首页 | 本学科首页   官方微博 | 高级检索  
     

基于纹理结构分析的织物疵点检测方法
引用本文:祝双武,郝重阳,李鹏阳,齐华.基于纹理结构分析的织物疵点检测方法[J].计算机应用,2008,28(3):647-649.
作者姓名:祝双武  郝重阳  李鹏阳  齐华
作者单位:西北工业大学,电子信息学院,西安,710072;西安工程大学,纺织与材料学院,西安,710048;西北工业大学,电子信息学院,西安,710072
基金项目:陕西省教育厅产业化重点项目 , 西北工业大学校科研和校改项目
摘    要:提出了一种新的基于纹理结构分析的织物疵点检测方法,首先根据规则纹理的特点,利用自相关函数计算纹理基元模板,并通过计算每个纹理基元与基元模板的差来进行疵点区域的增强。然后通过计算纹理图像的局部不平整度来定位疵点,并采用Otsu方法自动获取阈值进行图像分割,从而实现织物疵点的检测。最后通过对不同织物疵点图像检测分割实验证明了算法的有效性和鲁棒性。

关 键 词:纹理基元  织物检测  不平整度  疵点分割
文章编号:1001-9081(2008)03-0647-03
收稿时间:2007-10-09
修稿时间:2007-12-06

Fabric defect detection method based on texture structure analysis
ZHU Shuang-wu,HAO Chong-yang,LI Peng-yang,QI Hua.Fabric defect detection method based on texture structure analysis[J].journal of Computer Applications,2008,28(3):647-649.
Authors:ZHU Shuang-wu  HAO Chong-yang  LI Peng-yang  QI Hua
Affiliation:ZHU Shuang-wu1,2,HAO Chong-yang1,LI Peng-yang1,QI Hua1(1.College of Electronic Information,Northwestern Polythenical University,Xi'an Shaanxi 710072,China,2.College of Textile , material,Xi'an Polytechnic University,Xi'an Shaanxi 710048,China)
Abstract:A new fabric defect segmentation was proposed based on texture structure analysis in this paper. Firstly in accordance with the characteristics of the well-regulated texture, texture primitive template was calculated using auto-correlation function and defect image was enhanced using difference between each texture primitive and primitive template. Secondly local roughness of texture image was calculated to locate defect, and defect image was segmented using threshold value gained according to Otsu's approach to detect fabric defect. Lastly validity and robustness of this approach is proved by different fabric defect image segmentation in our experiment.
Keywords:texture primitive  fabric inspection  roughness  defect segmentation
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》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