基于Gabor滤波器组的织物疵点检测方法  

Scheme for fabric defect detection based on Gabor filters

作　　者：韩润萍[1] 孙苏榕[1] 姜玲[1] 

机构地区：[1]北京服装学院工业设计与信息工程学院,北京100029

出　　处：《计算机工程与应用》2007年第7期211-214,共4页Computer Engineering and Applications

基　　金：北京市教育委员会科技发展计划面上项目(No.KM200510012002)

摘　　要：给出了基于Gabor滤波器组的织物疵点检测方法。在分析Gabor滤波器时频特性的基础上,针对素色坯布织物疵点图像,设计了椭圆形多尺度多方向的Gabor滤波器组,并应用该滤波器组在频域对织物疵点图像进行滤波处理,对滤波后的多幅图像进行融合与分割处理,将疵点从织物背景中分割出来,从而实现了疵点的检测。实验结果证明了该方法的有效性。A scheme for fabric defect detection based on Gabor filters is proposed in this paper.Based on the features of Gabor filters and textured materials with single color,a bank of ellipse-shaped Gabor filters with multi-scale and multi-orientation are designed.The fabric defect image is processed using this filter bank,and filtered sub-images are obtained which characterize the fabric defect in different orientations and scales in the frequency domain.These sub-images are fused in order to reconstruct the defect binary image that segments the defect from the texture background.Experiment results have confirmed the usefulness of this scheme for fabric defect detection.

关 键 词：织物疵点检测 Gabor盛波器 多通道滤波 图像融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]