remainder component is a noise signal.
It will be appreciated that the image is two-dimensional, comprising m x n pixels. First, initialize, let r0(x,y)＝I(m,n)，k＝1，r0(m, n) represents the input image signal to be decomposed, and k is the number of eigenmode components. Next, the k-th eigenmode component is extracted, which is denoted as imfk(m, n). Specifically, the extraction of the eigenmode components is performed in the following order 1 to 6:
1. initialization, let hk,l-1(m,n)＝rk-1(m,n)，l＝1；
2. Determination of hk,l-1(m, n) all local maxima and minima points;
3. fitting all maximum value points by utilizing a two-dimensional surface interpolation method to obtain hk,l-1Upper envelope surface E of (m, n)max,l-1(m, n), fitting all minimum value points by using a two-dimensional surface interpolation method to obtain hk,l-1Lower envelope surface E of (m, n)min,l-1(m,n)；
4. Averaging the upper and lower envelopes: eaverage,l-1(m,n)＝[Emax,l-1(m,n)+Emax,l-1(m,n)]/2；
5. Let hk,l(m,n)＝hk,l-1(m,n)-Eaverage,l-1(m,n)，l＝l+1；
6.imfk(m,n)＝hk,l(m,n)。
Then, the standard deviation is calculated
Figure BDA0002482032160000051
Under the condition that SD is larger than a preset value, continuously decomposing the decomposed residual image, and performing rk(m,n)＝rk-1(m,n)-imfk(m, n), repeating the above steps 1-6, k ═ k + 1. And finally, ending the decomposition process until the SD is less than or equal to the preset value. Preferably, the preset value is 0.2. In other embodiments, the preset value may be 0.18, 0.22, or other suitable value.
Through the stepwise decomposition, the two-dimensional image signal is decomposed into a sum of a plurality of eigenmode components and remainder components as follows:
Figure BDA0002482032160000061
where I (m, n) is a two-dimensional image signal, imfk(m, n) is the eigenmode component from the kth decomposition, k being the number of eigenmode components, rk(m, n) is the remainder component (Residue) of the final decomposition.
Referring to fig. 4, in some embodiments, step S30 includes:
step S32: performing feature extraction and feature fusion on the plurality of eigenmode components based on a support vector machine to generate feature vectors;
step S34: determining a plurality of fusion eigenvalues according to the eigenvectors;
step S36: and comparing the plurality of fusion characteristic values with the plurality of preset characteristic values to detect the brightness defect.
The defect detection method of the present embodiment can be realized by the defect detection apparatus 100 of the present embodiment. Specifically, the detection module 30 is configured to perform feature extraction and feature fusion on the plurality of eigenmode components based on a support vector machine to generate a feature vector, determine a plurality of fused feature values according to the feature vector, and compare the plurality of fused feature values with a plurality of preset feature values to detect the luminance defect.
Specifically, in step S32, the feature extraction and feature fusion of the plurality of eigenmode components includes performing spatial size normalization of the plurality of eigenmode components, and then generating feature vectors through feature transformation, pooling operations, and vectorization operations
Figure BDA0002482032160000062
Wherein the feature vector comprises a plurality of fused features
Figure BDA0002482032160000063
In one embodiment, the plurality of fusion features includes a gravity center position R, C of the defect region in the image, an average gray scale value Mean of the defect region, an Entropy of a gray scale histogram of the defect region, potentials Alpha and Beta of a gray scale distribution of the defect region, an anisotropy coefficient Aniso, and mixed potentials MRow and MCol along row and column directions respectively corresponding to the defect region
Figure BDA0002482032160000064
Therefore, in step S34, a plurality of fused feature values corresponding to the plurality of fused features may be determined from the feature vector.
The plurality of preset feature values in step S36 are obtained by training the support vector machine using an image containing a luminance defect. It is understood that the support vector machine may be trained by manually screening out a plurality of images containing luminance defects as training samples. In the training process, the image signal of each sample image is gradually decomposed based on an empirical mode decomposition algorithm to obtain a plurality of eigenmode components, then feature extraction and feature fusion are carried out based on the plurality of eigenmode components of each sample image of the support vector fleet to generate a feature vector of each sample image, and finally a plurality of preset feature values corresponding to a plurality of fusion features are determined according to the feature vectors of the plurality of sample images. Therefore, a plurality of preset characteristic values corresponding to the image with the brightness defect can be determined.
Further, the support vector machine comprises a kernel function parameter g and a penalty parameter c, and the kernel function parameter g and the penalty parameter c are optimized in the training process of the support vector machine. Therefore, the kernel function parameter g and the penalty parameter c are optimized, and the detection accuracy of the brightness defect of the image can be improved.
In step S36, by comparing the plurality of fused feature values with the plurality of preset feature values, it can be determined whether the image has a luminance defect, thereby achieving detection of the luminance defect. The preset characteristic values and the fusion characteristic values are specific numerical values, and under the condition that each fusion characteristic value is the same as the corresponding preset characteristic value or within the allowable range of the preset characteristic value, the brightness defect of the image is determined; otherwise, determining that the image has no brightness defect.
In some embodiments, the luminance defect includes a plurality of defect types, and each defect type corresponds to a different plurality of preset feature values. Step S36 includes: and comparing the plurality of fusion characteristic values with a plurality of preset characteristic values corresponding to each defect type to determine the type of the brightness defect.
