CN116309574B - Method, system, equipment and storage medium for detecting panel leakage process defects - Google Patents
Method, system, equipment and storage medium for detecting panel leakage process defects Download PDFInfo
- Publication number
- CN116309574B CN116309574B CN202310565080.4A CN202310565080A CN116309574B CN 116309574 B CN116309574 B CN 116309574B CN 202310565080 A CN202310565080 A CN 202310565080A CN 116309574 B CN116309574 B CN 116309574B
- Authority
- CN
- China
- Prior art keywords
- template
- pixel
- matched
- panel
- total value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- 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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- 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
- G06V10/443—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 by matching or filtering
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G01N2021/8887—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 based on image processing techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The application provides a method, a system, equipment and a storage medium for detecting defects in panel leakage manufacturing process, which relate to the technical field of defect detection and comprise the following steps: acquiring a standard template based on a normal panel image, wherein the standard template comprises periodic elements of a line; acquiring a plurality of templates to be matched based on the panel images to be detected, and screening the templates to be matched based on the standard templates; acquiring a pixel matrix of a standard template based on a path walking mode, and screening the pixel matrix of the template to be matched; and calculating the pixel total value corresponding to the pixel matrix of the standard template and the pixel total value corresponding to the pixel matrix of the template to be matched, and judging whether the panel image to be detected has the missing processing defect or not based on the pixel total value. The application accurately detects the panel missing processing defects based on the template matching and path walking modes, and solves the problems that the panel missing processing defects lack identification characteristics and the existing target detection model is difficult to effectively detect.
Description
Technical Field
The present application relates to the field of defect detection technologies, and in particular, to a method, a system, an apparatus, and a storage medium for detecting a panel leakage process defect.
Background
The panel processing factory can generate a plurality of defects in the panel production process, however, the whole panel product has complex production process flow and long production period, and long time is often required from the base plate to the production and processing, so that the defects generated in each process section need to be monitored at all times, and the defect is prevented from flowing into the next production Cheng Zaocheng to reduce the yield. However, the missing process is one of the defects with higher severity level, and if there is a missing process defect, the panel is directly scrapped.
The traditional missing process defect detection method is to collect images of the panel products through an AOI (Automatic Optical Inspection) instrument, then manually judge the defects of the images, and repair the panel once missing process defects occur. The traditional defect detection relies on an artificial naked eye judgment chart, is easily influenced by personnel experience difference and mental state, so that the misjudgment rate is higher, and the labor cost is relatively higher, so that a plurality of panel factories start to introduce automatic defect detection and classification systems for replacing the artificial defect detection, however, the systems generally adopt a target detection algorithm based on deep learning as a core detection algorithm, the supervised learning algorithm is influenced by the quality of a training set sample, the possible characteristics of the missed process defect are not obvious, the missed process region and the surrounding normal background difference are smaller, and the model is easy to generate missed detection.
Disclosure of Invention
The application provides a method, a system, equipment and a storage medium for detecting panel missing process defects, which solve the problem that missing detection is easy to occur in panel product missing process defect detection.
In a first aspect, an embodiment of the present application provides a method for detecting a defect in a panel leakage process, the method including the following steps:
based on normal panel image P 0 Obtaining a standard template M 0 The standard template M 0 A periodic element comprising a wire;
based on the panel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 And is based on a standard template M 0 For a plurality of templates M to be matched 1 Screening;
standard template M is obtained based on path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 ;
Calculating a pixel matrix F 0 Is the pixel total value L of (2) 0 Pixel matrix F 1 Is the pixel total value L of (2) 1 And is based on the pixel total value L 0 Sum pixel total value L 1 Determining a panel image P to be detected 1 Whether or not there is a leakage processDefects.
In the embodiment, the method and the device accurately detect the missing processing defects based on the template matching and path walking modes, and solve the problem that the missing processing defects lack identification characteristics and the existing target detection model is difficult to effectively detect.
As some optional embodiments of the application, the normal-based panel image P 0 Obtaining a standard template M 0 The flow of (2) is as follows:
for normal panel image P 0 Image contour recognition processing is performed to obtain a standard template M 0 Is a part of the position information of the mobile terminal;
based on standard templates M 0 Image capturing processing is carried out on the position information of the template to obtain an initial template N 0 ;
For the initial template N 0 Performing binarization and edge contour extraction to obtain final standard template M 0 。
As some optional embodiments of the application, the detection is based on the panel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 The flow of (2) is as follows:
panel image P to be detected 1 Binarization processing and edge contour extraction processing are performed, and a panel image P is acquired 1 Is the lower left corner pixel point of (c);
the panel image P to be detected 1 The lower left corner pixel point of (2) is used as the lower left corner point coordinate, and the lower left corner point coordinate is used as the reference point to obtain a standard template M 0 One template M to be matched with the same size 1 ;
Template M to be matched 1 Sequentially shifting one pixel rightward/upward to obtain a plurality of templates M to be matched 1 。
In the above embodiment, the pixel translation is adopted to obtain the template M for later similarity matching 1 Is positioned accurately.
