Indian Sign Language Recognition: Support Vector Machine Approach

Abstract

Indian Sign Language (ISL) is the primary form of communication for the dumb and deaf community in India. Recognizing Indian Sign Language plays an imperative part in promoting communication rights, social inclusion and equality for deaf people, while also contributing to technological advancement and cultural diversity. System’s ability to automatically recognize ISL signs could significantly improve community interactions between deaf and people with hearing loss. The objective of this research is to design a system that can accurately recognize and interpret Indian Sign language (ISL), thereby improving communication accessibility for the deaf and dumb community. Also, enhance the accuracy of Indian Sign language (ISL) recognition. In this research, Machine Learning approach for Sign Language (SL) Recognition using Support Vector Machine (SVM) is implemented. The Support Vector Machine (SVM) model was trained using a linear kernel and a regularization parameter (C) set to 0.999 on a dataset of sequences for gesture recognition. After training, the model achieved a test accuracy of 86% on the test data. The development and implementation of gesture recognition system can increase awareness of the communication needs and rights of deaf people.