Title: Extraction of mid-level semantics from gesture videos using a Bayesian network
Authors: Dimitrios I. Kosmopoulos, Ilias G. Maglogiannis
Addresses: National Centre for Scientific Research 'Demokritos', Institute of Informatics and Telecommunications, 15310 Aghia Paraskevi, Greece. ' Department of Information and Communication Systems Engineering, University of Aegean, 83200 Karlovasi, Greece
Abstract: A method for extraction of mid-level semantics from sign language videos is proposed, by employing high level domain knowledge. The semantics concern labelling of the depicted head and hands as well as the occlusion events, which are essential for interpretation and for higher level semantic indexing. A Bayesian network is employed to bridge in a probabilistic fashion the gap between the high level knowledge about the valid spatiotemporal configurations of the human body and the extractor. The approach is applied here in sign language videos, but it can be generalised to any case, where semantically rich information can be derived from gesture.
Keywords: video processing; hand tracking; gesture semantics; Bayesian networks; Zernike moments; sign language; gestures; uncertainty.
International Journal of Intelligent Systems Technologies and Applications, 2006 Vol.1 No.3/4, pp.359 - 375
Published online: 01 Jun 2006 *Full-text access for editors Access for subscribers Purchase this article Comment on this article