摘要
钢板作为制造业发展的基础,表面缺陷检测具有重要的研究意义和应用价值。本文总结了基于传统机器视觉的钢板表面缺陷检测算法的优缺点及应用,分别从缺陷分类、目标检测和缺陷分割三个方面介绍深度学习技术在钢板表面缺陷检测领域的应用,总结目前钢板表面缺陷检测存在的短板与不足,并对未来的研究趋势进行展望。
As the basis of the manufacturing industry development,the research on surface defect detection of steel plate has important significance and application value. In this paper,the advantages,disadvantages,and applications of steel plate surface defect detection algorithms based on traditional machine vision are summarized. The application of deep learning technology in the field of steel plate surface defect detection is introduced from three aspects:defect classification,target detection,and defect segmentation. The shortcomings of the current steel plate surface defect detection technologies are summarized,and the future research trends are prospected.
作者
李雪露
杨永辉
储茂祥
LI Xuelu;YANG Yonghui;CHU Maoxiang(School of Electronics and Information Engineering,University of Science and Technology Liaoning,Anshan 114051,China)
出处
《辽宁科技大学学报》
CAS
2022年第3期193-202,共10页
Journal of University of Science and Technology Liaoning
基金
国家自然科学基金(21978123)
辽宁省高等学校基本科研项目(2020LNZD06)。
关键词
缺陷检测
机器视觉
缺陷分类
目标检测
缺陷分割
深度学习
defect detection
machine vision
defect classification
target detection
defect segmentation
deep learning
