CN111366582A - Automatic judgment method based on automatic optical detection - Google Patents
Automatic judgment method based on automatic optical detection Download PDFInfo
- Publication number
- CN111366582A CN111366582A CN201811597727.7A CN201811597727A CN111366582A CN 111366582 A CN111366582 A CN 111366582A CN 201811597727 A CN201811597727 A CN 201811597727A CN 111366582 A CN111366582 A CN 111366582A
- Authority
- CN
- China
- Prior art keywords
- defect
- defects
- detection
- detection result
- automatic
- 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
Images
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
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an automatic judgment method based on automatic optical detection, which comprises the following steps: the automatic optical detection system captures images and detects the panel to be detected to generate a detection result; analyzing and classifying the detection result; filtering the non-detection area of the detection result; filtering defects in the detection result through a single rule; performing composite rule filtering on the defects in the detection result, and analyzing the position relevance among the defects; and classifying and summarizing all defects which accord with the rules to generate a final defect detection report, and uploading the final defect detection report to a client storage system. The invention can meet the requirements of users by methods based on automatic optical detection, automatic judgment and the like.
Description
Technical Field
The invention relates to the field of automatic optical detection, in particular to an automatic judgment method based on automatic optical detection.
Background
Under the existing Automatic Optical Inspection (AOI) system, different manufacturer customers need to analyze and judge Inspection result data of the AOI system, and the requirements of the different manufacturer customers are different. In order to meet the requirements of different customers, a universal method and a framework system capable of analyzing the AOI system requirement rules of the customers of different manufacturers are needed, each customer can make the rules according to the requirement of the customer, and then the universal framework analyzes the defects of the panel by applying the rules made by the customer and outputs the corresponding panel grade.
Therefore, those skilled in the art are devoted to develop an automatic judgment method based on AOI, etc. to meet the user's needs.
Disclosure of Invention
In view of the above-mentioned defects in the prior art, the technical problem to be solved by the present invention is to provide an automatic determination method based on automatic optical detection, which meets the user's requirements.
In order to achieve the above purpose, the invention provides an automatic judgment method based on automatic optical detection, comprising the following steps:
1) the automatic optical detection system is used for carrying out image capture and detection on the panel to be detected to generate a detection result;
2) analyzing and classifying the detection result;
3) filtering the non-detection area of the detection result;
4) filtering defects in the detection result through a single rule;
5) performing composite rule filtering on the defects in the detection result, and analyzing the position relevance among the defects;
6) and classifying and summarizing all defects which accord with the rules to generate a final defect detection report, and uploading the final defect detection report to a client storage system.
Preferably, the detection result is analyzed and classified in the step 2), and each defect in the detection result includes the following information: defect type, defect detection picture, defect coordinate, defect area size, defect length and width, defect contrast, defect gray value, defect circularity, defect variance and defect sharpness.
Preferably, the non-detection area in step 3) is filtered to remove the defect when four conditions of the defect type, the defect detection picture, the defect coordinates, the defect length and the defect width of one defect in the detection result are the same as the set values.
Preferably, the single rule in step 4) is filtered by comparing single information of a defect in the detection result with a required value of the information specified by a customer, deleting the defect which does not meet the condition, and naming and encoding the defect which meets the condition according to the customer requirement, wherein the single information of the defect includes defect type, defect detection picture, defect coordinate, defect area size, defect length and width, defect contrast, defect gray value, defect circularity, defect variance, and defect sharpness.
Preferably, the filtering of the composite rule in step 5) is to delete the defect that does not meet the condition by comparing all the defects in the detection result with the composite rule specified by the customer, and name and code the defect that meets the condition according to the customer requirement.
Preferably, when all the defects meeting the rules in the step 6) are classified and summarized, the defect quantity card control filtering, the defect priority card control filtering, the defect duplication removing card control filtering and the defect severity comparing screening are performed, and finally the defects after screening and filtering are obtained to generate a final defect detection report.
The invention has the beneficial effects that: according to the invention, based on automatic optical detection and automatic judgment and other methods, different judgment and other rules are formulated by combining the internal requirements of the clients of each manufacturer, so that the own requirements of the clients of each manufacturer are realized. The invention makes each client formulate rules according to own requirements through a universal framework, and then the universal framework analyzes the defects of the panel by applying the rules formulated by the client and outputs the corresponding panel grade.
Drawings
Fig. 1 is a flowchart of an automatic determination method based on automatic optical detection according to an embodiment of the present invention.
