CN116823771A - ZARA defect specification detection method, system and storage medium - Google Patents
ZARA defect specification detection method, system and storage medium Download PDFInfo
- Publication number
- CN116823771A CN116823771A CN202310775791.4A CN202310775791A CN116823771A CN 116823771 A CN116823771 A CN 116823771A CN 202310775791 A CN202310775791 A CN 202310775791A CN 116823771 A CN116823771 A CN 116823771A
- Authority
- CN
- China
- Prior art keywords
- area
- bright
- image
- region
- gray
- 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.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 107
- 238000001514 detection method Methods 0.000 title claims abstract description 49
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 37
- 230000008569 process Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30121—CRT, LCD or plasma display
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Pathology (AREA)
- Software Systems (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Image Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a ZARA defect specification detection method, a system and a storage medium, which comprises the following steps: step one: acquiring and intercepting a panel image; step two: sequentially determining a first bright area and a second bright area based on a gray average value and a gray standard deviation of the panel image; the first bright area is an image formed by combining the areas with the gray average value and the gray standard deviation of each area of the panel image being greater than or equal to a preset threshold value; step three: calculating the regional extensibility region Exterm of the second bright region, and determining the bright point defect in the panel image based on the regional extensibility region Exterm; the defect specification detection method, the defect specification detection system and the storage medium can reduce the arrangement complexity of the combination characteristics among the point clusters, reduce the memory resources occupied by calculation and quickly judge; the dependency on the image contrast is reduced for detection, not limited to a certain fixed feature threshold.
Description
Technical Field
The present invention relates to the field of defect detection technologies, and in particular, to a method, a system, and a storage medium for detecting a ZARA defect specification.
Background
In a part of processes from panel production to shipment in the panel industry, for the purposes of improving product quality, saving manpower, reducing cost and the like, a mode of "manual work+machine vision" has been generally adopted for screen quality monitoring, product classification and defect repair. Among which application products of relatively sophisticated machine vision, such as AOI, demura, etc., defect detection and classification in the related art are a great specific gravity, and ZARA defect detection is one of them.
ZARA defects detected in the current industry are represented as a phenomenon of point clusters, and the morphological characteristics of the point clusters comprise oval anchor clusters, small-distance scattered adjacent, tailing gradual change, bright corona at the edge of the point clusters, ultra-large bright points with bright corona and the like. The existing point cluster defect detection technology mainly obtains scattered point clusters through 'image strengthening' processing, then calculates the number of points in the point clusters, the distance between the points and the uniformity of the distribution of the points, respectively defines threshold values by utilizing the number characteristics, and detects 'point cluster defects' on the detected object image. However, when the zapa defect of the panel image is detected, most types cannot be covered only by the number of features, the calculation and analysis processes of the features are complicated, resources are occupied sometimes greatly, and the detection time is long.
CN202211130233.4, "a method for identifying defects in production of a grinding material layer of a photovoltaic grinding wheel" provides a method for identifying defects in production of a grinding material layer of a photovoltaic grinding wheel, which classifies pixels in a detection ring area to obtain a plurality of pixel clusters, calculates the number of pixels, uniformity of distribution and other characteristics of each pixel cluster, and performs feature integration to confirm abrasion level. The scheme is complex to realize in the ZARA defect detection process of the panel image, and has large occupation of computing resources and long detection time.
Disclosure of Invention
Based on the technical problems in the background art, the invention provides a ZARA defect specification detection method, a ZARA defect specification detection system and a ZARA defect specification storage medium, which can reduce the arrangement complexity of combination features among point clusters, reduce memory resources occupied by calculation and rapidly judge; the dependency on the image contrast is reduced for detection, not limited to a certain fixed feature threshold.
