Gesture recognition system using 2D-invariant moment feature and Elman neural network

This paper presents a simple sign language recognition system that has been developed using skin colour segmentation and Elman neural network. A simple segmentation process is carried out to separate the right and left hand. The 2D-invariant moments of the right and left hand segmented image are obtained as features. Using the 2D-invariant moment features, an Elman neural network model was developed. The system has been implemented and tested for its validity. Experimental results show that the system has a recognition rate of 90.63%.