International Journal of All Research Education & Scientific Methods

An ISO Certified Peer-Reviewed Journal

ISSN: 2455-6211

Latest News

Visitor Counter
6172944159

Hand iGesture iRecognition ion iIndian iSign ...

You Are Here :
> > > >
Hand iGesture iRecognition ion iIndian iSign ...

Hand iGesture iRecognition ion iIndian iSign iLanguage iusing iNeural iNetwork

Author Name : HARSHITA V PAWAR

ABSTRACT

This ipaper ipresents ia inovel itechnique ifor irecognize ithe ihand igesture iduring ihuman–computer iinteraction. Vision-based hand gesture recognition enabling computers to understand hand gestures as humans do is an important technology for intelligent human computer interaction. In this paper, a recognition system for dynamic hand gestures is proposed. In dynamic hand gesture recognition, hand is segmented by using background subtraction method. MPEG-7 ART based shape descriptors are used to extract spatial information. Our approach is based on particle filter to extract trajectory features. After collecting suitable features, Radial Basis Function neural network is used for classification. Gesture recognition rate is in the range of 80% to 98%. iOur imain iobjective iis ito iexplore ithe ineural inetwork-based iapproach ito ithe irecognition iof ithe ihand igestures. iWe ihave ibeen iused iorientation ihistogram ialgorithm ithat iwill irecognize ihand igesture inamely ia isubset iof iISL i(Indian isign ilanguage). iPattern irecognition isystem iused ifor itransformation ithat iconvert ian iimage iinto ifeature ivector ithen icompared ito ifeature ivector iof itraining iset iof igestures. iAt ilast ithe ifinal isystem iis iimplemented iwith ia iperceptron inetwork.

Keywords: iHCI, iISL, iANN, iPattern iRecognition.