%0 Journal Article 
%F 98Ksp
%A Kervrann, C.
%T Learning probabilistic deformation models from image sequences
%J Signal Processing
%N 71
%P 155-171
%X In This paper, we present an approach for an unsupervised learning of probabilistic deformation modes of 2D moving objects from images sequences. The object representation relies on a statistical description of global and local deformations applied to an a priori prototype shape. The optimal Bayesian estimate of the deformation process is obtained by maximizing a nonlinear joint probability distribution using stochastic and deterministic optimization techniques. The estimates obtained at time t are integrated in the deformation model as a priori knowledge for the segmentation at time \textit{t} + 1. Deformation modes are updated on-line using a principal component analysis of the distortions computed from the shapes estimated previously in the image sequence. In addition, the updated deformation modes are exploited for the real-world image sequences showing the tracking of hands undergoing 2D articulated movements
%U http://www.irisa.fr/vista/Papers/1998_sp_kervrann.pdf
%D 1998