As some optional embodiments of the application, the method is based on a standard template M 0 For a plurality of templates M to be matched 1 The screening procedure was as follows:
sequentially calculating a plurality of templates M to be matched 1 And standard template M 0 Similarity R of (2);
judging whether the similarity R is larger than a matching degree threshold T 0 If so, the corresponding template M to be matched 1 And standard template M 0 Match, and match the corresponding template M to be matched 1 Reserving, otherwise, the corresponding template M to be matched 1 And standard template M 0 Does not match and will correspond to the template M to be matched 1 And (5) removing.
In the above embodiment, the matching degree threshold T 0 For the preset value, sequentially calculating a plurality of templates M to be matched 1 And standard template M 0 If the similarity R of the templates M to be matched 1 And standard template M 0 Is greater than the matching degree threshold T 0 Then the corresponding template M to be matched is extracted by segmentation 1 Wherein, the template M to be matched 1 May be one or more.
As some optional embodiments of the application, the standard template M is acquired based on a path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 The flow of (2) is as follows:
obtaining a standard template M according to a preset path walking route 0 To form a pixel matrix F with respect to the coordinates and pixel values 0 ;
Obtaining a template M to be matched after screening according to a preset path walking route 1 To form a pixel matrix F with respect to the coordinates and pixel values 1 。
In the above embodiment, the pixel matrix F is based on 0 And a pixel matrix F 1 The outline of the line and corresponding coordinate information can be accurately acquired.
As some optional embodiments of the application, the path walking route is set based on the shape and the size of the route corresponding to the panel manufacturing process, and the path walking route is a straight line segment or a curve segment.
As bookApply for some alternative embodiments, calculate the pixel matrix F 0 Is the pixel total value L of (2) 0 Pixel matrix F 1 Is the pixel total value L of (2) 1 And is based on the pixel total value L 0 Sum pixel total value L 1 The process of determining whether the panel image to be detected has a missing process defect is as follows:
for pixel matrix F 0 The pixel values corresponding to all coordinates are added to obtain a total pixel value L 0 ;
For pixel matrix F 1 The pixel values corresponding to all coordinates are added to obtain a total pixel value L 1 ;
Calculating a pixel total value L 0 Sum pixel total value L 1 If the difference is smaller than the leak process threshold T 1 And judging that the panel image to be detected has no missing process defect, and judging that the panel image to be detected has missing process defect if the panel image to be detected has missing process defect.
In the above embodiment, the panel image P to be detected due to the missing process 1 The line of the corresponding position is definitely missing, and the normal panel image P 0 The line of the corresponding position is certainly present, so the pixel total value L of the corresponding position is sequentially acquired based on the path walk mode 0 Sum pixel total value L 1 If the difference value is within the preset range, the corresponding position is proved to have no line missing, namely no missing process defect, otherwise, if the difference value is not within the preset range, the corresponding position is proved to have line missing, namely missing process defect, so that the process position can be accurately detected, but not the whole image is detected, the detection accuracy is higher, and the missing detection condition can not occur.
In a second aspect, the present application provides a panel leakage process defect detection system, the system comprising:
a matching template generation unit based on the normal panel image P 0 Obtaining a standard template M 0 The standard template M 0 A periodic element comprising a wire;
the template generating unit to be matched is based onPanel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 And is based on a standard template M 0 For a plurality of templates M to be matched 1 Screening;
a detection element generation unit for acquiring a standard template M based on a path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 ;
A missing process defect determination unit for calculating a pixel matrix F 0 Is the pixel total value L of (2) 0 Pixel matrix F 1 Is the pixel total value L of (2) 1 And is based on the pixel total value L 0 Sum pixel total value L 1 Determining a panel image P to be detected 1 Whether there is a leakage process defect.
In a third aspect, the present application provides a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor performing the panel leakage process defect detection method.
In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the panel leakage process defect detection method.
The beneficial effects of the application are as follows: the application adopts the template matching and path walking modes to accurately detect the missed processing procedure defects, and solves the problems that the missed processing procedure defects lack identification characteristics and the existing target detection model is difficult to effectively detect.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting defects in a panel leakage process according to an embodiment of the application;
FIG. 2 is a normal panel image according to an embodiment of the present application;
FIG. 3 is a panel image of a drain process according to an embodiment of the application;
FIG. 4 is a comparison graph of path walking of templates to be matched according to an embodiment of the present application;
FIG. 5 is a system block diagram of a panel leakage process defect detection system according to an embodiment of the application.
