Hand Gesture Interpretation Model for Indian Sign Language using Neural Networks

Exchange of words among the community is one of the essential mediums of survival. Besides that, as claimed by the World Health Organization in 2021 over 5% of the world population suffers from speech impairments, they are lacking the basic prerequisite that is needed for the survival of the human race. These people communicate using "Sign Language" among their communities which has its meaning, grammar, and lexicons, and it may not be comprehensible for every other individual. Our proposed methodology focuses on creating a vision-based prototype that interprets the Indian sign language into understandable speech or text on an embedded device and this is done using deep learning technique which is an advanced extension of machine learning technology. our model makes use of an integrated webcam for capturing the real-time hand gestures and a Raspberry Pi to process the collected samples. The model uses a dataset that has 1200 images for every gesture for better results. Training data and test data have been partitioned into 9:1 ratio. This work involves CNN, IoT, and Python Language.