Method and system using a data-driven model for monocular face tracking
作者： Jean-Yves Bouguet , Salih Gokturk , Radek Grzeszczuk
DOI:
关键词: Linear combination 、 Sequence 、 Principal component analysis 、 Pattern recognition 、 Facial motion capture 、 Geography 、 Artificial intelligence 、 Data-driven 、 Tracking (particle physics) 、 Face (geometry) 、 Computer vision 、 Monocular
摘要: A method and system using a data-driven model for monocular face tracking are disclosed, which provide versatile three-dimensional (3D) images, e.g., face, single camera. For one method, stereo data based on input image sequences is obtained. 3D built the obtained data. sequence tracked model. Principal Component Analysis (PCA) can be applied to learn, possible facial deformations, build (“3D model”). The used approximate generic shape (e.g., pose) as linear combination of basis vectors PCA analysis.
lens.org 参考文章(44)
Koji Fujiwara, Shinichi Ban, Device for and method of processing 3-D shape data ,(2000)
Gianluca Francini, Mauro Quaglia, A method of creating 3 d facial models starting from face images ,(1999)
Michael Cheiky, Peter Gately, Shawn Smith, Do-it-yourself photo realistic talking head creation system and method ,(2006)
Henrique Sarmento Malvar, Brian Guenter, Cindy Marie Grimm, Method and system for capturing and representing 3D geometry, color and shading of facial expressions and other animated objects ,(1998)
Thomas Vetter, Volker Blanz, Method and apparatus for the processing of images Max-Planck-Gesellschaft zur Forderung der Wissenschaften e.V.. ,(2000)
Arsev H. Eraslan, Three-dimensional face identification system ,(1998)
Edward O. Clapper, Operator training system ,(2000)
Hartmut Neven, Johannes Bernhard Steffens, Egor Valerievich Elagin, Thomas Maurer, Face recognition from video images ,(1999)