The defect detection method of the present embodiment can be realized by the defect detection apparatus 100 of the present embodiment. Specifically, the detection module 30 is configured to compare the plurality of fusion feature values with a plurality of preset feature values corresponding to each defect type to determine the type of the brightness defect.
Specifically, referring to fig. 5 to 7, the luminance defect includes three defect types of point Mura, line Mura, and plane Mura. In one embodiment, the method includes training 30 sample images to obtain a plurality of preset feature values corresponding to a point Mura, a line Mura and a plane Mura: the gravity center position R, C of the defect region in the image, the Mean gray value Mean of the defect region, the Entropy of the gray histogram of the defect region, the potentials Alpha, Beta of the gray value distribution of the defect region, the anisotropy coefficient Aniso, and the mixed potentials MRow, MCol along the row and column directions are shown in table 1. Referring to fig. 8, in the training process, the kernel parameter g and the penalty parameter c of the support vector machine are optimized to obtain g being 0.133, and c being 0.042. After the kernel function parameter g and the penalty parameter c are optimized, luminance defect detection can be performed by using a plurality of test images so as to test the detection accuracy of the trained support vector machine on the luminance defects of the images. The test images are manually marked, including images with and without brightness defects.
Type (B) R C Mean Entropy Alpha Beta Aniso MRow MCol
Point Mura 36 90 45 0.16 1.35 6.65 1.65 2.65 1.58
Line Mura 130 182 156 3.19 4.77 0.36 0.34 0.085 0.37
Flour Mura 2032 3500 240 12.63 1.76 4.57 1.56 1.65 5.42
TABLE 1
Therefore, after determining a plurality of fusion feature values according to the feature vectors, the existence of the points Mura, the lines Mura and/or the planes Mura in the image can be determined by comparing the plurality of fusion feature values with a plurality of preset feature values corresponding to the points Mura, the lines Mura and the planes Mura, or the absence of brightness defects in the image. Therefore, whether the image of the display device in the display state has the brightness defect or not can be detected, and the brightness defect can be classified to detect the specific type of the brightness defect.
In one example, where the plurality of fused feature values R, C, Mean, Entrophy, Alpha, Beta, Aniso, MRow, MCol are the same as or within an allowable range of the plurality of feature values corresponding to point Mura, the image presence point Mura may be determined.
It should be noted that the specific values mentioned above are only for illustrating the implementation of the invention in detail and should not be construed as limiting the invention. In other examples or embodiments or examples, other values may be selected in accordance with the present invention and are not specifically limited herein.
Referring to fig. 9, a defect detecting apparatus 100 for a display device is provided according to an embodiment of the present invention. The defect detection apparatus 100 includes a memory 102 and a processor 104. The memory 102 stores a computer program, and the processor 104 implements the defect detection method according to any of the above embodiments when executing the program.
The defect detection device 100 of the embodiment of the invention extracts the characteristic signals of the image through the empirical mode decomposition algorithm and processes the characteristic signals by the support vector machine, can automatically detect the brightness defects of the image of the display device in the display state, has uniform and objective detection standard, can realize reliable detection of the brightness defects, and has higher detection speed.
It is understood that the memory 102 may be used to store computer programs and that the processor 104 may implement various functions of the defect detection apparatus 100 by running or executing the computer programs stored in the memory 102 and calling up data stored in the memory 102. The computer program includes computer program code. The computer program code may be in the form of source code, object code, an executable file or some intermediate form, etc.
The memory 102 may include high-speed random access memory and may also include non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device. The Processor 104 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 device, discrete hardware component, etc.
It should be noted that the explanation and the advantageous effects of the defect detection method of the above embodiment are also applicable to the defect detection apparatus 100 of the present embodiment, and are not detailed here to avoid redundancy. The acquiring module 10, the extracting module 20, the detecting module 30 and the marking module 40 of the defect detecting apparatus 100 of the above embodiment may be integrated into one processor 104, i.e. the processor 104 of the defect detecting apparatus 100 may implement the functions of the acquiring module 10, the extracting module 20, the detecting module 30 and the marking module 40.
The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by the processor 104, the defect detection method of any of the above embodiments is implemented.
For example, in the case where the program is executed by the processor 104, the following defect detection method is implemented:
step S10: acquiring an image of a display device in a display state;
step S20: removing noise signals of the image and extracting characteristic signals based on an Empirical Mode Decomposition (EMD) algorithm;
step S30: the feature signals are processed based on a Support Vector Machine (SVM) to detect a luminance defect (Mura defect, luminance unevenness) of the image.
The computer readable storage medium may be disposed in the defect detection apparatus 100, or may be disposed in the cloud server, and the defect detection apparatus 100 may communicate with the cloud server to obtain the corresponding program.
In the description herein, references to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example" or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processing module-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of embodiments of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims (10)

