Key Frame Selection for One-Two Hand Gesture Recognition with HMM
Ketki P. Kshirsagar
Abstract
The sign language recognition is the most popular research area involving computer vision, pattern recognition and image processing. It enhances communication capabilities of the mute person. In this paper, I present an object based key frame selection. Forward Algorithm is used for shape similarity for one and two handed gesture recognition. That recognition is with feature and without feature using HMM method. I proposed use to the hidden markov model with key frame selection facility and gesture trajectory features for one and two hand gesture recognition. Experimental results demonstrate the effectiveness of my proposed scheme for recognizing One Handed American Sign Language and Two Handed British Sign Language.
Keyword
Sign language, Hidden markov model and Trajectory feature for one handed and two handed sign.