Journal for Geometry and Graphics 13 (2009), No. 2, 209--220
Copyright Heldermann Verlag 2009
A 3D Head Model From Stereo Images by a Self-Organizing Neural Network
Levente Sajó
Faculty of Informatics, University of Debrecen, P. O. Box 12, 4010 Debrecen, Hungary
sajo.levente@inf.unideb.hu
Miklós Hoffmann
Institute of Mathematics and Informatics, Eszterházy Károly College, Leányka str. 4, 3300 Eger, Hungary
hofi@ektf.hu
Attila Fazekas
Faculty of Informatics, University of Debrecen, P. O. Box 12, 4010 Debrecen, Hungary
fazekas.attila@inf.unideb.hu
A model based approach is presented for generating 3D face models from two stereo images. The proposed method works with a small number of feature points of the face. The automatically registrated point pairs are used to reconstruct their 3D correspondence, then a predefined general face model is adjusted to the reconstructed 3D points. Fitting the general face model to the feature points is made iteratively by applying a self-organizing neural network.
Keywords: 3D face model, stereo images, neural network.
MSC: 68U05; 51N05, 51N20
[ Fulltext-pdf (365 KB)] for subscribers only.