1. A defect detection method for a display device, the defect detection method comprising:
acquiring an image of the display device in a display state;
removing noise signals of the image and extracting characteristic signals based on an empirical mode decomposition algorithm;
and processing the characteristic signals based on a support vector machine to detect the brightness defect of the image.
2. The defect detection method of claim 1, wherein removing noise signals and extracting feature signals of the image based on an empirical mode decomposition algorithm comprises:
gradually decomposing the image signal of the image based on the empirical mode decomposition algorithm to obtain a plurality of eigenmode components and remainder components;
and acquiring the plurality of eigenmode components as the characteristic signal, wherein the residual component is the noise signal.
3. The defect detection method of claim 2, wherein processing the feature signals to detect luminance defects of the image based on a support vector machine comprises:
performing feature extraction and feature fusion on the plurality of eigenmode components based on the support vector machine to generate feature vectors;
determining a plurality of fusion eigenvalues according to the eigenvectors;
and comparing the plurality of fusion characteristic values with a plurality of preset characteristic values to detect the brightness defect.
4. The method of claim 3, wherein the luminance defect comprises a plurality of defect types, each of the defect types corresponds to a different one of the plurality of default eigenvalues, and comparing the fused eigenvalues with the default eigenvalues to detect the luminance defect comprises:
and comparing the plurality of fusion characteristic values with the plurality of preset characteristic values corresponding to each defect type to determine the type of the brightness defect.
5. The defect detection method of claim 3, wherein the preset feature values are obtained by training the support vector machine using an image containing the brightness defect.
6. The defect detection method of claim 5, wherein the support vector machine comprises a kernel function parameter and a penalty parameter, and the kernel function parameter and the penalty parameter are optimized during a training process of the support vector machine.
7. The defect detection method of claim 1, wherein the defect detection method comprises:
and marking the brightness defect.
8. A defect detecting apparatus for a display device, the defect detecting apparatus comprising:
the acquisition module is used for acquiring the image of the display device in a display state;
an extraction module for removing noise signals of the image and extracting characteristic signals based on an empirical mode decomposition algorithm;
a detection module for processing the feature signals based on a support vector machine to detect a brightness defect of the image.
9. A defect detection apparatus for a display device, the defect detection apparatus comprising a memory and a processor, the memory storing a computer program, the processor implementing the defect detection method of any one of claims 1-7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of defect detection according to any one of claims 1 to 7.
CN202010380877.3A 2020-05-08 2020-05-08 Defect detection method, device and storage medium Active CN111583225B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010380877.3A CN111583225B (en) 2020-05-08 2020-05-08 Defect detection method, device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010380877.3A CN111583225B (en) 2020-05-08 2020-05-08 Defect detection method, device and storage medium

