面向物体匹配的具有仿射不变性的可变形轮廓模型.docVIP

面向物体匹配的具有仿射不变性的可变形轮廓模型.doc

  1. 1、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。。
  2. 2、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
  3. 3、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)。
  4. 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
  5. 5、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
  6. 6、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。
  7. 7、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
ImageandVisionComputing20(2002)77±84/locate/imavis AI-EigenSnake:anaf?ne-invariantdeformablecontourmodelforobjectmatching ZhongXuea,StanZ.Lib,EamKhwangTeoha,* aSchoolofElectricalandElectronicEngineering,NanyangTechnologicalUniversity,Vice-DeansOf?ce,BlockS2,Singapore,Singapore639798bMicrosoftResearchChina,3/FBeijingSigmaCenter,No.49ZhichunRoad,Beijing100080,PeoplesRepublicofChina Received11April2000;receivedinrevisedform3March2001;accepted16July2001 Abstract Anaf?ne-invariant(AI)deformablecontourmodelforobjectmatching,calledAI-EigenSnake(AI-ES),isproposedintheBayesianframework.InAI-ES,thepriordistributionofobjectshapesisestimatedfromthesampledata.Thisdistributionisthenusedtoconstraintheprototypecontour,whichisdynamicallyadjustableinthematchingprocess.Inthisway,largeshapedeformationsduetothevariationsofsamplescanbetolerated.Moreover,anAIinternalenergytermisintroducedtodescribetheshapedeformationsbetweentheprototypecontourintheshapedomainandthedeformablecontourintheimagedomain.Experimentsbasedonrealobjectmatchingdemonstratethattheproposedmodelismorerobustandinsensitivetothepositions,viewpoints,andlargedeformationsofobjectshapes,ascomparedtotheActiveShapeModelandtheAI-SnakeModel.q2002ElsevierScienceB.V.Allrightsreserved. Keywords:Activeshapemodel;Af?neinvariant;Deformablemodel;EigenSnake;Objectmatching 1.Introduction Deformablemodelshavebeenstudiedintensivelyduringthelast10years[1,3±6].Theyhavebeendemonstratedtobemoreeffectiveinobjectmatchingandabletoadaptthemselvesto?tobjectsmorecloselythanthetraditionalrigidmodels.Generally,deformablemodelscanbeclassi-?edintotwoclasses[6,17,24]:thefree-formmodelsandtheparametricmodels.Thefree-formmodels,e.g.activecontoursorsnakes,canbeusedtomatchanarbitraryshapethatprovidedsomegeneralregularizationconstraints,suchascontinuityandsmoothness,aresatis?ed[25,27].Althoughthefree-formmodelsalsoactasinteractivetoolsforobjectextractionandimagesegmentation,theparametricmodelsaremoreconstrainedbecausesomepriorinformationofthegeometricalshapeisi

文档评论(0)

339910001 + 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