Spotting and recognition of hand gesture for Indian sign language recognition system with skin segmentation and SVM

The hearing impaired people use sign language for communication. It relates letters, words, and sentences of spoken language to gestures, helping them to communicate among themselves. An automation system that can convert sign language to spoken language can help the hearing impaired community to intermingle with normal people. It will aid them to strengthen their abilities and make them aware that they can do better for the growth and development of humanity. In this paper we have tried to develop an automation system to recognize sign language in complex backgrounds. Video of the signer is taken and part of the hand showing the sign is segmented with respect to skin colour. Features that can identify the sign are extracted from the hand image and classified to recognize the sign. The classification is done using support vector machine.