INDIAN SIGN LANGUAGE RECOGNITION USING NEURAL NETWORKS AND KNN CLASSIFIERS

Sign language recognition is helpful in communication between signing people and non-signing people. Various research projects are in progress on different sign language recognition systems worldwide. The research is limited to a particular country as there are country wide variations available. The idea of this project is to design a system that can interpret the Indian sign language in the domain of numerals accurately so that the less fortunate people will be able to communicate with the outside world without need of an interpreter in public places like railway stations, banks, etc. The research presented here describes a system for automatic recognition of Indian sign language of numeric signs which are in the form of isolated images, in which only a regular camera was used to acquire the signs. To use the project in real environment, first we created a numeric sign database containing 5000 signs, 500 images per numeral sign. Direct pixel value and hierarchical centroid techniques are used to extract desired features from sign images. After extracting features from images, neural network and kNN classification techniques were used to classify the signs. The result of these experiments is achieved up to 97.10% accuracy.