The invention provides a ZARA defect specification detection method, which comprises the following steps:
step one: acquiring and intercepting a panel image;
step two: sequentially determining a first bright area and a second bright area based on a gray average value and a gray standard deviation of the panel image; the first bright area is an image formed by combining the gray average value and the gray standard deviation of each area of the panel image with the areas larger than or equal to a preset threshold value, and the second bright area is an image formed by cutting out the image with the size larger than the first bright area and positioning the image;
step three: and calculating the regional extensibility region Exterm of the second bright region, and determining the bright point defect in the panel image based on the regional extensibility region Exterm.
Further, in the second step, the positioning process of the first bright area is as follows:
calculating a minimum value and a maximum value of the gray values of the panel image, and scaling the gray values of the panel image to a range of 0 to 255;
performing Gaussian filter image processing on the panel image;
traversing the panel image by using a Mask with the size of Mask width multiplied by Mask height to calculate the gray average value and the gray standard deviation of each region in the panel image, and merging the regions with the gray average value and the gray standard deviation larger than or equal to a preset threshold value to obtain a first bright region.
Further, in the second step, the screening process of the first bright area after positioning is as follows:
calculating the area characteristic and the Ratio characteristic of the long and short axes of the first bright area;
judging whether the area characteristic belongs to a small area region or not based on the area characteristic of the first bright region;
if the area is small, the bright point defect in the panel image is a point defect;
if the image is not in the small area, intercepting the image with the set size larger than the first bright area as an unoositioned second bright area;
based on the Ratio of the long axis to the short axis of the first bright area, judging whether the Ratio of the long axis to the short axis is smaller than or equal to a preset lower threshold R min Or, whether the Ratio of the long shaft to the short shaft is greater than or equal to a preset upper threshold R max ；
If yes, the bright point defect in the panel image is a line defect;
if not, intercepting an image with a set size larger than the first bright area as an unoositioned second bright area.
Further, in the second step, the positioning process of the second bright area is as follows:
calculating the minimum value and the maximum value of the gray value of the second bright area which is not positioned, and scaling the gray value of the second bright area which is not positioned to the range of 0 to 255;
carrying out Gaussian filtering image processing on the second bright area which is not positioned;
traversing the second unoositioned bright area by using a Mask with the size of Mask width multiplied by Mask height to calculate the gray average value and the gray standard deviation of each area in the second unoositioned bright area, and merging the areas with the gray average value and the gray standard deviation larger than or equal to a preset threshold value to obtain the second bright area.
Further, in step three: before calculating the region extensibility region of the second bright region, screening and intercepting the second bright region, wherein the specific screening and intercepting process is as follows:
deleting the area on the grid in the second bright area, intercepting an image with a set size larger than the second bright area, and detecting a dark area to locate the dark area, wherein the dark area is a dark image formed by combining the gray average value of each area and the area with the gray standard deviation smaller than a preset threshold value;
if the dark image is an annular area and completely contains a bright spot area, the panel image is a Gap defect;
if the dark image is not a ring-shaped region, the region extensibility region of the second bright region is calculated.
Further, the positioning process of the dark area is as follows:
intercepting an image larger than the set size of the second bright area to obtain a dark image, calculating the minimum value and the maximum value of the gray value of the dark image, and scaling the gray value of the dark image to the range of 0 to 255;
performing Gaussian filtering image processing on the dark image;
and traversing the dark image by using a Mask with the size of Mask width multiplied by Mask height to calculate the gray average value and the gray standard deviation of each region in the dark image, and merging the regions with the gray average value and the gray standard deviation smaller than a preset threshold value to obtain the dark region.
Further, in the third step, specifically including:
calculating the region extensibility region of the second bright region;
judging whether the regional extensibility region Exterm is larger than the preset regional extensibility;
if yes, the defect of the panel image is ZARA defect;
if not, the panel image has no defect.
Further, the calculation formula of the region extensibility region is as follows:
RegionExtern＝Area/Ratio
where Ratio represents the Ratio of the length to the short axis of the second bright region, and Area represents the Area of the detection region.
