A Variational Segmentation Framework using Active Contours and Thresholding

S. Dambreville, M. Niethammer, A. Yezzi, and A. Tannenbaum (USA)

Keywords

Image segmentation, curve evolution, PDE, levelset meth ods, thresholding, parametric estimation.

Abstract

Segmentation involves separating distinct regions in an im age. In this note, we present a novel variational approach to perform this task. We propose an energy functional that naturally combines two segmentation techniques usu ally applied separately: intensity thresholding and geomet ric active contours. Although our method can deal with more complex image statistics, intensity averages are used to separate regions, in this present work. The proposed ap proach affords interesting properties that can lead to sensi ble segmentation results.

Important Links:



Go Back