首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于神经网络的带钢表面孔洞检测系统研究
引用本文:赵松青,王敏,黄心汉,李炜,伍翼.基于神经网络的带钢表面孔洞检测系统研究[J].华中科技大学学报(自然科学版),2004(Z1).
作者姓名:赵松青  王敏  黄心汉  李炜  伍翼
作者单位:华中科技大学控制科学与工程系 华中科技大学控制科学与工程系 湖北武汉 湖北武汉
摘    要:简要介绍了带钢表面孔洞实时检测中的图像处理系统 ,提出了一种应用边缘检测和聚类分析的图像分割算法对带钢表面孔洞进行准确快速的分割 ,同时采用改进的BP神经网络分类器对孔洞进行分类与识别 ,实验结果表明 ,该带钢表面孔洞实时检测系统具有较高的精度和较快的速度 .

关 键 词:带钢缺陷  边缘检测  图像分割  特征提取  BP神经网络

Research on inspection system of steel surface hole based on neural network
Zhao Songqing Wang Min Huang Xinhan Li Wei Wu Yi Postgraduate, Dept. of Control Science & Engineering,Huazhong Univ. of Sci. & Tech.,Wuhan ,China..Research on inspection system of steel surface hole based on neural network[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,2004(Z1).
Authors:Zhao Songqing Wang Min Huang Xinhan Li Wei Wu Yi Postgraduate  Dept of Control Science & Engineering  Huazhong Univ of Sci & Tech  Wuhan  China
Institution:Zhao Songqing Wang Min Huang Xinhan Li Wei Wu Yi Postgraduate, Dept. of Control Science & Engineering,Huazhong Univ. of Sci. & Tech.,Wuhan 430074,China.
Abstract:This paper briefly introduces the image processing system in the real-time inspection of steel surface hole, also proposes an algorithm of image segmentation of applying edge detection and cluster analysis to accurately and fast segment the steel surface holes, and classifies and recognizes the holes applying the improved BP Neural Network classifier. The experiment result shows that this real-time inspection system of steel surface hole possesses the high precision and fast speed.
Keywords:steel defect  edge detection  image segmentation  feature extraction  BP neural network
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号