首页 | 本学科首页   官方微博 | 高级检索  
     

基于数学形态学的织物疵点检测方法
引用本文:王锋,焦国太,杜烨.基于数学形态学的织物疵点检测方法[J].测试技术学报,2007,21(6):515-518.
作者姓名:王锋  焦国太  杜烨
作者单位:中北大学,机电工程学院,山西,太原,030051;中北大学,机电工程学院,山西,太原,030051;中北大学,机电工程学院,山西,太原,030051
摘    要:针对织物中普遍存在的破洞、断经和缺纬三类疵点,提出了一种基于数学形态学的织物疵点检测方法.首先运用自相关函数和快速傅立叶变换找出织物经纬结构上的重复单元,然后以这些重复单元作为依据,运用形态处理学中的腐蚀背景法和膨胀目标法确定图像中的疵点信息,通过不同疵点样本对该方法进行仿真实验.运用该方法可使疵点识别率达到97%.实验结果证明该检测方法是可行的.

关 键 词:织物疵点  形态学  检测  仿真  识别率
文章编号:1671-7449(2007)06-0515-04
收稿时间:2006-11-07
修稿时间:2006年11月7日

Method of Fabric Defects Detection Based on Mathematical Morphology
WANG Feng,JIAO Guotai,DU Ye.Method of Fabric Defects Detection Based on Mathematical Morphology[J].Journal of Test and Measurement Techol,2007,21(6):515-518.
Authors:WANG Feng  JIAO Guotai  DU Ye
Affiliation:Institude of Mechatronic Engineering, North University of China, Taiyuan 030051, China
Abstract:In this paper, a method based on mathematical morphology is presented to detect fabric defects including hole, warp-lacking and weft-lacking. First, the fabric-structural repeat units are identified through autocorrelation function and FFT. Second, mathematical morphological erosion and dilation methods are used to detect the defects information in terms of those repeat units. The experiments on the different kinds of defect samples show that the accuracy rate by this method can reach 97%, and proved its feasibility.
Keywords:fabric defect  morphology  detection  simulation  accuracy rate
本文献已被 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号