Comparing key frame selection for one-two hand gesture recognition using different methods

摘要: Hand gesture recognition system has gained potential importance in application areas of human-computer interaction, machine vision, etc. Vision-based hand involves visual analysis shape, position and/or motion. Finite State Machine (FSM) and Dynamic Time Warping (DTW) are most prominent methods used for recognition. In this paper, we use object-based key frame selection from video sequence segmenting Video Object Plane (VOP). Each VOP is a meaningful position, where Hausdorff Euclidean distance shape similarity. The VOPs selected on the basis changes significantly subsequently. core approach proposed work that frames with FSM non-linear time alignment facility trajectory features. Experimental results show accuracy effectiveness system, one-handed American two-handed British sign language