Abstract
Hand gesture recognition is a way to create a useful, highly adaptive interface between machines and their users. The recognition of gestures is difficult because gestures exhibit human variability. Sign languages are used for communication and interface . There are various types of systems and methods available for sign languages recognition. Our approach is robust and efficient for static hand gesture recognition. The main objective of this paper is to propose a system which is able to recognize 36 static hand gestures of American Sign Language (ASL) for letter A- Z and digits 0-9 successfully and also it is able to perform the classification on static images correctly in real time. We proposed a novel method of pattern recognition to recognize symbols of the ASL based on the features extracted by SIFT algorithm and its performance is compared it with widely used methods such as PCA and Template Matching.
Users
Please
log in to take part in the discussion (add own reviews or comments).