A ZARA defect specification detection system comprises an acquisition module, a region positioning module and a calculation module;
the acquisition module is used for acquiring and intercepting a panel image;
the area positioning module is used for sequentially determining a first bright area and a second bright area based on the gray average value and the gray standard deviation of the panel image; the first bright area is an image formed by combining the gray average value and the gray standard deviation of each area of the panel image with the areas larger than or equal to a preset threshold value, and the second bright area is an image formed by cutting out the image with the size larger than the first bright area and positioning the image;
the calculating module is used for calculating the regional extensibility region Exterm of the second bright region, and determining the bright point defect in the panel image based on the regional extensibility region Exterm.
Intercepting an image with a set size larger than the second bright area to detect a dark area, and positioning the dark area;
a computer readable storage medium having stored thereon a number of programs for being invoked by a processor and performing a zap defect specification detection method as described above.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable storage medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
The ZARA defect specification detection method, system and storage medium provided by the invention have the advantages that: the ZARA defect specification detection method, system and storage medium provided by the structure of the invention realize a lightweight ZARA defect detection scheme, extract and analyze the geometric features and brightness features of the point clusters forming ZARA based on bright point feature detection, solve the ZARA intelligent defect detection task more rapidly and efficiently, and make the ZARA intelligent defect detection task easier to adjust, so that the ZARA intelligent defect detection scheme can be popularized and applied in different gray-scale images of panel images; the complexity of the arrangement of the combination features among the point clusters can be reduced, the memory resources occupied by calculation are reduced, and the judgment is fast; in addition, the dependency on the image contrast can be reduced for detection, the method is not limited to a certain fixed characteristic threshold value, and the wide applicability of the method in the condition of not using gray-scale pictures is enhanced.
Drawings
FIG. 1 is a schematic diagram of the structure of the present invention;
FIG. 2 is a flow chart of an embodiment;
fig. 3 is a bright point defect existing in a panel image, wherein a red portion is a bright point defect.
Detailed Description
In the following detailed description of the present invention, numerous specific details are set forth in order to provide a thorough understanding of the present invention. The invention may be embodied in many other forms than described herein and similarly modified by those skilled in the art without departing from the spirit or scope of the invention, which is therefore not limited to the specific embodiments disclosed below.
ZARA defects in the panel industry are a group of scattered bright spots, and the detection process is often misjudged. In the actual industrial production process, a similar false defect is formed, namely a dot cluster and a fingerprint spot, and the false defect can be a stain, a mechanism component reflection or dust in practice; the real ZARs are often irregularly distributed and of a peculiar shape, such as a trailing bright spot. The image data of the embodiment is an 8-bit single-channel image with gray values of 0-256, and is suitable for the gray-scale picture images with the average gray values of 60, 90, 127 and the like. The specific implementation mode is as follows:
as shown in fig. 1 to 3, the method for detecting the zapa defect specification provided by the invention comprises the following steps:
step one: acquiring and intercepting a panel image;
the panel image can be an image directly acquired through a camera, and the structural image which is not the panel itself exists on the periphery of the acquired image, so that the acquired image is intercepted, the black area of a mechanism outside the panel is removed, and the contrast processing difficulty of ZARA defects is reduced.
Step two: sequentially determining a first bright area and a second bright area based on a gray average value and a gray standard deviation of the panel image; the first bright area is an image formed by combining the gray average value and the gray standard deviation of each area of the panel image with the areas larger than or equal to a preset threshold value, and the second bright area is an image formed by cutting out the image with the size larger than the first bright area and positioning the image;
step three: and calculating the regional extensibility region Exterm of the second bright region, and determining the bright point defect in the panel image based on the regional extensibility region Exterm.
The higher the extensibility, the higher the possibility of tailing bright spots, and the calculation formula of the regional extensibility region is as follows:
RegionExtern＝Area/Ratio
where Ratio represents the Ratio of the length to the short axis of the second bright region, and Area represents the Area of the detection region.
