基于Gabor滤波器的布匹瑕疵自动检测方法

被引:12
作者
肖乐
朱玉文
丁丽宏
刘万春
机构
[1] 北京理工大学计算机科学与工程系
[2] 北京理工大学计算机科学与工程系 北京 
[3] 北京 
关键词
Gabor滤波; 瑕疵检测; 图像融合;
D O I
10.15918/j.tbit1001-0645.2002.06.015
中图分类号
TS101.97 [];
学科分类号
摘要
给出一种基于多通道Gabor滤波技术实现高速实时布匹瑕疵检测方法.在多分辨率和多方向上分别对图像进行Gabor滤波,建立金字塔图像表示结构,并对滤波后的多幅图像进行融合与重建,把瑕疵区域从布匹背景中提取出来,从而实现对布匹瑕疵的实时检测.实验表明,这种方法的检测准确率可达到95%,而且具有计算量小、稳定性好等优点.
引用
收藏
页码:718 / 721
页数:4
相关论文
共 8 条
  • [1] Performance evaluation for four classes of textural features. Ohanian P,Dubes R. Pattern Recognition . 1992
  • [2] Detection of local defects in textile webs using Gabor filters. Escofet J,Navarro R. Proceedings of SPIE the International Society for Optical Engineering . 1996
  • [3] Defect detection in textured materials using Gabor filters. Kumar A,Pang G. Proceedings of the IEEE . 2000
  • [4] Automatic visual inspection and flaw detection in textile materials: Past ,present and future. Bennamoun M,Bodnarova A. IEEE Transactions on Systems Man and Cybernetics . 1998
  • [5] Fabric defect detection by Fourier analysis. Chan Chiho,Pang G. Proceedings of the IEEE . 1999
  • [6] Efficient spatial -domain implementation of a multiscale image representation based on Gabor functions. Nestares O,Navarro R. Joumal of Electronic Imaging . 1998
  • [7] Optimal Gabor filters for texture segmentation. Dunn D,Higgins W E. IEEE Transactions on Image Processing . 1995
  • [8] Automatic quality control of textile webs by image processing. Millan M,Escofet J,Abril H. Proceedings of SPIE the International Society for Optical Engineering . 1998