A Real Time Sign Language Recognition System using Hand Tracking

Abstract: While the majority of individuals can communicate using spoken language, certain persons with restricted skills must communicate using sign language, which involves hand and finger gestures, even if not everyone can comprehend what they are saying. The fast advancement ofinformation technology can aid in the comprehension and translation of gestures. Using the Kinect camera, this project seeks to develop and build a system that recognises alphabet sign language gestures with the feature of fingers opening. The tracking process and the recognitionprocess are the two steps of the recognition system. The tracking procedure was completed by using the hands tracking approach. The recognition process is divided into two phases: the first is to get input that will be used as reference data and data testers, which is accomplished by calculating vectors and vector angles; the second is to recognise gestures, which is accomplished by calculating the Euclid distance. The system can detect motions alphabets withan average degree of accuracy of 69.79 percent, which varies according on the scenario.