Automatic Visual Recognition of Gestures Made by Motor-Impaired Computer UsersBy Morrison, K.; McKenna, S.J.; Technology and Disability, Vol. 14, No. 4, pp. 197-203
Publication Date: 2002
Article discussing the use of gesture recognition as a means of human computer interaction for computer users with physical disabilities. A real-time computer vision system for recognition of one- and two-handed gestures is described. The system was developed in collaboration with computer users with fine motor disabilities. The system detects, tracks, and identifies a person’s head and hands by using skin color as a visual cue. Extracted motor trajectories are used as a basis for the recognition of dynamic gestures that consist of movements of one or both hands. Hidden Markov models are used to model the gestures based on observing the user perform them several times. Implications for further research are discussed.
Published by: IOS Press (Website:http://www.iospress.nl)
Association for the Advancement of Assistive Technology in Europe (AAATE) (Web Site: http://www.aaate.net )
This publication is included in the library of the National Rehabilitation Information Center (NARIC), accession number J44855