According to the first to third steps, a light-weight ZARA defect detection scheme is realized, on the basis of bright point feature detection, geometric features and brightness features of point clusters forming ZARA are extracted and analyzed, so that ZARA intelligent defect detection tasks are more quickly and efficiently solved, and are easier to adjust, and the ZARA intelligent defect detection scheme can be popularized and applied in different gray-scale images of panel images; the complexity of the arrangement of the combination features among the point clusters can be reduced, the memory resources occupied by calculation are reduced, and the judgment is fast; in addition, the dependency on the image contrast can be reduced for detection, the method is not limited to a certain fixed characteristic threshold value, and the wide applicability of the method in the condition of not using gray-scale pictures is enhanced.
The following is a specific description:
as an embodiment, as shown in fig. 2, a ZARA defect specification detection method, the specific detection method includes steps S1 to S17.
S1: a panel image is acquired.
S2: preprocessing the panel image;
the panel image is cut, the black area of the mechanism outside the panel is removed, and the contrast processing difficulty of ZARA defects is reduced.
S3: based on the panel image, a first bright area is positioned, and the positioning process is specifically as follows:
calculating a minimum value and a maximum value of the gray values of the panel image, and scaling the gray values of the panel image to a range of 0 to 255;
performing Gaussian filter image processing on the panel image;
traversing the panel image by using a Mask with the size of Mask width multiplied by Mask height to calculate the gray average value and the gray standard deviation of each region in the panel image, and merging the regions with the gray average value and the gray standard deviation larger than or equal to a preset threshold value to obtain a first bright region.
S4: calculating the area characteristic and the Ratio characteristic of the long and short axes of the first bright area;
the Ratio of the long axis to the short axis is a parameter characteristic commonly used by those skilled in the art.
S5: judging whether the area characteristic belongs to a small area region or not based on the area characteristic of the first bright region, if so, entering a step S6, and if not, entering a step S9;
wherein the setting of the small Area is set according to the following formula:
Area≤AreaThreah
the area threshold value is obtained by debugging according to the field requirement.
S6: the bright point defect is a point defect.
S7: based on the Ratio of the long axis to the short axis of the first bright area, judging whether the Ratio of the long axis to the short axis is smaller than or equal to a preset lower threshold R min Or, whether the Ratio of the long shaft to the short shaft is greater than or equal to a preset upper threshold R max If yes, the step S8 is carried out, and if not, the step S9 is carried out;
wherein a preset lower threshold R min And a preset upper threshold R max Is set according to the actual implementation of the site.
S8: the bright point defect in the panel image is a line defect.
S9: intercepting an image with a size larger than the first bright area as an unoositioned second bright area, positioning the second bright area, and for the image with the size larger than the first bright area, firstly, the size of the image is generally larger than the width and height of the smallest rectangular area capable of covering the first bright area, and the width difference value (or height difference value) is preferably 4-6 pixel values.
The positioning process of the second bright area is as follows:
calculating the minimum value and the maximum value of the gray value of the second bright area which is not positioned, and scaling the gray value of the second bright area which is not positioned to the range of 0 to 255;
carrying out Gaussian filtering image processing on the second bright area which is not positioned;
traversing the second unoositioned bright area by using a Mask with the size of Mask width multiplied by Mask height to calculate the gray average value and the gray standard deviation of each area in the second unoositioned bright area, and merging the areas with the gray average value and the gray standard deviation larger than or equal to a preset threshold value to obtain the second bright area.
S10: deleting the area on the grid in the second bright area;
the basic form of the area on the grid is represented as unidirectional pixel points and triangular point points, the area on the grid is deleted on the specific row number and column number of the image luminous points, and the area on the grid is used for eliminating the interference of the image display grid.
S11: and intercepting an image with a set size larger than the second bright area to perform dark area detection so as to position the dark area, wherein for the image with the set size larger than the second bright area, the size of the image is generally larger than the width and height of the smallest rectangular area capable of covering the second bright area, and the width difference value (or height difference value) is preferably 4-6 pixel values.
