Sign Language Detection System

Sign language is a system for communication usingvisual gestures and signs for deaf and dumb people. Thislanguage is especially used by people who can’t speak or hear.Sign language is oldest and natural form of language forcommunication, since most of the people are not aware of signlanguage, hence it is tedious to understand, for solving thisproblem we have built a real time method using convolutionneural networks (CNN) for hand-based gestures to detect signlanguage. In our CNN model, first the hand is passed througha filter and then the filter is applied. Finally, the hand ispassed through a classifier which predicts the class of thehand gestures. Our model provides 98% accuracy for thealphabet A-Z letters. On the other hand, the most commonhurdle deaf and dumb come across is communication withthe normal people and with the fact i.e., each and everynormal person doesn't know the sign language. Another mainfeature of the project is to create a communication system forthe deaf people. The functionality of these part of the system isto translate audio message to the corresponding sign language.This part of the system takes the audio message as input, andconverts the audio recorded message into the respective signimage and videos and displays the relevant American signlanguage or GIFs which we have already defined. With the aidof this part of the system, communication between normal anddeaf people gets feasible. Overall, the main idea of the projectis to make a system which can help deaf and dumb to interactwith normal people.