Sign language recognition for hearing impaired people based on hands symbols classification
Naresh Kumar · 2017
Understating the exact context of symbolic expressions is challenging job in the social media until unless it is properly specified. This problem finds a communication gap between the people belonging to different community. Communication is always having a great impact in every domain and how it is considered the meaning of the thoughts andexpressions that attract the researchers to bridge this gap for every living being. In this work, we proposed an idea for feasible communication between hearing impaired and normal person with the help of machine learning approach. Instead of preprocessing techniques, like filtering and segmentation of hand patch images, we extract features from our dataset by discrete wavelet transform. The dimension of the feature vector is reduced by linear discriminant analysis. Both linear discriminant analysis (LDA) and support vector machine (SVM) are used on the basis of tenfold classification to recognition sign language symbols. This work ensures the 97.3% accuracy on random sign symbolic dataset of gestural communication.