The positioning process of the dark area is as follows:
intercepting an image larger than the set size of the second bright area to obtain a dark image, calculating the minimum value and the maximum value of the gray value of the dark image, and scaling the gray value of the dark image to the range of 0 to 255;
performing Gaussian filtering image processing on the dark image;
and traversing the dark image by using a Mask with the size of Mask width multiplied by Mask height to calculate the gray average value and the gray standard deviation of each region in the dark image, and merging the regions with the gray average value and the gray standard deviation smaller than a preset threshold value to obtain the dark region.
S12: judging whether the dark image is an annular area and completely contains a bright spot area, if so, entering a step S13, and if not, entering a step S14;
in the field Gap type defect, the center of the defect is a dark area or a bright area, in the ZARA type frequent image, the center of the defect is basically a bright area, the periphery of the defect is a dark area, and the defect presents a ring-shaped feature, so if the dark image is not a ring-shaped area, the panel image is not the Gap type defect, and whether the defect is the ZARA defect is continuously judged.
S13: the panel image is Gap defect.
S14: calculating the region extensibility region of the second bright region;
and (3) performing final feature clamping control on the residual region after the Gap detection condition screening of the second bright region by the step S12, and calculating the region extensibility RegionExtern by using the area of the residual region and the Ratio of the long axis to the short axis. The calculation formula is as follows, and the higher the extensibility is, the higher the possibility of tailing bright spots is, as shown in fig. 3.
S15: judging whether the region extensibility is greater than the preset region extensibility, if so, entering a step S17, otherwise, entering a step S16;
s16: the panel image is free of defects.
S17: the defect of the panel image is a zap defect.
S12: calculating the region extensibility region of the second bright region;
and (3) performing final feature clamping control on the residual region after the Gap detection condition screening of the second bright region by the step (S13), and calculating the region extensibility RegionExtern by using the area of the residual region and the Ratio of the long axis to the short axis. The calculation formula is as follows, and the higher the extensibility is, the higher the possibility of tailing bright spots is, as shown in fig. 3.
S13: judging whether the dark image is an annular area and completely contains a bright spot area, if so, entering a step S14, and if not, entering a step S16;
it can be understood that, since the second bright area is an image formed by combining the gray average value and the gray standard deviation of each area of the first bright area with the gray average value and the gray standard deviation of each area being greater than or equal to the preset threshold, the dark image is a dark image formed by combining the gray average value and the gray standard deviation of each area being less than the preset threshold, and obviously the dark image is an image arranged outside the second bright area, if the second bright area is annularly wrapped by the dark area, the second bright area is a false defect with a similar form, so that the detection of the traditional false defect can be performed, and the detection efficiency of the ZARA defect is improved.
In the field Gap type defect, the center of the defect is a dark area or a bright area, in the ZARA type frequent image, the center of the defect is basically a bright area, the periphery of the defect is a dark area, and the defect presents a ring-shaped characteristic, so that if the dark image is not a ring-shaped area, whether the panel image has the ZARA defect is further judged.
S14: the panel image is Gap defect.
S15: judging whether the region extensibility is greater than the preset region extensibility, if so, proceeding to step S17, otherwise, proceeding to step S16.
S16: the panel image is free of defects.
S17: the defect of the panel image is a zap defect.
Based on the steps S1 to S17, the scheme comprises a positioning method of 'brighter' defects such as ZARA defects, and then ZARA defect distinguishing detection is carried out according to ZARA characteristics, and mainly distinguishing the defects from defects such as points, gaps, lines and the like; the method used in the scheme is light and simple, the number of parameters is small, and the scheme is convenient to adjust; meanwhile, the scheme can not limit the image with specific brightness, can basically distinguish different forms of ZARA, and can be applied to different gray-scale images in the panel image defect detection process.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (10)
1. A ZARA defect specification detection method comprises the following steps:
step one: acquiring and intercepting a panel image;
step two: sequentially determining a first bright area and a second bright area based on a gray average value and a gray standard deviation of the panel image; the first bright area is an image formed by combining the gray average value and the gray standard deviation of each area of the panel image with the areas larger than or equal to a preset threshold value, and the second bright area is an image formed by cutting out the image with the size larger than the first bright area and positioning the image;
step three: and calculating the regional extensibility region Exterm of the second bright region, and determining the bright point defect in the panel image based on the regional extensibility region Exterm.
