Improved ASL based Gesture Recognition using HMM for System Application.

Gesture recognition is a growing field of research and among various human computer interactions; hand gesture recognition is very popular for interacting between human and machines. It is non verbal way of communication and this research area is full of innovative approaches. This project aims at recognizing 34 basic static hand gestures based on American Sign Language (ASL) including alphabets as well as numbers (0 to 9). In this project we have not considered two alphabets i.e J and Z as our project aims as recognizing static hand gesture but according to ASL they are considered as dynamic. The main features used are optimization of the database using neural network and Hidden Markov Model (HMM). That is the algorithm is based on shape based features by keeping in the mind that shape of human hand is same for all human beings except in some situations.