Detailed Description
In order to better understand the above technical solutions, the following detailed description of the technical solutions of the present application is made by using the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and the embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limiting the technical solutions of the present application, and the technical features of the embodiments and the embodiments of the present application may be combined with each other without conflict.
It should also be appreciated that in the foregoing description of at least one embodiment of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of at least one embodiment of the application. This method of disclosure, however, is not intended to imply that more features than are required by the subject application. Indeed, less than all of the features of a single embodiment disclosed above.
Example 1
Referring to fig. 1, an embodiment of the present application provides a method for detecting a panel missing process defect, which can detect the missing process defect to prevent the missing process defect from missing.
Specifically, the method comprises the following steps:
(1) Based on normal panel image P 0 Obtaining a standard template M 0 The standard template M 0 A periodic element comprising a wire;
in the embodiment of the application, the circuits on the panel product are repeatedly arranged, so the standard template M 0 At least one periodic element of the line, i.e. the standard template M 0 May represent the overall line characteristics of the panel product.
Specifically, the normal-based panel image P 0 Obtaining a standard template M 0 The flow of (2) is as follows:
(1.1) for a normal Panel image P 0 Image contour recognition processing is performed to obtain a standard template M 0 Is a part of the position information of the mobile terminal;
(1.2) Standard template-based M 0 Image capturing processing is carried out on the position information of the template to obtain an initial template N 0 ;
(1.3) for initial template N 0 Performing binarization and edge contour extraction to obtain final standard template M 0 。
(2) Based on the panel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 And is based on a standard template M 0 For a plurality of templates M to be matched 1 Screening;
specifically, based on the panel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 The flow of (2) is as follows:
(2.1) Panel image P to be detected 1 Binarization processing and edge contour extraction processing are performed, and a panel image P is acquired 1 The coordinates of the lower left corner pixel point may be set to (x, y);
(2.2) the Panel image P to be detected 1 The lower left corner pixel point of (2) is used as the lower left corner point coordinate, and the lower left corner point coordinate is used as the reference point to obtain a standard template M 0 One template M to be matched with the same size 1 If standard template M 0 Is l in length and w in width, and matches the template M 1 The coordinates of (a) are represented as [ x, y, x+l, y+w ]];
(2.3) template M to be matched 1 Sequentially shifting one pixel rightward/upward to obtainTaking a plurality of templates M to be matched 1 ;
Specifically, based on standard templates M 0 For a plurality of templates M to be matched 1 The screening procedure was as follows:
(2.4) sequentially calculating a plurality of templates M to be matched 1 And standard template M 0 Similarity R of (2);
(2.5) determining whether the similarity R is greater than the matching degree threshold T 0 If so, the corresponding template M to be matched 1 And standard template M 0 Match, and match the corresponding template M to be matched 1 Reserving, otherwise, the corresponding template M to be matched 1 And standard template M 0 Does not match and will correspond to the template M to be matched 1 Removing; wherein, the matching degree threshold T 0 According to the actual condition, presetting, namely, the larger the similarity R is, the description of the template M to be matched 1 And standard template M 0 The contained line content is approximately similar, so that the positioning of the image is realized.
(3) Standard template M is obtained based on path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 ;
Specifically, a pixel matrix F is acquired 0 And a pixel matrix F 1 The flow of (2) is as follows:
(3.1) acquiring a Standard template M according to a preset Path travel route 0 To form a pixel matrix F with respect to the coordinates and pixel values 0 ;
(3.2) acquiring the template M to be matched after screening according to a preset path walking route 1 To form a pixel matrix F with respect to the coordinates and pixel values 1 ;
The path travel route is set based on the shape and size of the route corresponding to the panel process, the path travel route is a straight line segment or a curve segment, and the path travel route can be set in a plurality of ways, only the pixel total value L corresponding to the plurality of routes is needed 0 Sum pixel total value L 1 And accumulating according to the weights.
