Sign Language Alphabets Recognition Using Wavelet Transform

Abstract

Bridging communication gap between the common man and the hearing impaired people is a big challenge. Thus lot of research is being done in the area of sign language recognition to come-up with the optimum algorithm or solution for cent percent recognition of signs. Till now numbers of techniques are being developed. This article explains wavelet feature based method to recognize the 24 static-image based alphabets A to Z (excluding dynamic alphabets J and Z) of American Sign Language (ASL). This method extracts the wavelet feature vectors of the images. Further neural network is used for the classification of these alphabets. This method is qualified to provide an average recognition rate of 97.47 percent at fourth level decomposition of wavelet features.