Classification of cell nuclei using shape and texture indexes

Abstract

In this paper, we present a study on the characterization and the classification of binary digital objects. This study is performed using a set of values obtained by the computation of "shape and texture indexes". To get the shape indexes, we extract a set of data called "measures" from 2D shapes, like for example surface and perimeter. These indexes are then used as parameters of a function returning a real value that gives information about geometrical and morphological features of the shape to analyze. A model characterizing the shape (and the texture) of objects is subsequently built. An application to the classification of cell nuclei (in order to diagnose patients affected by the Progeria syndrome) is proposed.