纺织学报 ›› 2008, Vol. 29 ›› Issue (6): 11-14.

• 纤维材料 • 上一篇    下一篇

异形纤维截面测量中的边缘检测算法

杨崇倡1;冯经明1;黄作英2;魏蕊1;孙瑞玉1;王征黎3   

  1. 1.东华大学机械工程学院 上海201620;2.上海交通大学自动检测研究所 上海200240;3.神马实业股份有限公司 河南平顶山467000
  • 收稿日期:2007-06-25 修回日期:2007-10-24 出版日期:2008-06-15 发布日期:2008-06-15

Algorithm study of edge detection in profiled fibers cross-section measurement

YANG Chongchang;FENG Jingming;HUANG Zuoying;WEI Rui;SUN Ruiyu;WANG Zhengli   

  1. 1.College of Mechanical Engineering;Donghua University;Shanghai 201620;China;2.Institute of Automatic Detection;Shanghai Jiaotong University;Shanghai 200240;China;3.Shen Ma Industry Co.;Ltd.;Pingdingshan;Henan 467000;China
  • Received:2007-06-25 Revised:2007-10-24 Online:2008-06-15 Published:2008-06-15

摘要: 边缘检测是数字图像处理中的重要内容之一,也是实现图像分割、特征提取和图像理解的基础;而截面的特征参数是表征异形纤维截面形状的主要指标。计算机数字图像处理可以提取异形纤维的特征参数来自动识别不同类型的异形纤维。讨论采用常用的几种经典边缘检测算法对截面形状为五角形的异形纤维图像进行处理的情况,并通过实验得出这些边缘检测算法的优缺点及结论,以便为正在开发的异形纤维截面自动检测系统的图像处理技术作铺垫。

Abstract: Edge detection is a basic content of digital image processing,and is the base of image segmentation,feature extraction and image understanding.The fiber characteristic parameters are the principal indexes of showing cross-sectional shape of profiled fiber.The characteristic parameters of profiled fibers can be acquired by computer digital image processing system and the type of profiled fibers will be distinguished.So the performances of several typical edge detection algorithms in pentagonal shape of profiled fiber are discussed.Meanwhile,the advantages and disadvantages of these algorithms are demonstrated in the experiments and some conclusions are drawn.This study will provide some basis for the image processing of automatic detection system for profiled fiber cross-section,which is being developed.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!