Video Audio Interface for recognizing gestures of Indian sign Language

We proposed a system to automatically recognize gestures of sign language from a video streamof the signer. The developed system converts words and sentences of Indian sign language intovoice and text in English. We have used the power of image processing techniques and artificialintelligence techniques to achieve the objective. To accomplish the task we used powerful imageprocessing techniques such as frame differencing based tracking, edge detection, wavelettransform, image fusion techniques to segment shapes in our videos. It also uses EllipticalFourier descriptors for shape feature extraction and principal component analysis for feature setoptimization and reduction. Database of extracted features are compared with input video of thesigner using a trained fuzzy inference system. The proposed system converts gestures into a textand voice message with 91 percent accuracy. The training and testing of the system is doneusing gestures from Indian Sign Language (INSL). Around 80 gestures from 10 different signersare used. The entire system was developed in a user friendly environment by creating a graphicaluser interface in MATLAB. The system is robust and can be trained for new gestures using GUI.