[ Component-Based Recognition ]
Computer Vision      
  Component-Based Face Recognition. In collaboration with: B. Heisele, J. Huang and B. Weyrauch.  
  Combining the class-specific information captured by the Morphable Model of 3D Faces with a Support Vector Machine for classification, we detect facial components in images efficiently. Given three images of each person to be recognized, the Morphable Model and a 3D model fitting algorithm are used to reconstruct the 3D shape. Then, a large number of images are generated, showing the same person from different viewing angles. These synthetic images form the training set of the Support Vector Machine for viewpoint-independent detection of facial components.  
Face Recognition Using Component-Based SVM Classification and Morphable Models
J. Huang, V. Blanz, B. Heisele. In: S.-W. Lee and A. Verri (Eds.): SVM 2002, LNCS 2388, pp.334-341, 2002
Springer-Verlag, Berlin Heidelberg 2002. pdf
  Component-Based Face recognition with 3D Morphable Models, B. Weyrauch, J. Huang, B. Heisele and V. Blanz, IEEE Workshop on Face processing in Video, FPIV04, Washington, D.C., 2004  

© Sascha Nesch 2009