Top-Down Segmentation of Histological Images Using a Digital Deformable Model

Abstract

This paper presents a straightforward top-down segmentation method based on a contour approach on histological images. Our approach relies on a digital deformable model whose internal energy is based on the minimum length polygon and that uses a greedy algorithm to minimise its energy. Experiments on real histological images of breast cancer yields results as good as that of classical active contours.

Jacques-Olivier Lachaud

Professor of Computer Science

My research interests include digital geometry, geometry processing, image analysis, variational models and discrete calculus.