Region-based active contour with noise and shape priors

TL;DR

This paper introduces a novel region-based active contour method that integrates noise and shape priors using exponential family models and invariant moments, enhancing segmentation robustness and flexibility.

Contribution

It combines noise and shape priors within a unified active contour framework, with a rigorous derivation of the evolution equation using shape derivatives.

Findings

Robust segmentation on synthetic and real images

Effective noise handling and shape fidelity

Demonstrated robustness to initialization and noise

Abstract

In this paper, we propose to combine formally noise and shape priors in region-based active contours. On the one hand, we use the general framework of exponential family as a prior model for noise. On the other hand, translation and scale invariant Legendre moments are considered to incorporate the shape prior (e.g. fidelity to a reference shape). The combination of the two prior terms in the active contour functional yields the final evolution equation whose evolution speed is rigorously derived using shape derivative tools. Experimental results on both synthetic images and real life cardiac echography data clearly demonstrate the robustness to initialization and noise, flexibility and large potential applicability of our segmentation algorithm.