Canny算子在织物疵点检测中的应用  

Application of Canny Operator to Textile Defects Inspection

作　　者：姜玲[1] 韩润萍[1] 袁晔[1] 郑有增[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：《北京服装学院学报（自然科学版）》2005年第4期57-63,共7页Journal of Beijing Institute of Fashion Technology：Natural Science Edition

摘　　要：在分析斜纹织物纹理结构规律性的基础上,运用Canny算子对织物疵点图像进行了边缘检测,获得了织物疵点二值图像,再由灰度统计的方法生成投影图,获取织物图像的特征波形,并通过阈值过滤,将疵点定位,从而正确检测织物疵点.在Visual C++6.0环境下编程并调用Matlab6.5图像处理函数实现了本算法.Based on the analysis of texture feature of twill materials, the Canny operator was used in the edge detection of fabric samples with defects, in order to obtain the segmented binarized image. Then the horizontal and vertical projection signals were gotten by applying gray-level statistical means to the binarized image, and the feature waves of fabric image could be obtained. With the threshold filtration of the feature waves, fabric defects areas could be located precisely, so the fabric defects could be recognized correctly. The algorithm mentioned above could be realized by using VC ＋ ＋ 6.0 code and the corresponding image processing functions of Matlab 6.5.

关 键 词：织物疵点 边缘检测 CANNY算子 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]