The standard geometric or geodesic active contour is a powerful segmentation method, whose performance however is commonly affected by the presence of weak edges and noise. Since image modalities of all types in medical imaging are prone to such outcomes, it is important for geomertic snakes to develop some level of immunity towards them. In this chapter, a region-aided geometric snake, enhanced for more tolerance towards weak edges and noise, is introduced. It is based on the principle of the conjunction of the traditional gradient flow forces with new region constraints. We refer to this as the Region-aided Geometric Snake or RAGS. The RAGS formulation is easily extended to deal with colour images. Quantitive comparisons with other well-known geometric snakes in synthetic noisy images are presented. We also show the evaluation of RAGS with application to the localisation of the Optic Disk in colour retinal images. Many other images are also used to demonstrate the proposed method.
|Translated title of the contribution
|A Region-Aided Color Geometric Snake
|Title of host publication
|Handbook of Biomedical Image Analysis: Segmentation Models
|Published - 2005
Bibliographical noteOther page information: 535-582
Other identifier: 2000225