Low cost approach for real time sign language recognition

Sign Language is the language of people who suffer from speech and hearing defects. Still the rest of the world doesn´t have a clear idea of sign language. The communication between speech impaired people and other people is very inefficient. To overcome this problem technology can act as an intermediate flexible medium for speech impaired people to communicate amongst themselves and with other individuals as well as to enhance their level of learning / education. The suggested solutions in the literature for sign language recognition are very expensive for day to day use. Therefore, the main objective of this research is to find out a low cost affordable method of sign language interpretation. This paper discusses the possible ways to deal with the sign language postures to identify the signs and convert them into text and speech using appearance based approach with a low cost web camera. Further this approach will be very useful to the sign language learners to practice sign language. During the research available human computer interaction approaches in posture recognition were tested and evaluated. A series of image processing techniques with Hu-moment classification was identified as the best approach. The system is able to recognize selected Sign Language signs with the accuracy of 76% without a controlled background with small light adjustments.