基于小波变换和形态学的织物疵点边缘检测  

Edge Detection of Fabric Defect Based on Wavelet Transform and Mathematical Morphology

作　　者：胡艳[1] 张瑞林[1] 

机构地区：[1]浙江理工大学软件工程研究所,浙江杭州310018

出　　处：《测试技术学报》2009年第2期173-177,共5页Journal of Test and Measurement Technology

基　　金：浙江省自然科学基金资助项目(ZJ602014)

摘　　要：为了精确确定织物疵点边缘,提出了一种基于小波变换和形态学的织物疵点边缘检测方法.在利用形态学实现疵点检测后,对其进行小波分解,用小波模极大值法和基于数学形态学的算法分别提取高低频子图像的疵点边缘,采用合理的融合规则将两个边缘图像进行融合.实验结果表明,该算法能有效地抑制噪声,且边缘清晰、准确,效果优于经典的边缘检测算法,具有可行性和有效性.In order to detect the edges of fabric defect precisely, an edge detection method based on wavelet transform and mathematical morphology is presented. The method utilizes the morphology to realize the defect detection, and decomposes the image using wavelet transform, then uses the modulus maximum of the wavelet transform and the algorithm based on mathematical morphology to extract the edges in high-frequency and low-frequency sub-image. Finally, the method adopts the reasonable fusion rule to fuse the two edge images. Experimental results show that the algorithm can effectively suppress noise, the edges are clear and accurate, and this method is effective than the classical edge detection algorithm.

关 键 词：边缘检测 织物疵点 小波变换 数学形态学 图像融合 

分 类 号：TS101.1[轻工技术与工程—纺织工程]