Detection method, system and cloud platform for photoresist defects based on image recognition
By analyzing photoresist image data and building a defect detection model, the problems of insufficient accuracy and automation of defect detection in the photolithography process are solved, and efficient defect identification and quality control are achieved.
CN120259755BActive Publication Date: 2025-09-05XINJITECH (BEIJING) ELECTRONIC NEW MATERIALS CO LTD
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202510335458.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-20
- Publication Date
- 2025-09-05
- Estimated Expiration
- 2045-03-20
AI Technical Summary
Technical Problem
The existing technology for defect detection in the lithography process has problems such as low recognition accuracy, insufficient automation, and limited real-time lithography image processing capabilities.
Method used
By analyzing the photoresist image data, determining the category of lithography data and category labels, building a defect detection model, and combining artificial intelligence and computer vision technology, defect detection of real-time lithography images can be achieved.
Benefits of technology
It improves the accuracy and efficiency of defect identification in the lithography process, reduces manual intervention, and improves production efficiency and product quality.
✦ Generated by Eureka AI based on patent content.
Abstract
The present invention relates to the field of image processing technology, and specifically discloses a method, system, and cloud platform for detecting photoresist defects based on image recognition. The method comprises: S1: acquiring target image data of multiple target images based on photolithography within a specified time period, and acquiring photoresist image data of all target images; S2: determining multiple categories of photolithography data and category labels for each category of photolithography data; S3: determining a first defect fitting matrix for each target image in the category photolithography data, and determining a second defect fitting matrix for each category label; S4: constructing a defect detection model for each category label; S5: acquiring a real-time photolithography image to be detected and determining defect data. By combining artificial intelligence and computer vision technology and utilizing automated defect fitting and classification methods, the accuracy and efficiency of defect recognition in the photolithography process are improved, the degree of automation of defect detection is improved, and production efficiency and product quality are improved.
Need to check novelty before this filing date? Find Prior Art