Indian Sign Language Recognition for Static Gestures using DenseNet169 Model

It is usually difficult to communicate with someone who has hearing loss. Sign language is a way of communication used by dumb and deaf people. Each country has its own unique sign language. Being an Indian, it’s a pride and identity to develop a system for Indian sign language (ISL) recognition. This proposed system aims to examine the difficulties in classifying signs in ISL and intends to take a step forward in this field by utilizing machine learning (ML) models for gesture prediction. This model is trained using a convolutional neural network (CNN), and then the Densenet169 architecture is utilized to recognize the images. This model has been tested and has yielded the highest accuracy of 99.95% in the classification of signs.