Sign language to text by SVM

Abstract

In this paper is presented an automatic deaf language to text system. The scheme is based on support vector machines (SVM) classifier using a Gaussian kernel. The input parameter vector to SVM is the Fisher score, which represents the derivate of the matrix of symbol probability in hidden Markov model (HMM). The HMM, which needs a sequence to be trained and used, is fed by the hand contour chain code. Besides, an improvement on the calculation of Fisher score is introduced by means of reducing the kernel scores variance. The error ratio classifying hand letter of the proposed system is less than 0.4% with our database.