2. The method for detecting a zap defect specification according to claim 1, wherein in step two, the positioning procedure of the first bright area is as follows:
calculating a minimum value and a maximum value of the gray values of the panel image, and scaling the gray values of the panel image to a range of 0 to 255;
performing Gaussian filter image processing on the panel image;
traversing the panel image by using a Mask with the size of Mask width multiplied by Mask height to calculate the gray average value and the gray standard deviation of each region in the panel image, and merging the regions with the gray average value and the gray standard deviation larger than or equal to a preset threshold value to obtain a first bright region.
3. The method according to claim 2, wherein in the second step, the screening process of the first bright area after positioning is as follows:
calculating the area characteristic and the Ratio characteristic of the long and short axes of the first bright area;
judging whether the area characteristic belongs to a small area region or not based on the area characteristic of the first bright region;
if the area is small, the bright point defect in the panel image is a point defect;
if the image is not in the small area, intercepting the image with the set size larger than the first bright area as an unoositioned second bright area;
based on the Ratio of the long axis to the short axis of the first bright area, judging whether the Ratio of the long axis to the short axis is smaller than or equal to a preset lower threshold R min Or, whether the Ratio of the long shaft to the short shaft is greater than or equal to a preset upper threshold R max ；
If yes, the bright point defect in the panel image is a line defect;
if not, intercepting an image with a set size larger than the first bright area as an unoositioned second bright area.
4. A zap defect specification detection method as claimed in claim 3 wherein in step two the location of the second bright region is as follows:
calculating the minimum value and the maximum value of the gray value of the second bright area which is not positioned, and scaling the gray value of the second bright area which is not positioned to the range of 0 to 255;
carrying out Gaussian filtering image processing on the second bright area which is not positioned;
traversing the second unoositioned bright area by using a Mask with the size of Mask width multiplied by Mask height to calculate the gray average value and the gray standard deviation of each area in the second unoositioned bright area, and merging the areas with the gray average value and the gray standard deviation larger than or equal to a preset threshold value to obtain the second bright area.
5. The method for detecting a zap defect specification according to claim 1, wherein in step three: before calculating the region extensibility region of the second bright region, screening and intercepting the second bright region, wherein the specific screening and intercepting process is as follows:
deleting the area on the grid in the second bright area, intercepting an image with a set size larger than the second bright area, and detecting a dark area to locate the dark area, wherein the dark area is a dark image formed by combining the gray average value of each area and the area with the gray standard deviation smaller than a preset threshold value;
if the dark image is an annular area and completely contains a bright spot area, the panel image is a Gap defect;
if the dark image is not a ring-shaped region, the region extensibility region of the second bright region is calculated.
6. The method for detecting the ZARA defect specification according to claim 5, wherein the positioning process of the dark area is as follows:
intercepting an image larger than the set size of the second bright area to obtain a dark image, calculating the minimum value and the maximum value of the gray value of the dark image, and scaling the gray value of the dark image to the range of 0 to 255;
performing Gaussian filtering image processing on the dark image;
and traversing the dark image by using a Mask with the size of Mask width multiplied by Mask height to calculate the gray average value and the gray standard deviation of each region in the dark image, and merging the regions with the gray average value and the gray standard deviation smaller than a preset threshold value to obtain the dark region.
7. The method for detecting a zap defect specification according to claim 5, wherein in step three, the method specifically comprises:
calculating the region extensibility region of the second bright region;
judging whether the regional extensibility region Exterm is larger than the preset regional extensibility;
if yes, the defect of the panel image is ZARA defect;
if not, the panel image has no defect.
