A Real-Time Continuous Gesture Recognition System for Sign Language

In this paper, a large vocabulary sign language interpreter is presented with real-time continuous gesture recognition of sign language using a DataGlove. The most critical problem, end-point detection in a stream of gesture input is first solved and then statistical analysis is done according to 4 parameters in a gesture : posture, position, orientation, and motion. We have implemented a prototype system with a lexicon of 250 vocabularies in Taiwanese Sign Language (TWL). This system uses hidden Markov models (HMMs) for 51 fundamental postures, 6 orientations, and 8 motion primitives. In a signerdependent way, a sentence of gestures based on these vocabularies can be continuously recognized in real-time and the average recognition rate is 80.4%.