Stochastic Algorithm For Parameter Estimation For Dense Deformable Template Mixture Model
Abstract
Estimating probabilistic deformable template models is a new approach in the fields of computer vision and probabilistic atlases in computational anatomy. A first coherent statistical framework modelling the variability as a hidden random variable has been given by Allassonni\`ere, Amit and Trouv\'e in [1] in simple and mixture of deformable template models. A consistent stochastic algorithm has been introduced in [2] to face the problem encountered in [1] for the convergence of the estimation algorithm for the one component model in the presence of noise. We propose here to go on in this direction of using some "SAEM-like" algorithm to approximate the MAP estimator in the general Bayesian setting of mixture of deformable template model. We also prove the convergence of this algorithm toward a critical point of the penalised likelihood of the observations and illustrate this with handwritten digit images.
Cite
@article{arxiv.0802.1521,
title = {Stochastic Algorithm For Parameter Estimation For Dense Deformable Template Mixture Model},
author = {Stéphanie Allassonnière and Estelle Kuhn},
journal= {arXiv preprint arXiv:0802.1521},
year = {2009}
}