Hand Gesture Based Sign Language Recognition Using Deep Learning

Sign Language Recognition (SLR) serves a very important role in creating a bridge between deaf/mute community and conventional society. SLR uses facial, head, arm, and hand motions to communicate linguistic information. Since mostly used body parts for communication are hands, therefore this paper is based on hand gesture sign language recognition system. The proposed method performs very well not only in detecting hand landmarks but also tracking of hand gesture continuously by using Google's MediaPipe. AlexNet classifier is used for classification of different gestures of Indian Sign Language (ISL) and also, comparison of the proposed method is done with some other existing SLR models. The dataset is a self-generated dataset which contains 15 classes for words and captured by stable webcam. This proposed method presents a system with recognition accuracy of 98.9% and its effectiveness is increased by translating the hand gesture recognition into readable text.