We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基于机器视觉的接线端子缺陷检测算法.
- Authors
赵久强; 曾豪辉; 冯毅萍; 曹峥; 仲玉芳
- Abstract
Terminal blocks are commonly used as circuit connection components in industrial production, which determines the safety and reliability of electronic system. Taking the commonly used spring-type straight plug terminals as an example, the defects are defined and classified, and the defect detection algorithm for its brass conductive strips and high-strength springs is designed in a targeted manner. Firstly, the image is preprocessed and corrected, and the positioning reference fitting and pose correction algorithms are designed to normalize the morphology. Then the area matching based on quadtree fractal and the fine feature detection based on random forest are designed respectively, to achieve the detection of different categories of defects. The experimental results show that the detection accuracy of the conductive strip in the terminal is almost 100%, and the accuracy of the defect in the high-strength spring is more than 98%. The detection accuracy is robust to noise, which can meet the needs of actual industrial production.
- Subjects
ELECTRONIC systems; RELIABILITY in engineering; BRASS; ALGORITHMS; NOISE; RANDOM forest algorithms
- Publication
Experimental Technology & Management, 2022, Vol 39, Issue 11, p40
- ISSN
1002-4956
- Publication type
Article
- DOI
10.16791/j.cnki.sjg.2022.11.008