Using The 3D Hand Model To Recognize Stationary Hand Signs
Jintae Lee · International Journal of Modelling and Simulation · 1999
Sign language is the primary communication means for the hearing impaired because typewriting or handwriting cannot provide equivalent power of expression, naturalness, or convenience. The capability to computer-process sign language has consequently received much research attention. This paper presents the 3D hand model for performing hand sign recognition based on 3D “structural features” of the hand, that is, flexion of joints and contactness of fingers. This technique mitigates the weaknesses in conventional approaches, as the 3D structural features of the hand extracted using the hand model are stable against perturbations and provide more clues to distinguish hand signs. The effectiveness and capability of our approach is successfully demonstrated by testing it on the American Sign Language manual alphabet.