Abstract. Mutual Information (MI) is a long studied measure of information content, and many attempts to apply it to feature extraction and stochastic coding have been made. Howeve...
Atypical observations, which are called outliers, are one of difficulties to apply standard Gaussian density based pattern classification methods. Large number of outliers makes di...
We focus on characterizing spatial region data when distinct classes of structural patterns are present. We propose a novel statistical approach based on a supervised framework for...
Despina Kontos, Vasileios Megalooikonomou, Marc J....
Many attempts have been made to represent families of 2D shapes in a simpler way. These approaches lead to so-called structures as the Symmetry Set (SS) and a subset of it, the Med...
We present a novel clustering method using HMM parameter space and eigenvector decomposition. Unlike the existing methods, our algorithm can cluster both constant and variable leng...