(4) Calculating a pixel matrix F 0 Is the pixel total value L of (2) 0 Pixel matrix F 1 Is the pixel total value L of (2) 1 And is based on the pixel total value L 0 Sum pixel total value L 1 Determining a panel image P to be detected 1 Whether a missing process defect exists;
specifically, the flow of missing process defect determination is as follows:
(4.1) pair pixel matrix F 0 The pixel values corresponding to all coordinates are added to obtain a total pixel value L 0 ;
(4.2) pair pixel matrix F 1 The pixel values corresponding to all coordinates are added to obtain a total pixel value L 1 ;
(4.3) calculating the pixel Total value L 0 Sum pixel total value L 1 If the difference is smaller than the leak process threshold T 1 Then the panel image P to be detected is determined 1 If the missing processing defect does not exist, judging that the panel image P to be detected is positive and negative 1 There is a leakage process defect, wherein the leakage process threshold T 1 A value near 0 is typically set;
referring to FIG. 2, a normal image of a panel product is shown, referring to FIG. 3, a to-be-detected image corresponding to a missing process of the product is shown, and a standard template M can be obtained based on FIG. 2 0 Based on fig. 3, a template M to be matched can be obtained 1 Referring to fig. 4, a pixel matrix F is sequentially acquired based on a path walking line (virtual line) 1 And the corresponding pixel total value L 1 If there is a leak process defect, the total value L of the pixels at the path line position 1 Obviously smaller than the total value L of the pixels corresponding to the normal picture 0 Therefore, whether the leakage processing defect exists can be judged through the simple pixel value correspondence;
at the same time, it can also be based on pixel matrix F 0 And a pixel matrix F 1 And performing one-to-one comparison, so that the position information of the defect occurrence of the defect can be obtained in detail.
Example 2
The embodiment of the application provides a method for detecting a panel missing process defect, which can also detect other defects (defects except missing process defects) so as to prevent the problem of missing defect detection.
Specifically, the method comprises the following steps:
(1) Based on normal panel image P 0 Obtaining a standard template M 0 The standard template M 0 A periodic element comprising a wire;
specifically, the normal-based panel image P 0 Obtaining a standard template M 0 The flow of (2) is as follows:
(1.1) for a normal Panel image P 0 Image contour recognition processing is performed to obtain a standard template M 0 Is a part of the position information of the mobile terminal;
(1.2) Standard template-based M 0 Image capturing processing is carried out on the position information of the template to obtain an initial template N 0 ;
(1.3) for initial template N 0 Performing binarization and edge contour extraction to obtain final standard template M 0 。
(2) Based on the panel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 And is based on a standard template M 0 For a plurality of templates M to be matched 1 Screening;
specifically, based on the panel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 The flow of (2) is as follows:
(2.1) Panel image P to be detected 1 Binarization processing and edge contour extraction processing are performed, and a panel image P is acquired 1 Is the lower left corner pixel point of (c);
(2.2) the Panel image P to be detected 1 The lower left corner pixel point of (2) is used as the lower left corner point coordinate, and the lower left corner point coordinate is used as the reference point to obtain a standard template M 0 One template M to be matched with the same size 1 ;
(2.3) template M to be matched 1 Sequentially shifting one pixel rightward/upward to obtain a plurality of templates M to be matched 1 。
Specifically, based on standard templates M 0 For a plurality of templates M to be matched 1 The screening procedure was as follows:
(2.4) sequentially calculating a plurality of templates M to be matched 1 And standard template M 0 Similarity R of (2);
(2.5) determining whether the similarity R is greater than the matching degree threshold T 0 If so, the corresponding template M to be matched 1 And standard template M 0 Match, and match the corresponding template M to be matched 1 Reserving, otherwise, the corresponding template M to be matched 1 And standard template M 0 Does not match and will correspond to the template M to be matched 1 And (5) removing.
(3) Standard template M is obtained based on path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 ;
Specifically, a pixel matrix F is acquired 0 And a pixel matrix F 1 The flow of (2) is as follows:
(3.1) acquiring a Standard template M according to a preset Path travel route 0 To form a pixel matrix F with respect to the coordinates and pixel values 0 ;
(3.2) acquiring the template M to be matched after screening according to a preset path walking route 1 To form a pixel matrix F with respect to the coordinates and pixel values 1 ;
The path walking route is set based on the shape and the size of a route corresponding to the panel manufacturing process, and the path walking route is a straight line segment or a curve segment.
