Laurent Perroton

Nonlinear features extraction applied to pollen grain images

In this work, we introduced an unsupervised segmentation and classification method based on combining two approaches: the wavelet analysis and a neural network indexation technique. The wavelet approach exploits multispectral and multiresolution analysis, providing texture description, which is a very interesting attribute. The resulting extracted features are used to perform the classification of a database of pollen grain images. This classification is performed by a neural network together with a clustering algorithm.

Parallelization of an efficient 3D thinning algorithm

In this paper, we introduce an original fully parallel thinning algorithm. Our algorithm is based on the notion of P- simple points which insure to preserve the topology while removing set of simple points in parallel. We then propose a parallel implementation of this algorithm on MIMD architectures with the PVM computation model including dynamic load-balancing.