网站大量收购独家精品文档,联系QQ:2885784924

基于自适应阈值的棉网图像中结杂的识别_李美玲.pdf

基于自适应阈值的棉网图像中结杂的识别_李美玲.pdf

  1. 1、本文档共4页,可阅读全部内容。
  2. 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
  3. 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载
  4. 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
基于自适应阈值的棉网图像中结杂的识别_李美玲

36 2 () Vol.36, No.2 2010 4 JOU RNAL OF DONG HUA UNIVERSIT Y(NA TU RAL SCIENCE ) Apr.2010   :1671-0444 (2010)02-0144-04 * 李美玲, 陈俊琰, 郁崇文 ( , 201620)  :在棉网图像中, 棉结和杂质(简称结杂)大多都混杂在聚集的纤维网中难以检出和识别.针对这 一 题, 提出 了一种将最大类间方差法(Ots 法)与线性回归相结合的棉网图像结杂分割方法.首先对棉网图像进行预处理, 然后根 据Ots 法获取棉网图像与背景分开的阈值, 再根据线性回归找出该阈值与结杂灰度的关系, 获得结杂分割的最佳阈 值, 从而实现结杂的识别. :棉网图像;结杂识别;自适应阈值;图像分割;最大类间方差法 :TN 941.1   :A Nep and Trash Recognit ion from Carded Web Image Based on Adapt ive Threshold L I Mei -ling , CH E N J un-y an ,YU Chong -wen (Key Laboratory of TextileScience Technology, Ministry of Education, DonghuaUniversity, Shanghai201620, hina) Abstract:Nep and trash in carded w eb image are s ally diffic lt to be detected as they often s perimpose on dense fiber layer.In order to solve this problem, one adaptive threshold segmentation method w as proposed for obtaining the information abo t nep and trash from card w eb image, based on Ots threshold method and linear regression model.Firstly, the image of card w eb w as preprocessed.Secondly, the basic threshold w as obtained by Ots threshold method.Then, the linear regression model betw een this threshold and the optimal one w as b ilt, and more precise threshold w as got, w hich w as taken to segment the webs.Finally, nep and trash w ere segmented aw ay from the w eb image m ch acc rately. Key words:carded w eb image;nep and trash recognition;adaptive threshold;image segmentation;Ots threshold method   () , , . , 、. [1] , . (), , .NCT . , , ,

文档评论(0)

jiupshaieuk12 + 关注
实名认证
内容提供者

该用户很懒,什么也没介绍

版权声明书
用户编号:6212135231000003

1亿VIP精品文档

相关文档