ASL Detection and Gesture Based Control of Robotic Hand Using Image Processing

Abstract

Abstract ASL has been used by deaf people all over the world as a means of communication. The problem arises in the interpretation of the gestures to a person who is unaware of the language. The project intends to develop a real-time ASL interpretation system that is affordable, effective, and might even be used as a teaching tool. It also provides a suitable gesture recognizer which will facilitate a better understanding for the user.. In this project, we have proposed a methodology which will act as a dynamic interpreter by utilizing machine learning and computer vision techniques to enhance the efficiency and decrease the time constraint of the message detection. Along with the real time recognition of hand gestures, we have also used a robotic hand to replicate those gestures using two different methods. The first method that replicates the gesture based on the prediction made by the machine learning model and the later which replicates the gestures in real time based on the positions of finger landmarks. Using the second method we were able to bring out a faster response