(4) Calculating a pixel matrix F 0 Is the pixel total value L of (2) 0 Pixel matrix F 1 Is the pixel total value L of (2) 1 And is based on the pixel total value L 0 Sum pixel total value L 1 Judging whether the panel image to be detected has a missing processing defect or not;
specifically, the flow of missing process defect determination is as follows:
(4.1) pair pixel matrix F 0 All of them sitThe pixel values corresponding to the labels are added to obtain a total pixel value L 0 ;
(4.2) pair pixel matrix F 1 The pixel values corresponding to all coordinates are added to obtain a total pixel value L 1 ;
(4.3) calculating the pixel Total value L 0 Sum pixel total value L 1 If the difference is greater than the defect threshold T 2 Then the panel image P to be detected is determined 1 There are other defects, wherein the defect threshold T 2 Generally according to actual conditions;
referring to FIG. 2, a normal image of a panel product is shown, referring to FIG. 3, a to-be-detected image corresponding to a missing process of the product is shown, and a standard template M can be obtained based on FIG. 2 0 Based on fig. 3, a template M to be matched can be obtained 1 Referring to fig. 4, a pixel matrix F is sequentially acquired based on a path walking line (virtual line) 1 And the corresponding pixel total value L 1 If there are other defects (defects other than the missing process defect) in the missing process, the image of the defect is certainly present in the corresponding position of the path-walking line, and the pixel total value L of the path-line position 1 Obviously will be greater than the total value L of the pixels corresponding to the normal picture 0 Therefore, whether other defects exist can be judged through simple pixel value correspondence;
at the same time, it can also be based on pixel matrix F 0 And a pixel matrix F 1 And performing one-to-one comparison, so that the position information of the defect occurrence of the defect can be obtained in detail.
Example 3
The application provides a panel leakage process defect detection system, which corresponds to the method of embodiment 1 one by one, referring to fig. 5, and comprises:
a matching template generation unit based on the normal panel image P 0 Obtaining a standard template M 0 The standard template M 0 A periodic element comprising a wire;
the template generating unit to be matched is based on the panel diagram to be detectedImage P 1 Obtaining a plurality of templates M to be matched 1 And is based on a standard template M 0 For a plurality of templates M to be matched 1 Screening;
a detection element generation unit for acquiring a standard template M based on a path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 ;
A missing process defect determination unit for calculating a pixel matrix F 0 Is the pixel total value L of (2) 0 Pixel matrix F 1 Is the pixel total value L of (2) 1 And is based on the pixel total value L 0 Sum pixel total value L 1 Determining a panel image P to be detected 1 Whether there is a leakage process defect.
In the embodiment, the template matching and path walking modes of the application accurately detect the missed process defects, solve the problem that the missed process defects lack identification characteristics and the existing target detection model is difficult to effectively detect, and realize the effective detection of all defect types in the panel production process.
Example 4
The present application provides a computer device, which includes a memory and a processor, where the memory stores a computer program that executes a panel leakage process defect detection method described in embodiment 1 or 2 when the processor is running.
The computer device provided in this embodiment may implement the method described in embodiment 1 or 2, and in order to avoid repetition, a description thereof will be omitted.
Example 5
The present application provides a computer-readable storage medium having a computer program stored thereon, which when executed by a processor, implements a panel leakage process defect detection method as described in embodiment 1 or 2.
The computer readable storage medium provided in this embodiment may implement the method described in embodiment 1 or 2, and will not be described herein again for avoiding repetition.
The processor may be a central processing unit (CPU, central Processing Unit), other general purpose processors, digital signal processors (digital signal processor), application specific integrated circuits (Application Specific Integrated Circuit), off-the-shelf programmable gate arrays (Field programmable gate array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The above embodiments are merely illustrative of the principles of the present application and its effectiveness, and are not intended to limit the application. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the application. Accordingly, it is intended that all equivalent modifications and variations of the application be covered by the claims, which are within the ordinary skill of the art, be within the spirit and scope of the present disclosure.
Claims (8)
1. The method for detecting the panel leakage process defect is characterized by comprising the following steps:
based on normal panel image P 0 Obtaining a standard template M 0 The standard template M 0 A periodic element comprising a wire;
based on the panel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 And is based on a standard template M 0 For a plurality of templates M to be matched 1 Screening;
standard template M is obtained based on path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 ;
Calculating a pixel matrix F 0 Is the pixel total value L of (2) 0 Pixel matrix F 1 Is the pixel total value L of (2) 1 And is based on the pixel total value L 0 Sum pixel total value L 1 Determining a panel image P to be detected 1 Whether or not there is missing Cheng Quexian;
Standard template M is obtained based on path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 The flow of (2) is as follows:
obtaining a standard template M according to a preset path walking route 0 To form a pixel matrix F with respect to the coordinates and pixel values 0 ;
Obtaining a template M to be matched after screening according to a preset path walking route 1 To form a pixel matrix F with respect to the coordinates and pixel values 1 ;
The path walking route is set based on the shape and the size of a route corresponding to the panel manufacturing process, and the path walking route is a straight line segment or a curve segment.
