首页 | 本学科首页   官方微博 | 高级检索  
     

基于独立成分分析的冷轧带钢表面缺陷识别
引用本文:段志娟,周新星,陈分雄,孙林.基于独立成分分析的冷轧带钢表面缺陷识别[J].钢铁研究学报,2011,23(10):63-67.
作者姓名:段志娟  周新星  陈分雄  孙林
作者单位:1. 中国地质大学武汉机械与电子信息学院,湖北武汉,430074
2. 中国地质大学武汉地球物理与空间信息学院,湖北武汉,430074
3. 武汉钢铁集团公司,湖北武汉,430083
基金项目:湖北省自然科学基金资助项目(2009CDA146)
摘    要:为了提高冷轧带钢表面缺陷识别率,提出基于独立成分分析(ICA)的缺陷图像特征提取方法。通过ICA建立缺陷图像的统计生成模型,从缺陷库中自适应地估计ICA基向量,将缺陷图像向基向量张成的空间投影,从而将图像变换到ICA域,图像在ICA域内的表示即为相应的特征向量。这种特征元素之间统计独立,是图像的稀疏编码。试验表明,本方...

关 键 词:带钢表面缺陷  独立成分分析  稀疏编码  特征提取  缺陷识别

Recognition Based on Independent Component Analysis for Surface Defects of Cold Strips
DUAN Zhi-juan,ZHOU Xin-xing,CHEN Fen-xiong,SUN Lin .Faculty of Mechanical , Electronic Information,China University of Geosciences,Wuhan ,Hubei,China.Recognition Based on Independent Component Analysis for Surface Defects of Cold Strips[J].Journal of Iron and Steel Research,2011,23(10):63-67.
Authors:DUAN Zhi-juan  ZHOU Xin-xing  CHEN Fen-xiong  SUN Lin [Faculty of Mechanical  Electronic Information  China University of Geosciences  Wuhan  Hubei  China
Affiliation:1. Faculty of Mechanical and Electronic Information, China University of Geosciences Wuhan, Wuhan 430074,Hubei, China ;2. Institute of Geophysics and Geomatics, China University of Geosciences Wuhan, Wuhan430074, Hubei, China ;3. Wuhan Iron and Steel Group Corporation, Wuhan 430083, Hubei, China
Abstract:In order to improve the recognition rate of cold rolled strip surface defects,a new method of feature extraction was investigated for defect images based on Independent Component Analysis(ICA).Base vectors were estimated adaptively from the defect library using the statistics generation model established by ICA.Defect image were transformed to ICA domain through projecting to the space spanned by base vectors.The coefficients in ICA domain were defect's feature vector,which were statistically independent an...
Keywords:strip surface defects  independent component analysis(ICA)  sparse coding  feature extraction  defect recognition  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《钢铁研究学报》浏览原始摘要信息
点击此处可从《钢铁研究学报》下载全文
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