A New Fast Border Search Algorithm and Its Expansion
Because of high real-time requirement for an on-line surface inspection system, traditional algorithms cannot meet the requirement. According to border search theory, a new fast border-detection algorithm named Local Border Search Algorithm (LBSA) was presented here, and it can detect border of cold rolled strips as 10 times fast as traditional Gray Level Gradient Threshold Algorithm (GLGTA). However it is still short in some aspects and makes the algorithm can be only used in border searching of strips. In order to overcome shortages of the algorithm, it is improved and expanded in the paper, and after the expansion of Local Border Search Algorithm, it can be used to detect defects of cold rolled strips, and experimental results show that the speed is about 10 times faster and more accurate in defect detection than traditional defect detection algorithm. Therefore, it is suitable to be used in real-time detection occasions.
Border Search Cold Rolled Strip On-line Surface Inspection Image Processing Defect Detection
Haichao Zhang Guifang Wu Xiuming Sun Jinwu Xu Jinwu Xu
Huazhong University of Science & Technology Wuhan, 430074, China Electronic Information Engineering College Henan University of Science & Technology Luoyang, Henan P School of Mechanical Engineering University of Science & Technology Beijing Beijing, 100083, China
国际会议
2007 IEEE International Conference on Automation and Lofistics
山东济南
英文
2007-08-18（万方平台首次上网日期，不代表论文的发表时间）