一种自适应织物疵点图像分割的方法  

An Adaptive Fabric Defect Segmentation Method

作　　者：石美红[1] 付蓉[1] 毛江辉[1] 张旭凤[1] 

机构地区：[1]西安工程大学计算机科学学院,陕西西安710048

出　　处：《东华大学学报（自然科学版）》2007年第6期743-750,共8页Journal of Donghua University(Natural Science)

基　　金：陕西省教育科研项目(05JC13);陕西省科技厅国际合作(2004WK-06)资助项目

摘　　要：由于受到光照、噪声以及组织纹理等因素的影响,使得织物疵点图像分割一直是织物疵点检测研究中的热点和难点问题.针对常见织物疵点大多在相邻纱线上带有纬向或经向的方向性变异的特点,提出了提取织物图像变异度特征及基于此的简化脉冲耦合神经网络(Pulse-Coupled Neural Network,PCNN)的织物图像疵点分割的新方法.实验结果表明,本方法不仅对常见的织物疵点能进行快速、准确地分割,而且具有一定的健壮性.Segmenting fabric defect from a woven fabric image in research of detecting fabric defect has proven to be a difficult task due to the influence of environment （e. g. illumination and noise, etc. ） and various kinds of weave textures. Based on the property of variation with weft or warp direction on its adjacent yarns produced mostly in common fabric defects, this paper proposes methods of the feature of variability degrees extracted from woven fabric images and segmenting fabric defect adaptively based on the feature image by a simplified pulse-coupled neural network （PCNN）. Experimental results show that the proposed method is effective and robust for segmenting common fabric defects.

关 键 词：织物疵点 变异度 脉冲耦合神经网(PCNN) 点火 同步 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]