2. The method for detecting a panel leakage process defect according to claim 1, wherein the normal panel image P is based on 0 Obtaining a standard template M 0 The flow of (2) is as follows:
for normal panel image P 0 Image contour recognition processing is performed to obtain a standard template M 0 Is a part of the position information of the mobile terminal;
based on standard templates M 0 Image capturing processing is carried out on the position information of the template to obtain an initial template N 0 ;
For the initial template N 0 Performing binarization and edge contour extraction to obtain final standard template M 0 。
3. The method for detecting a panel leakage process defect according to claim 1, wherein the method is based on a panel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 The flow of (2) is as follows:
panel image P to be detected 1 Binarization processing and edge contour extraction processing are performed, and a panel image P is acquired 1 Is the lower left corner pixel point of (c);
panel image to be detectedP 1 The lower left corner pixel point of (2) is used as the lower left corner point coordinate, and the lower left corner point coordinate is used as the reference point to obtain a standard template M 0 One template M to be matched with the same size 1 ;
Template M to be matched 1 Sequentially shifting one pixel rightward/upward to obtain a plurality of templates M to be matched 1 。
4. The method for detecting a panel leakage process defect according to claim 1, wherein the method is based on a standard template M 0 For a plurality of templates M to be matched 1 The screening procedure was as follows:
sequentially calculating a plurality of templates M to be matched 1 And standard template M 0 Similarity R of (2);
judging whether the similarity R is larger than a matching degree threshold T 0 If so, the corresponding template M to be matched 1 And standard template M 0 Match, and match the corresponding template M to be matched 1 Reserving, otherwise, the corresponding template M to be matched 1 And standard template M 0 Does not match and will correspond to the template M to be matched 1 And (5) removing.
5. The method for detecting a panel leakage process defect according to claim 1, wherein a pixel matrix F is calculated 0 Is the pixel total value L of (2) 0 Pixel matrix F 1 Is the pixel total value L of (2) 1 And is based on the pixel total value L 0 Sum pixel total value L 1 The process of determining whether the panel image to be detected has a missing process defect is as follows:
for pixel matrix F 0 The pixel values corresponding to all coordinates are added to obtain a total pixel value L 0 ;
For pixel matrix F 1 The pixel values corresponding to all coordinates are added to obtain a total pixel value L 1 ;
Calculating a pixel total value L 0 Sum pixel total value L 1 If the difference is smaller than the leak process threshold T 1 Then the panel image P to be detected is determined 1 Is not stored inIn case of missing process defect, if the detected panel image P is positive, the detected panel image P is determined 1 There are leakage process defects.
6. A panel leakage process defect detection system, the system comprising:
a matching template generation unit based on the normal panel image P 0 Obtaining a standard template M 0 The standard template M 0 A periodic element comprising a wire;
a template generating unit to be matched, wherein the template generating unit to be matched is based on a panel image P to be detected 1 Obtaining a plurality of templates M to be matched 1 And is based on a standard template M 0 For a plurality of templates M to be matched 1 Screening;
a detection element generation unit for acquiring a standard template M based on a path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 ;
A missing process defect determination unit for calculating a pixel matrix F 0 Is the pixel total value L of (2) 0 Pixel matrix F 1 Is the pixel total value L of (2) 1 And is based on the pixel total value L 0 Sum pixel total value L 1 Determining a panel image P to be detected 1 Whether a missing process defect exists;
standard template M is obtained based on path walking mode 0 Is a pixel matrix F of (1) 0 Template M to be matched after screening 1 Is a pixel matrix F of (1) 1 The flow of (2) is as follows:
obtaining a standard template M according to a preset path walking route 0 To form a pixel matrix F with respect to the coordinates and pixel values 0 ;
Obtaining a template M to be matched after screening according to a preset path walking route 1 To form a pixel matrix F with respect to the coordinates and pixel values 1 ;
The path walking route is set based on the shape and the size of a route corresponding to the panel manufacturing process, and the path walking route is a straight line segment or a curve segment.
7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized by: the processor, when executing the computer program, implements a panel leakage process defect detection method as defined in any one of claims 1-5.
8. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, the computer program when executed by a processor implementing a panel leakage process defect detection method according to any one of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310565080.4A CN116309574B (en) | 2023-05-19 | 2023-05-19 | Method, system, equipment and storage medium for detecting panel leakage process defects |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310565080.4A CN116309574B (en) | 2023-05-19 | 2023-05-19 | Method, system, equipment and storage medium for detecting panel leakage process defects |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116309574A CN116309574A (en) | 2023-06-23 |
CN116309574B true CN116309574B (en) | 2023-08-18 |
Family
ID=86778315
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310565080.4A Active CN116309574B (en) | 2023-05-19 | 2023-05-19 | Method, system, equipment and storage medium for detecting panel leakage process defects |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116309574B (en) |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008159930A (en) * | 2006-12-25 | 2008-07-10 | Sony Corp | Defect-correcting apparatus and method for correcting defect |
TW201443460A (en) * | 2013-03-21 | 2014-11-16 | Ebara Corp | Inspection device, method for gyrating image data for inspection, display device for inspection, method for judging defects and memory medium in which a display program for inspection is recorded |
CN109738460A (en) * | 2019-01-28 | 2019-05-10 | 西京学院 | A kind of evaluation detection system for civil engineering structure visual defects |
CN109839385A (en) * | 2019-03-04 | 2019-06-04 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of adaptive pcb board defective vision detection and localization and categorizing system |
CN110967851A (en) * | 2019-12-26 | 2020-04-07 | 成都数之联科技有限公司 | Circuit extraction method and system for array image of liquid crystal panel |
CN111862057A (en) * | 2020-07-23 | 2020-10-30 | 中山佳维电子有限公司 | Picture labeling method and device, sensor quality detection method and electronic equipment |
CN111986190A (en) * | 2020-08-28 | 2020-11-24 | 哈尔滨工业大学(深圳) | Printed matter defect detection method and device based on artifact elimination |
CN112964724A (en) * | 2021-02-01 | 2021-06-15 | 苏州百迈半导体技术有限公司 | Multi-target multi-zone visual detection method and system |
CN113608378A (en) * | 2021-10-08 | 2021-11-05 | 深圳市绘晶科技有限公司 | Full-automatic defect detection method and system based on LCD (liquid crystal display) process |
CN113643289A (en) * | 2021-10-13 | 2021-11-12 | 海门市芳华纺织有限公司 | Fabric surface defect detection method and system based on image processing |
CN114047123A (en) * | 2021-10-09 | 2022-02-15 | 江苏芯亿达电子科技有限公司 | Method and system for detecting production defects of integrated board |
CN114926385A (en) * | 2021-02-02 | 2022-08-19 | Tcl科技集团股份有限公司 | Panel defect detection method, storage medium and terminal equipment |
CN115063618A (en) * | 2022-08-17 | 2022-09-16 | 成都数之联科技股份有限公司 | Defect positioning method, system, equipment and medium based on template matching |
CN115290663A (en) * | 2022-09-30 | 2022-11-04 | 南通艾美瑞智能制造有限公司 | Mini LED wafer appearance defect detection method based on optical detection |
CN115330783A (en) * | 2022-10-13 | 2022-11-11 | 启东谷诚不锈钢制品有限公司 | Steel wire rope defect detection method |
CN115375610A (en) * | 2021-05-21 | 2022-11-22 | 深圳中科飞测科技股份有限公司 | Detection method and device, detection equipment and storage medium |
CN115564727A (en) * | 2022-09-30 | 2023-01-03 | 成都数之联科技股份有限公司 | Method and system for detecting abnormal defects of exposure development |
CN115880520A (en) * | 2022-11-14 | 2023-03-31 | 成都数之联科技股份有限公司 | Defect grade classification method and system based on template matching and defect segmentation |
CN115908420A (en) * | 2023-01-10 | 2023-04-04 | 北京阿丘机器人科技有限公司 | Method, device and equipment for detecting defects of printed circuit board and storage medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4988276B2 (en) * | 2006-09-05 | 2012-08-01 | 理想科学工業株式会社 | Recording failure detection method and program |
US9311698B2 (en) * | 2013-01-09 | 2016-04-12 | Kla-Tencor Corp. | Detecting defects on a wafer using template image matching |
CN113545087A (en) * | 2019-03-11 | 2021-10-22 | Oppo广东移动通信有限公司 | Method for determining predicted value, encoder, and computer storage medium |
-
2023
- 2023-05-19 CN CN202310565080.4A patent/CN116309574B/en active Active
Patent Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008159930A (en) * | 2006-12-25 | 2008-07-10 | Sony Corp | Defect-correcting apparatus and method for correcting defect |
TW201443460A (en) * | 2013-03-21 | 2014-11-16 | Ebara Corp | Inspection device, method for gyrating image data for inspection, display device for inspection, method for judging defects and memory medium in which a display program for inspection is recorded |
