A Study on Static Hand Gesture Recognition using(中英对照)

《A Study on Static Hand Gesture Recognition using(中英对照)》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、AStudyonStaticHandGestureRecognitionusingMoments静态手势识别研究中矩的应用S.PadamPriyalandPrabin.K.BoraDepartmentofElectronicsandCommunicationEngineeringIndianInstituteofTechnologyGuwahati,Guwahati,IndiaEmail:{s.priyal,prabin}@iitg.ernet.inAbstract—Handgesturerecognitionison

2、eofthekeytechniquesindevelopinguser-friendlyinterfacesforhuman-computerinteraction.Statichandgesturesarethemostessentialfacetsofgesturerecognition.Viewpointinvarianceanduserindependenceareamongtheimportantrequirementsforrealizingarealtimegesturerecognitionsystem

3、.Inthiscontext,thegeometricmomentsandtheorthogonalmomentsnamelytheZernike,TchebichefandKrawtchoukmomentsareexplored.Theproposedsystemdetectsthehandregionthroughskincoloridentificationandobtainsthebinarysilhouette.Theseimagesarenormalizedforrotationandscalechange

4、s.Themomentfeaturesofthenormalizedhandgesturesareclassifiedusingaminimumdistanceclassifier.TheclassificationresultssuggestthattheKrawtchoukmomentfeaturesarecomparativelyrobusttoviewpointchangesandalsoexhibituserindependence.I摘要----手势识别是研发用户友好的人机交互界面的关键技术之一。静态手势手

5、势识别是其中最重要的方面。观察视点不变性和用户独立性是众多为实现实时手势识别系统的重要需求中的其中两种。因此，我们对几何矩和正交矩即Zernike，Tchebichef和Krawtchouk矩进行了探讨。在应用中，拟定系统通过皮肤颜色识别检测手所在的区域，并且得到了二进制表示的手部轮廓。将这些得到的图像根据旋转度的变化和比例的变化进行规范化。规范化后的手势利用一种最小距离分类器将其矩特性区分成各个不同类型。结果表明:相较其他类型的矩，Krawtchouk矩在观察点变化时健壮性（即稳定性）较好，并且较好地体现了用户独立性

6、。indexTerms—Geometricmoments,Handgesture,Krawtchoukmoments,Tchebichefmoments,Viewanduserindependentrecognition,Zernikemoments.索引词----几何矩，手势，Krawtchouk矩，,Tchebichef矩，视点和用户独立性的识别，Zernike矩。I.INTRODUCTIONHuman-computerinteraction(HCI)isaninterestingareaofresearchfac

7、toringdevelopmentinthefieldofautomaton.TherecentadvancementhasledtotheemergenceofHCIsystemsthatembodythe‘natural’wayofcommunicationbetweenhumans.Therefore,attemptsinintegratingcommunicationmodalitieslikespeech,handwritingandhandgesturesintoHCIhavegainedimportanc

8、e.Researchershavefocusedindevelopingadvancedhandgestureinterfacesresultinginsuccessfulapplicationslikerobotics,assistivesystems,signlanguagecommunicationandvirtualrea