中国机械工程2011，Vol.22Issue(12)：1402-1405,4.
基于图像处理的钢板表面缺陷支持向量机识别
Steel Surface Defect Recognition Based on Support Vector Machine and Image Processing
摘要
Abstract
Based on machine vision technology a steel plate surface defect detection was discussed. The characteristic values for six kinds of typical steel plate surface defect images were extracted and the dimensions reduced reasonably form 32 to 20. The principles and algorithm of SVM were introduced, and the method to classify the six kinds of steel plate surface defects using SVM was presented. The optimization of important parameters was obtained. The steel surface defect images have been classified with SVM,and then compared with a BP neural network algorithm. The results show that classification of steel strip surface defects based on SVM theory is effective, fast and robust.关键词
钢板表面缺陷；支持向量机；识别与分类；图像处理Key words
steel plate surface defect/support vector machine (SVM)/recognition and classification/image processing分类
信息技术与安全科学引用本文复制引用
汤勃,孔建益,王兴东,陈黎..基于图像处理的钢板表面缺陷支持向量机识别[J].中国机械工程,2011,22(12):1402-1405,4.基金项目
高等学校博士学科点专项科研基金资助项目(20104219110001)；武汉市科技攻关资助项目(200910321100) （20104219110001）
武汉科技大学青年科技骨干培育计划资助项目(2009xz24) （2009xz24）
