文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > Eye Activity Detection and Recognition Using Morphological Scale-Space Decomposition
侵权投诉

Eye Activity Detection and Recognition Using Morphological Scale-Space Decomposition

sieves, to extract eye gesture parameters from the gray-level data directly. The proposed method resembles the work Automatic recovery of eye gestures from image se- done by Matthews et al. [11] for lip reading, but differs in quences is one of the importa

EyeActivityDetectionandRecognitionusingMorphologicalScale-spaceDecomposition

I.Ravyse,H.Sahli,M.J.T.Reinders,J.Cornelis

VrijeUniversiteitBrussel,Dept.ofElectronicsandInformationprocessing-ETRO

Pleinlaan2,B-1050Brussels,Belgiumicravyse,hsahli,jpcornel@etro.vub.ac.be

DelftUniversityofTechnology,Dept.ofElectricalEngineering

P.O.Box5031,2600GADelft,TheNetherlands

M.J.T.Reinders@its.tudelft.nl

Publishedby15thInternationalConferenceonPatternRecognition,ICPR2000,

Vol.1,pp.1080-1083,September3-8,2000,Barcelona,Spain

Abstract

Automaticrecoveryofeyegesturesfromimagese-quencesisoneoftheimportanttopicsforfacerecognitionandmodel-basedcodingofvideophonesequences.Usu-allycomplicatedmodelsoftheeyeanditsmotionareused.Inthiscontributionaneyegestureparameterestimationisdescribed.Apreviouslypublishedautomaticeyede-tection/trackingalgorithm,basedontemplatematching,isusedfortheeyeposedetection.Theeyegestureanalysisisrealisedwithamathematicalmorphologyscale-spaceap-proach,formingspatio-temporalcurvesoutofscalemea-surementstatistics.Theresultingcurvesprovideadirectmeasureoftheeyegesture,whichcanthenbeusedasaneyeanimationparameter.Experimentalresultsdemonstratetheef ciencyandrobustness.

sieves,toextracteyegestureparametersfromthegray-leveldatadirectly.TheproposedmethodresemblestheworkdonebyMatthewsetal.[11]forlipreading,butdiffersintheimplementationandtheanalysisofthespatio-temporalcurvesforeyegestureparameterestimation.Inthispaper,theeyegestureisde nedastheclosingoftheeyelids.Thedirectionofgazeisnotconsideredyet.Theestimatedlow-levelanimationparameterisrepresentedbyanActionUnit(AU)[12].AnAUstandsforasmallvisiblechangeinthefacialexpression.Moreprecisely,AU43parameterizestheamountofeyeclosure.

Thepaperisorganizedasfollows.Section2summa-rizestheapproachforthetrackingofeyeregions.Section3describesthesievedecomposition.Insection4spatio-temporalcurvesofgranulesareintroduced,fromwhichges-tureparametersareestimated.Section5discussestheex-perimentalresultsobtainedwithtestsequencesSuzieandMissAmerica.Finalconclusionsaredrawninsection6.

1.Introduction

Vision-basedfacialgestureanalysisextracts,fromanimagesequence,spatio-temporalinformationaboutthefa-cialfeaturesposeandexpressions.Themodelingandtrackingoffacesandexpressionsisatopicofincreas-inginterest.Anoverviewcanbefoundin[6].Numer-oustechniqueshavebeenproposedforfacialfeaturedetec-tionandfacialexpression(gesture)analysissuchastem-platematching[5],principalcomponentanalysis[1],inter-polatedviews[7],deformabletemplates[15],activecon-tours[9],optical ow[4],physical-modelcoupledwithop-tical ow[8],etc

Here,weproposeatrackingalgorithmbasedontemplatematchingtolocatethepositionsoftheeyeregionsinsubse-quentframes,coupledtoascalespaceapproach,namelythe

2.Trackingeyeregions

Apreviouslypublishedeyetrackingscheme[14][13],isusedforthetrackingofthelocationoftheleftandrighteyeregionsinimagesequences.Theproposedschemeisbasedontemplatematching,butiskeptinvariantfororien-tation,scaleandshapebyexploitingtemporalinformation.Tocopewithappearancechangesoftheeyefeature,acode-bookoficonicviewsisautomaticallyconstructedduringtheeyeregiontracking.Foreachframethepositionandorien-tationoftheleftandrighteyeregionareprovidedaswellasthenormalizedeyeregionsforthetemplatematching.Figure1showsthedetectedlefteyeregionforthe rst9framesoftheClairesequence.Theseimageswillbeusedtoillustrateouralgorithmforeyestate(gesture)estimation.

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email