logo Idiap Research Institute        
 [BibTeX] [Marc21]
Active Shape Models for Visual Speech Feature Extraction
Type of publication: Book chapter
Citation: luettin-nato96
Booktitle: Speechreading by Humans and Machines
Series: NATO ASI Series, Series F: Computer and Systems Sciences
Volume: 150
Year: 1996
Publisher: Springer Verlag
Address: Berlin
Abstract: Most approaches for lip modelling are based on heuristic constraints imposed by the user. We describe the use of Active Shape Models for extracting visual speech features for use by automatic speechreading systems, where the deformation of the lip model as well as image search is based on a priori knowledge learned from a training set. We demonstrate the robustness and accuracy of the technique for locating and tracking lips on a database consisting of a broad variety of talkers and lighting conditions.
Userfields: ipdmembership={vision},
Projects Idiap
Authors Luettin, Juergen
Thacker, Neil A.
Beet, Steve W.
Editors Storck, D. G.
Hennecke, Hennecke
Added by: [UNK]
Total mark: 0
  • nato96.pdf
  • luettin_nato96.ps.gz