1997-Hand gesture recognition using hidden Markov models

1997-Hand gesture recognition using hidden Markov models

ID:40021383

大小:407.85 KB

页数:4页

时间:2019-07-17

1997-Hand gesture recognition using hidden Markov models_第1页
1997-Hand gesture recognition using hidden Markov models_第2页
1997-Hand gesture recognition using hidden Markov models_第3页
1997-Hand gesture recognition using hidden Markov models_第4页
资源描述:

《1997-Hand gesture recognition using hidden Markov models》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、HandGestureRecogrutionUsingHiddenMarkovModelsByung-WooMin,Ho-SubYoon,JungSoh,Yun-MoYangc'),andToskiakiEjimaUImageProcessingDiv./SystemsEngineeringResearchInstitute1Ueun-dong,Yuseong-gu,Taejeon,305-333Koreaemail:bwmin@cmke.seri.re.kr(')Dept.ofInformationEngineering,Kore

2、aUniversity,Chochiwon,Korea(")Dept.ofAI,KyushuInstituteofTechnology,Iizuka,JapanAbstractthatvocallanguage,gesturesandfacialexpressionsmustHandgesturerecognitionfromvisualimageshasabeintegratedforrealizingmorenaturalman-machinenuniberofpotentialapplicationinHCI(humancon

3、iputerinterfaceanddefinesitasamulti-modalinterface.interaction),machinevision,VR(virtua1reality),machineRecentlyresearchinhandgesturerecognitionaimsatcontrolintheindustryfield,andsoon.Mostconventionalapplyingtosignlanguagerecognition,controlofapproachestohandgesturerec

4、ognitionhaveemployedhouseholdelectronicappliances,human-computerdatagloves.But,formorenaturalinterface,handgestureinteraction,VR,andsoon.mustberecognizedfromvisualimagesasintheOurresearchisintendedtodevelopagraphiceditorcommunicationbetweenhumanswithoufusinganysystemop

5、eratedbyhandgestures.Thegesturesareexternaldevices.Ourresearchisintendedtodrawandeditclassifiedintotwotypes.Oneisthestaticgestureswhichgraphicelementsbyhandgesture.areone,two,three,four,fiveinKoreansignlanguageasUptonow,manymethodsforhandgestureshowninFigure1.recogniti

6、onhavebeenproposedsuchassyntacticalanalysis,neuralbasedapproach,HMM(hiddenMarkovmodel)basedrecognition.Asgestureisthecontinuousmotiononthesequentialtimeseries,HMMmustbeaprominentrecognitiontool.Thougheachanalysismethodhasme?ftsonetwothreefourfiveanddenierits,themostimp

7、ortantthinginhandgesturerecognitioniswhattheinputfeaturesarethatrepresentFigure1.5staticgesturesverywellthecharacteristicsofmovinghandgesture.Inourresearch,weconsidertheplanarhandgestureinfrontofTheotheristhedynamicgestureswhicharesixdrawingcameraandtherefore8-directio

8、nalchaincodesasinputelementssuchascircle,triangle,rectangle,arc,horizontalvectors.FortraininganHMMnetwork,asimplecont

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。