Detailed Description
The invention is further illustrated by the following examples:
as shown in fig. 1, the embodiment of the present invention discloses an automatic judgment method based on automatic optical detection, which includes the following steps:
1) the automatic optical detection system is used for carrying out image capture and detection on the panel to be detected to generate a detection result;
2) analyzing and classifying the detection result;
3) filtering the non-detection area of the detection result;
4) filtering defects in the detection result through a single rule;
5) performing composite rule filtering on the defects in the detection result, and analyzing the position relevance among the defects;
6) and classifying and summarizing all defects which accord with the rules to generate a final defect detection report, and uploading the final defect detection report to a client storage system.
In this embodiment, the detection result is analyzed and classified in the step 2), and each defect in the detection result includes the following information: defect type, defect detection picture, defect coordinate, defect area size, defect length and width, defect contrast, defect gray value, defect circularity, defect variance and defect sharpness.
In this embodiment, the undetected area in step 3) is filtered to remove a defect from the detection result if four conditions of the defect type, the defect detection picture, the defect coordinates, the defect length, and the defect width of the defect are the same as the set values.
In this embodiment, the single rule in step 4) is filtered, by comparing the single information of one defect in the detection result with a required value of the information specified by a customer, the defect that does not meet the condition is deleted, and the defect that meets the condition is named and encoded according to the customer requirement, where the single information of the defect includes a defect type, a defect detection picture, a defect coordinate, a defect area size, a defect length and width, a defect contrast, a defect gray value, a defect circularity, a defect variance, and a defect sharpness.
In this embodiment, the filtering of the composite rule in step 5) is to delete the defect that does not meet the condition by comparing all the defects in the detection result with the composite rule specified by the customer, and name and code the defect that meets the condition according to the customer requirement.
In this embodiment, when all the defects meeting the rules are classified and summarized in step 6), performing defect quantity card control filtering, defect priority card control filtering, defect de-emphasis card control filtering, and defect severity comparison screening, and finally obtaining the defects after screening and filtering, and generating a final defect detection report.
According to the invention, based on automatic optical detection and automatic judgment and other methods, different judgment and other rules are formulated by combining the internal requirements of the clients of each manufacturer, so that the own requirements of the clients of each manufacturer are realized. The invention makes each client formulate rules according to own requirements through a universal framework, and then the universal framework analyzes the defects of the panel by applying the rules formulated by the client and outputs the corresponding panel grade.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (6)
1. An automatic judgment method based on automatic optical detection is characterized in that: the method comprises the following steps:
1) the automatic optical detection system is used for carrying out image capture and detection on the panel to be detected to generate a detection result;
2) analyzing and classifying the detection result;
3) filtering the non-detection area of the detection result;
4) filtering defects in the detection result through a single rule;
5) performing composite rule filtering on the defects in the detection result, and analyzing the position relevance among the defects;
6) and classifying and summarizing all defects which accord with the rules to generate a final defect detection report, and uploading the final defect detection report to a client storage system.
2. The automatic judging method for defects of different panels based on the automatic optical detection system according to claim 1, characterized in that: analyzing and classifying the detection result in the step 2), wherein each defect in the detection result comprises the following information: defect type, defect detection picture, defect coordinate, defect area size, defect length and width, defect contrast, defect gray value, defect circularity, defect variance and defect sharpness.
3. The automatic judging method for defects of different panels based on the automatic optical detection system according to claim 2, characterized in that: and filtering the undetected area in the step 3) to remove the defect when four conditions of the defect type, the defect detection picture, the defect coordinate, the defect length and the defect width of one defect in the detection result are the same as set values.
4. The automatic judging method for defects of different panels based on the automatic optical detection system according to claim 2, characterized in that: and the step 4) of filtering a single rule includes comparing single information of a defect in the detection result with a required value of the information specified by a customer, deleting the defect which does not meet the condition, naming and encoding the defect which meets the condition according to the customer requirement, wherein the single information of the defect comprises defect type, defect detection picture, defect coordinate, defect area size, defect length and width, defect contrast, defect gray value, defect circularity, defect variance and defect sharpness.
5. The automatic judging method for defects of different panels based on the automatic optical detection system according to claim 2, characterized in that: and in the step 5), the composite rule filtering is to delete the defects which do not meet the conditions by comparing all the defects in the detection result with the composite rule specified by the customer, and name and code the defects which meet the conditions according to the requirements of the customer.