Publications (2)

Publication Number Publication Date
CN111583225A true CN111583225A (en) 2020-08-25
CN111583225B CN111583225B (en) 2024-05-24

Family

ID=72117271

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010380877.3A Active CN111583225B (en) 2020-05-08 2020-05-08 Defect detection method, device and storage medium

Country Status (1)

Country Link
CN (1) CN111583225B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113218962A (en) * 2021-04-27 2021-08-06 京东方科技集团股份有限公司 Display defect detection device, detection method thereof and display defect detection system
CN114862801A (en) * 2022-05-11 2022-08-05 南京巨鲨显示科技有限公司 Method, system, device and storage medium for detecting display performance of medical display

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102622611A (en) * 2012-01-13 2012-08-01 哈尔滨工业大学 Multi-group image classification method based on characteristic expansion and fuzzy support vector machine
CN107464226A (en) * 2017-07-31 2017-12-12 东南大学 A kind of image de-noising method based on improvement two-dimensional empirical mode decomposition algorithm
US20180301071A1 (en) * 2017-04-18 2018-10-18 Samsung Display Co., Ltd. System and method for white spot mura detection
US20190191150A1 (en) * 2017-12-15 2019-06-20 Samsung Display Co., Ltd. System and method for mura detection on a display
US20190362481A1 (en) * 2018-05-24 2019-11-28 Keysight Technologies, Inc. Detecting mura defects in master panel of flat panel displays during fabrication
WO2019232862A1 (en) * 2018-06-06 2019-12-12 平安科技（深圳）有限公司 Mouth model training method and apparatus, mouth recognition method and apparatus, device, and medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102622611A (en) * 2012-01-13 2012-08-01 哈尔滨工业大学 Multi-group image classification method based on characteristic expansion and fuzzy support vector machine
US20180301071A1 (en) * 2017-04-18 2018-10-18 Samsung Display Co., Ltd. System and method for white spot mura detection
CN107464226A (en) * 2017-07-31 2017-12-12 东南大学 A kind of image de-noising method based on improvement two-dimensional empirical mode decomposition algorithm
US20190191150A1 (en) * 2017-12-15 2019-06-20 Samsung Display Co., Ltd. System and method for mura detection on a display
US20190362481A1 (en) * 2018-05-24 2019-11-28 Keysight Technologies, Inc. Detecting mura defects in master panel of flat panel displays during fabrication
WO2019232862A1 (en) * 2018-06-06 2019-12-12 平安科技（深圳）有限公司 Mouth model training method and apparatus, mouth recognition method and apparatus, device, and medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
刘宾;陈方林;陈平;: "基于EMD复合材料X射线图像微小缺陷提取", 无损检测 *
李大中;赵杰;: "基于EMD和GA-SVM的超声检测缺陷信号识别", 中国测试 *
黄世奇 等: "基于二维本征模态函数的SAＲ 图像目标检测", 兵器装备工程学报 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113218962A (en) * 2021-04-27 2021-08-06 京东方科技集团股份有限公司 Display defect detection device, detection method thereof and display defect detection system
WO2022227491A1 (en) * 2021-04-27 2022-11-03 京东方科技集团股份有限公司 Display defect detection apparatus and detection method therefor, and display defect detection system
CN114862801A (en) * 2022-05-11 2022-08-05 南京巨鲨显示科技有限公司 Method, system, device and storage medium for detecting display performance of medical display

Also Published As

Publication number Publication date
CN111583225B (en) 2024-05-24

Similar Documents

Publication Publication Date Title
US10043090B2 (en) Information processing device, information processing method, computer-readable recording medium, and inspection system
JP6794737B2 (en) Information processing equipment, information processing methods, programs and inspection systems
US20120027288A1 (en) Methods, Systems and Apparatus for Defect Detection
JP7274885B2 (en) Display device defect identification system and method
US11189019B2 (en) Method for detecting defects, electronic device, and computer readable medium
US20140119638A1 (en) System, method and computer program product to evaluate a semiconductor wafer fabrication process
CN112308854B (en) Automatic detection method and system for chip surface flaws and electronic equipment
CN107895377B (en) Foreground target extraction method, device, equipment and storage medium
US8542912B2 (en) Determining the uniqueness of a model for machine vision
US20170278234A1 (en) Method for detecting a defect on a surface of a tire
CN110910445B (en) Object size detection method, device, detection equipment and storage medium
CN109376783B (en) Robot adaptive terrain classification method, system and computer readable storage medium
CN111583225B (en) Defect detection method, device and storage medium
CN110738644A (en) automobile coating surface defect detection method and system based on deep learning
CN111598913B (en) Image segmentation method and system based on robot vision
CN108460344A (en) Dynamic area intelligent identifying system in screen and intelligent identification Method
US8542905B2 (en) Determining the uniqueness of a model for machine vision
CN117392042A (en) Defect detection method, defect detection apparatus, and storage medium
CN109785290B (en) Steel plate defect detection method based on local illumination normalization
CN113947598A (en) Plastic lunch box defect detection method, device and system based on image processing
Lee 16‐4: Invited Paper: Region‐Based Machine Learning for OLED Mura Defects Detection
CN117372415A (en) Laryngoscope image recognition method, device, computer equipment and storage medium
CN117333489A (en) Film damage detection device and detection system
CN112950598A (en) Method, device and equipment for detecting flaw of workpiece and storage medium
Chen et al. An effective image segmentation method for noisy low-contrast unbalanced background in Mura defects using balanced discrete-cosine-transfer (BDCT)

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