保留边缘信息和特定目标的高密脉冲噪声滤波算法.pdfVIP

保留边缘信息和特定目标的高密脉冲噪声滤波算法.pdf

  1. 1、本文档共5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)。
  5. 5、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
  6. 6、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们
  7. 7、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
  8. 8、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
保留边缘信息和特定目标的高密脉冲噪声滤波算法.pdf

50 2014 4 () Vol.50 2014 No.4 Journalof Northwest Normal University (Natural Science) 45 , , ( , 710025) : , . , ; , , ; , . , , ; , . : ;;; : TN 941.1 : A : 1001‐988Ⅹ (2014)04‐0045‐03 An algorithm for impulse noise with high density preserving edge information and special objects ZHAO Wei‐zhou, WANG Hui‐zhen, QU Na (Collegeof Science, TheSecond Artillery Engineering University , Xian 710025 , Shaanxi, China) : Aiming at many problems such as edge information being badly lost and special object being over‐ rocessedfor impulse noise, a denoising algorithm to maintain edge and object is proposed in thisp paper. Firstly, both every contaminatedpixelandthecontaminationcircumstanceinitsneighborhoodcan beobtained by the characteristic of impulse noise . Secondly , by means of details judgment and window optimization, some filtering methods are used to reduce the noise density and obtain genuine grey information. Finally , the special object detection and the double‐window edgejudgment are added to get the denoised image. Experiment show that the proposed method can obtain satisfactory result with a smaller RMSE (rootof meansquareerror) andabigger EPI (edgepreservedindex), furthermore, more information can be preservedfor special object in theimagewith impulse noise . : impulse noise; filtering; RMSE; EPI , [4 ,5] , ; [1‐3] . [ 6 ] , . , , . , . QASMF [ 7 ] , , , . , ( : 2013-11-01 ; : 2014-04-23 : (2013JGW041) : (1977— ), , , , . . E-mail: happywz_zhao@ 163.com () 50 46 Journalof Northwest Normal University (NaturalScience) Vol.50 ), . × , QASMF 3 , (, )= 1 , β , . = 5 , (, )≠ 1 8 , (3 ) β , 7 , (, )= 8 . β , . , , , . , , 1 , std{(, ),}≤ , (, ) ∈ . , , (4 ) . , std{(, ),} , , ; . , , = 15 . . , (, ) , (, ) × , (, ), (, ). ; (, ) 0 ( - 1), , α . 1 , (, )= 0 (, )= - 1 , 1.2.2 α(, )= 0 , . , (1 ) . α (, ) = β β ( sum{α(, )}, 3 ,5 ,7 , ). ( … , = 3 ; (, )∈ {0 ,1 ,2 ,… ,× }. ), β . region: . 1) (, )= -

文档评论(0)

rewfdgd + 关注
实名认证
文档贡献者

该用户很懒,什么也没介绍

1亿VIP精品文档

相关文档