SHAPE GRADIENT FOR MULTI-MODAL IMAGE SEGMENTATION USING MUTUAL INFORMATION (WA-P4)

Author(s) : Ariane Herbulot (I3S Laboratory, France) Stéphanie Jehan-Besson (GREYC-images Laboratory, France) Michel Barlaud (I3S Laboratory, France) Gilles Aubert (Dieudonne Laboratory, France)

Abstract : This paper deals with video and image segmentation using region based active contours. We consider the problem of segmentation through the minimization of a new criterion based on information theory. We use a general derivation framework based on the notion of shape gradient. This general derivation is applied to criterions based on information theory, such as mutual information for the segmentation of sequences of images. We present experimental results on multimodal images showing the accuracy of the proposed method.

Menu