multimedia annotation system for intelligent search

multimedia annotation system for intelligent search

ID:34492232

大小:76.65 KB

页数:9页

时间:2019-03-06

multimedia annotation system for intelligent search_第1页
multimedia annotation system for intelligent search_第2页
multimedia annotation system for intelligent search_第3页
multimedia annotation system for intelligent search_第4页
multimedia annotation system for intelligent search_第5页
资源描述:

《multimedia annotation system for intelligent search》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、MultimediaAnnotationSystemforIntelligentSearch*1213HaralamposKaranikas,NikosPelekis,DimitrisK.Iakovidis,IoannisKopanakis,12ThomasMavroudakis,YannisTheodoridis1National&KapodistrianUniv.ofAthens,KnowledgeManagementLab.,Greece{bkaranikas,tmavroudakis}@phs.uoa.g

2、r,diakov@di.uoa.gr2DepartmentofInformatics,UniversityofPiraeus,Greece{npelekis,ytheod}@unipi.gr3TechnologicalEducationalInstituteofCrete,e-BusinessIntelligenceLab.,Greecei.kopanakis@emark.teicrete.grAbstractInthispaperwepresentanoverviewoftheintelligentmultim

3、ediaannotationandsearchsystemMetaOn.Thecoreobjectiveistoconstructandintegratesemanticallyrichmetadata,extractedfromdocumentsandimages,tofacilitateintelligentsearchandanalysis.TheproposedMetaOnframeworkinvolves,ontology-basedinformationextractionanddatamining,

4、semi-automaticconstructionofdomainspecificontologies,content-basedimageindexingandretrieval,andmetadatamanagement.TheHellenichistoryhasbeenchosenasachallengingapplicationcasestudy.KeywordsMultimediadatamining,informationextraction,imageprocessing,patternmanag

5、ement1.IntroductionWearelivinginthe“InformationAge”.Theamazinggrowthofdatathatarebeinggeneratedfromheterogeneoussourcesmakesitdifficultforhumanstomanageitandmineusefulinformation.Inmostcompaniesandorganisationsemployeetimeandeffortiswastedinineffectivesearche

6、sintheweborotherconventionalsources.Theinformationoverloadisfurtherexacerbatedduetotheunstructuredformatofthemajorityofthedata.Thevastamountofdatafoundinanorganisation,someestimatesrunashighas80%,aretextualsuchasreports,emails,etc.(MerrillLynch,2000).However,

7、othertypesofdatasuchasimage,videoandspeecharebecomingincreasinglypopular.Thesetypesofdatausuallylackmetadata(dataaboutdata)andasaconsequencetherearenostandardmeanstofacilitatesearch,queryandanalysis.Ontheotherhand,Webisthebiggestdocument(textandimage)collecti

8、onandmostofthecurrentWeb’scontentisdesignedforhumanstoread,ratherthanfordataandinformationthatcanbeprocessedautomaticallybycomputerprograms(Tim,2001).Theneedforaccessing,managingandanalys

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。