基于灰度分布梯度的织物疵点检测算法  

Algorithm of fabric defect inspection based on gray-scale distributed gradient

作　　者：吴军 WU Jun(College of Information&Business,Zhongyuan University of Technology,Zhengzhou,Henan 451191,China)

机构地区：[1]中原工学院信息商务学院,河南郑州451191

出　　处：《毛纺科技》2018年第4期76-80,共5页Wool Textile Journal

基　　金：2014年度河南省重点科技攻关(142102210524)

摘　　要：针对织物疵点检测算法实用性差的问题,提出一种基于灰度分布梯度检测算法,通过对纹理织物相邻像素灰度差异和单位距离的商来判断纹理是否异变。在对灰度试样提高对比度和二值化图像预处理,并根据织物组织结构确定检测窗口的基础上,把试样分解成经向和纬向2个子图并得到各自方向的能量统计值,从中提取跃迁比等4种特征值,综合各类疵点对方向特征值的不同敏感程度检测出疵点。该算法简便,实时性好,特别适合方向性疵点及块状疵点的检测。For the problem of fabric defect detection algorithm poor practicability,an algorithm based on the gray-scale distribution gradient is proposed,when the ratio of adjacent pixels gray scale difference and unit distance is not normal,defects is found.First,the gray image is improved contrast and binarization,determined the detection window according to the fabric structure.The image is decomposed into two sub-images to warp and weft and then getting energy statistics from the direction,four kinds of character values are extracted such as transition-rate,and then varied defects are found according to different sensitivity.It's been verified that it possesses simply,real-time advantage,especially suitable for directional defect and block type of defect of statistical characteristics.

关 键 词：织物疵点检测 自相关 灰度分布梯度 跃迁比 

分 类 号：TS101.9[轻工技术与工程—纺织工程]