6. The automatic judging method for defects of different panels based on the automatic optical detection system according to claim 2, characterized in that: and 6) classifying and summarizing all the defects meeting the rules, performing defect quantity card control filtering, defect priority card control filtering, defect de-weight card control filtering and defect severity comparison screening, finally obtaining the screened and filtered defects, and generating a final defect detection report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811597727.7A CN111366582A (en) | 2018-12-26 | 2018-12-26 | Automatic judgment method based on automatic optical detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811597727.7A CN111366582A (en) | 2018-12-26 | 2018-12-26 | Automatic judgment method based on automatic optical detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111366582A true CN111366582A (en) | 2020-07-03 |
Family
ID=71209052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811597727.7A Pending CN111366582A (en) | 2018-12-26 | 2018-12-26 | Automatic judgment method based on automatic optical detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111366582A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112327524A (en) * | 2020-11-13 | 2021-02-05 | Tcl华星光电技术有限公司 | Method and device for inspecting substrate film defect |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107561737A (en) * | 2017-08-21 | 2018-01-09 | 武汉精测电子技术股份有限公司 | A kind of method, apparatus and instrument of AOI system IPC parameter adjust automaticallies |
| CN107843599A (en) * | 2017-10-24 | 2018-03-27 | 武汉精测电子集团股份有限公司 | The methods of a kind of panel detection based on AOI is sentenced and device |
| CN108827970A (en) * | 2018-03-28 | 2018-11-16 | 武汉精测电子集团股份有限公司 | Adaptation different panels defect based on AOI system the methods of sentences automatically and system |
-
2018
- 2018-12-26 CN CN201811597727.7A patent/CN111366582A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107561737A (en) * | 2017-08-21 | 2018-01-09 | 武汉精测电子技术股份有限公司 | A kind of method, apparatus and instrument of AOI system IPC parameter adjust automaticallies |
| CN107843599A (en) * | 2017-10-24 | 2018-03-27 | 武汉精测电子集团股份有限公司 | The methods of a kind of panel detection based on AOI is sentenced and device |
| CN108827970A (en) * | 2018-03-28 | 2018-11-16 | 武汉精测电子集团股份有限公司 | Adaptation different panels defect based on AOI system the methods of sentences automatically and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112327524A (en) * | 2020-11-13 | 2021-02-05 | Tcl华星光电技术有限公司 | Method and device for inspecting substrate film defect |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108827970B (en) | AOI system-based method and system for automatically judging defects of different panels | |
| CN113095438B (en) | Wafer defect classification method, device and system thereof, electronic equipment and storage medium | |
| KR101869895B1 (en) | Object recognition server and object recognition system and object recognition method based on deep learning | |
| CN112036755B (en) | Supervision method and system for quality detection of building engineering | |
| US10726535B2 (en) | Automatically generating image datasets for use in image recognition and detection | |
| US11397974B2 (en) | Method and system for assessing quality of commodities | |
| CN113282778A (en) | Quality abnormity recording method, device, AR equipment, system and medium | |
| CN114862832A (en) | Method, device and equipment for optimizing defect detection model and storage medium | |
| CN113284094A (en) | Method, device, storage medium and equipment for acquiring defect information of glass substrate | |
| CN110895811B (en) | Image tampering detection method and device | |
| Nawaz et al. | Single and multiple regions duplication detections in digital images with applications in image forensic | |
| WO2023045038A1 (en) | Cloud-fused product sorting system and method | |
| CN111366582A (en) | Automatic judgment method based on automatic optical detection | |
| CN113486856A (en) | Driver irregular behavior detection method based on semantic segmentation and convolutional neural network | |
| CN111738991A (en) | Method for creating digital ray detection model of weld defects | |
| KR20200124887A (en) | Method and Apparatus for Creating Labeling Model with Data Programming | |
| KR102342495B1 (en) | Method and Apparatus for Creating Labeling Model with Data Programming | |
| CN114897801A (en) | AOI defect detection method, device and equipment and computer medium | |
| CA2997335C (en) | Automatically generating image datasets for use in image recognition and detection | |
| CN111707677A (en) | PCB appearance detection method and device | |
| CN113034337B (en) | Image detection method and related device | |
| CN112905812B (en) | Media file auditing method and system | |
| CN113205110B (en) | Method for establishing panel defect classification model and panel defect classification method | |
| CN116305247B (en) | Sensitive information detection method and system for process data of vehicle-mounted application software | |
| CN114529784B (en) | Trademark infringement analysis method and system for E-commerce data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 523000 Building 1, No.8, Guangming industrial 1st Road, Dongcheng Street, Dongguan City, Guangdong Province Applicant after: Guangdong Jiyang Vision Technology Co.,Ltd. Address before: 523000 C District, building A, Dongting street, Guangming community, Dongguan, Guangdong. Applicant before: DONGGUAN JIYANG AUTOMATION SCIENCE & TECHNOLOGY Co.,Ltd. |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200703 |