Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms英文文献资料.docVIP

下载本文档

4
0
约2.76万字
约 8页
2017-05-10 发布于上海
举报
版权申诉

Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms英文文献资料.doc

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、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、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、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
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、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、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

Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms英文文献资料

HindawiPublishingCorporation InternationalJournalofBiomedicalImaging Volume2011,ArticleID241396,7pages doi:10.1155/2011/241396 ResearchArticle BiomedicalImagingModalityClassi?cationUsingCombined VisualFeaturesandTextualTerms Xian-HuaHan 1andYen-WeiChen 1,2 1 2 CollegeofInformationScienceandEngineering,RitsumeikanUniversity,Kusatsu-Shi,525-8577,Japan CollegeofInformationSciencesandTechnology,ThePennsylvaniaStateUniversity,UniversityPark,PA16802,USA CorrespondenceshouldbeaddressedtoXian-HuaHan,hanxhua@fc.ritsumei.ac.jp Received22February2011;Revised12May2011;Accepted6July2011 AcademicEditor:FeiWang Copyright?2011X.-H.HanandY.-W.Chen.ThisisanopenaccessarticledistributedundertheCreativeCommonsAttribution License,whichpermitsunrestricteduse,distribution,andreproductioninanymedium,providedtheoriginalworkisproperly cited. Wedescribeanapproachfortheautomaticmodalityclassi?cationinmedicalimageretrievaltaskofthe2010CLEFcross-language imageretrievalcampaign(ImageCLEF).Thispaperisfocusedontheprocessoffeatureextractionfrommedicalimagesandfuses thedi?erentextractedvisualfeaturesandtextualfeatureformodalityclassi?cation.Toextractvisualfeaturesfromtheimages, weusedhistogramdescriptorofedge,gray,orcolorintensityandblock-basedvariationasglobalfeaturesandSIFThistogramas localfeature.Fortextualfeatureofimagerepresentation,thebinaryhistogramofsomeprede?nedvocabularywordsfromimage captionsisused.Then,wecombinethedi?erentfeaturesusingnormalizedkernelfunctionsforSVMclassi?cation.Furthermore, forsomeeasymisclassi?edmodalitypairssuchasCTandMRorPETandNMmodalities,alocalclassi?erisusedfordistinguishing samplesinthepairmodalitytoimproveperformance.Theproposedstrategyisevaluatedwiththeprovidedmodalitydatasetby ImageCLEF2010. 1.Introduction image representation for modality classi?cation. Recently, using local visual feature for image representation has becomeverypopular,andbeenprovedtobeverye?ective forimagecategorizationorretrieval[11].Themostfamous approachforimagerepresentationusinglocalvis