Use of motion-print in sign language recognition

The work presented in this paper goals to develop a system for automatic translation of static as well as dynamic gestures of Indian Sign Language. Image processing features such as skin tone detection spatial filter velocimetry and temporal tracing features are utilized for obtaining the motion print which is nothing but the power spectrum representation of the gestures that is unique for each gesture. The system deals with images of bare hands, which allows the user to interact with the system in a natural way in whatever environment. The sequence of images processed and converted to motion print will be compared with the motion print of a training set of signs by pattern matching to synthesize the desired speech at the output.