Publication

Abstract : Invisible Mouse (IM) endeavours the real-time implementation of Computer Mouse using Hand Gesture Recognition. IM uses gesture rules corresponding to each mouse function and accepts video containing hand gestures as input. Gestures are extracted from video, matched with existing gesture rule set and appropriate mouse functionality is invoked. It plays an important role in Virtual Reality Environments as well as areas of Human-Computer Interfacing. In this work, we propose a vision based, single camera model that uses 2D-tree based virtual grid for camera-to-screen coordinate mapping. The proposed model is cost effective, easy to set up and provides same functionality of hardware mouse. It overcomes the inadequacy of earlier approaches. The proposed method provides satisfactory results for various texture backgrounds under uniform illumination. © 2012 by IJTS.