8. The method for detecting a ZRA defect specification according to claim 7, wherein the region extensibility region exten is calculated as follows:
RegionExtern＝Area/Ratio
where Ratio represents the Ratio of the length to the short axis of the second bright region, and Area represents the Area of the detection region.
9. A zap defect specification detection system comprising the steps of: the device comprises an acquisition module, a region positioning module and a calculation module;
the acquisition module is used for acquiring and intercepting a panel image;
the area positioning module is used for sequentially determining a first bright area and a second bright area based on the gray average value and the gray standard deviation of the panel image; the first bright area is an image formed by combining the gray average value and the gray standard deviation of each area of the panel image with the areas larger than or equal to a preset threshold value, and the second bright area is an image formed by cutting out the image with the size larger than the first bright area and positioning the image;
the calculating module is used for calculating the regional extensibility region Exterm of the second bright region, and determining the bright point defect in the panel image based on the regional extensibility region Exterm.
10. A computer readable storage medium having stored thereon a number of programs for being called by a processor and performing the zap defect specification detection method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310775791.4A CN116823771A (en) | 2023-06-27 | 2023-06-27 | ZARA defect specification detection method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310775791.4A CN116823771A (en) | 2023-06-27 | 2023-06-27 | ZARA defect specification detection method, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116823771A true CN116823771A (en) | 2023-09-29 |
Family
ID=88123646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310775791.4A Pending CN116823771A (en) | 2023-06-27 | 2023-06-27 | ZARA defect specification detection method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116823771A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117130186A (en) * | 2023-10-25 | 2023-11-28 | 深圳市晶鸿电子有限公司 | LCD display screen flaw defect intelligent detection method |
-
2023
- 2023-06-27 CN CN202310775791.4A patent/CN116823771A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117130186A (en) * | 2023-10-25 | 2023-11-28 | 深圳市晶鸿电子有限公司 | LCD display screen flaw defect intelligent detection method |
| CN117130186B (en) * | 2023-10-25 | 2024-01-05 | 深圳市晶鸿电子有限公司 | LCD display screen flaw defect intelligent detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| Rahaman et al. | Automatic defect detection and classification technique from image: a special case using ceramic tiles | |
| CN113646801B (en) | Defect detection method, device and computer readable storage medium for defect image | |
| US5917957A (en) | Method of and apparatus for processing an image | |
| JP2004294202A (en) | Defect detection method and device of screen | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN109886960A (en) | The method of glass edge defects detection based on machine vision | |
| CN104637067B (en) | A kind of defect inspection method of grain surface | |
| CN116823771A (en) | ZARA defect specification detection method, system and storage medium | |
| CN114881915A (en) | Symmetry-based mobile phone glass cover plate window area defect detection method | |
| CN106228541A (en) | The method and device of screen location in vision-based detection | |
| CN114119591A (en) | Display screen picture quality detection method | |
| CN115424008A (en) | Method and system for detecting light modulation and focusing of laser projector production line | |
| CN114897881A (en) | Crystal grain defect detection method based on edge characteristics | |
| CN113139943B (en) | Method and system for detecting appearance defects of open circular ring workpiece and computer storage medium | |
| Feng et al. | Image processing of the grinding wheel surface | |
| CN113971681A (en) | Edge detection method for belt conveyor in complex environment | |
| CN113780235A (en) | Icon flaw detection method and system | |
| CN111833350A (en) | Machine vision detection method and system | |
| CN106530292A (en) | Strip steel surface defect image rapid identification method based on line scanning camera | |
| JP7469740B2 (en) | Belt inspection system and belt inspection program | |
| CN116309307A (en) | Weld defect detection method and device, readable storage medium and electronic equipment | |
| JPH04238592A (en) | Automatic bundled bar steel tally device | |
| CN114937003A (en) | Multi-type defect detection system and method for glass panel | |
| CN112907510B (en) | Surface defect detection method |
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 |