CN109738460A (en) * | 2019-01-28 | 2019-05-10 | 西京学院 | A kind of evaluation detection system for civil engineering structure visual defects |
CN109839385A (en) * | 2019-03-04 | 2019-06-04 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of adaptive pcb board defective vision detection and localization and categorizing system |
CN110967851A (en) * | 2019-12-26 | 2020-04-07 | 成都数之联科技有限公司 | Circuit extraction method and system for array image of liquid crystal panel |
CN111862057A (en) * | 2020-07-23 | 2020-10-30 | 中山佳维电子有限公司 | Picture labeling method and device, sensor quality detection method and electronic equipment |
CN111986190A (en) * | 2020-08-28 | 2020-11-24 | 哈尔滨工业大学(深圳) | Printed matter defect detection method and device based on artifact elimination |
CN112964724A (en) * | 2021-02-01 | 2021-06-15 | 苏州百迈半导体技术有限公司 | Multi-target multi-zone visual detection method and system |
CN114926385A (en) * | 2021-02-02 | 2022-08-19 | Tcl科技集团股份有限公司 | Panel defect detection method, storage medium and terminal equipment |
CN115375610A (en) * | 2021-05-21 | 2022-11-22 | 深圳中科飞测科技股份有限公司 | Detection method and device, detection equipment and storage medium |
CN113608378A (en) * | 2021-10-08 | 2021-11-05 | 深圳市绘晶科技有限公司 | Full-automatic defect detection method and system based on LCD (liquid crystal display) process |
CN114047123A (en) * | 2021-10-09 | 2022-02-15 | 江苏芯亿达电子科技有限公司 | Method and system for detecting production defects of integrated board |
CN113643289A (en) * | 2021-10-13 | 2021-11-12 | 海门市芳华纺织有限公司 | Fabric surface defect detection method and system based on image processing |
CN115063618A (en) * | 2022-08-17 | 2022-09-16 | 成都数之联科技股份有限公司 | Defect positioning method, system, equipment and medium based on template matching |
CN115290663A (en) * | 2022-09-30 | 2022-11-04 | 南通艾美瑞智能制造有限公司 | Mini LED wafer appearance defect detection method based on optical detection |
CN115564727A (en) * | 2022-09-30 | 2023-01-03 | 成都数之联科技股份有限公司 | Method and system for detecting abnormal defects of exposure development |
CN115330783A (en) * | 2022-10-13 | 2022-11-11 | 启东谷诚不锈钢制品有限公司 | Steel wire rope defect detection method |
CN115880520A (en) * | 2022-11-14 | 2023-03-31 | 成都数之联科技股份有限公司 | Defect grade classification method and system based on template matching and defect segmentation |
CN115908420A (en) * | 2023-01-10 | 2023-04-04 | 北京阿丘机器人科技有限公司 | Method, device and equipment for detecting defects of printed circuit board and storage medium |
Non-Patent Citations (1)
Title |
---|
梁博.基于机器视觉检测PCB板的关键技术研究.《中国优秀硕士学位论文全文数据库 信息科技辑》.2022,(第(2022)11期),I135-78. * |
Also Published As
Publication number | Publication date |
---|---|
CN116309574A (en) | 2023-06-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106920245B (en) | Boundary detection method and device | |
CN111311542A (en) | Product quality detection method and device | |
CN104459421B (en) | Diode polarity detection method and system | |
US11315229B2 (en) | Method for training defect detector | |
CN104021565A (en) | PCB (Printed Circuit Board) layer quantity and lead wire thickness measurement method based on straight-line detection | |
CN113111903A (en) | Intelligent production line monitoring system and monitoring method | |
WO2014103617A1 (en) | Alignment device, defect inspection device, alignment method, and control program | |
CN114299040A (en) | Ceramic tile flaw detection method and device and electronic equipment | |
CN116091503B (en) | Method, device, equipment and medium for discriminating panel foreign matter defects | |
CN113744252A (en) | Method, apparatus, storage medium and program product for marking and detecting defects | |
CN116309574B (en) | Method, system, equipment and storage medium for detecting panel leakage process defects | |
CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
CN113822836A (en) | Method of marking an image | |
CN113870754B (en) | Method and system for judging defects of panel detection electronic signals | |
CN112308061B (en) | License plate character recognition method and device | |
CN110634124A (en) | Method and equipment for area detection | |
JP2011069742A (en) | Defect detector and defect detection method | |
CN109215068B (en) | Image magnification measuring method and device | |
CN110874837A (en) | Automatic defect detection method based on local feature distribution | |
JP2000321038A (en) | Method for detecting fault of pattern | |
CN117495846B (en) | Image detection method, device, electronic equipment and storage medium | |
CN117495857B (en) | Belt tearing edge detection method, system, equipment and medium | |
CN112730427B (en) | Product surface defect detection method and system based on machine vision | |
KR102273585B1 (en) | Method and system for inspecting mura defect in compact camera module | |
Choi et al. | Edge-based text localization and character segmentation algorithms for automatic slab information recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |