REAL TIME INDIAN SIGN LANGUAGE RECOGNITION SYSTEM TO AID DEAFDUMB PEOPLE USING COLOR EDGE DETECTION ALGORITHM

The Sign Language is a method of communication for deaf dumb people. This paper proposes a method that provides a basis for the development of Sign Language Recognition system for one of the south Indian languages. In the proposed method, a set of 32 signs, each representing the binary UP DOWN positions of the five fingers is defined. The images are of the palm side of right hand and are loaded at runtime i.e. dynamic loading. The method has been developed with respect to single user both in training and testing phase. The static images have been pre-processed using feature point extraction method and are trained with 10 numbers of images for each sign. The images are converted into text by identifying the finger tip position of static images using image processing techniques. The proposed method is able to identify the images of the signer which are captured dynamically during testing phase. The results with test images are presented, which show that the proposed Sign Language Recognition System is able to recognize images with 98.125 percent accuracy when trained with 320 images and tested with 160 images The proposed method is applied over large database of color images both synthetic and real life images and performance of the algorithm is evident from the results and is comparable with other edge detection algorithms.