Coupled Geodesic Active Regions for Image Segmentation: A Level Set Approach

Abstract. This paper presents anovel variational method forimage segmentation that uni es boundary and region-based information sources under the Geodesic Active Region framework. A statistical analysis based on the Minimum Description Length criterion and the Maximum Likelihood Principle for the observed density function (image histogram) using a mixture of Gaussian elements, indicates the number of the di erent regions and their intensity properties. Then, the boundary information is determined using a probabilistic edge detector, while the region information is estimated using the Gaussian components of the mixture model. The de ned objective function is minimized using a gradientdescent method where a level set approach is used to implement the resulting PDE system. According to the motion equations, the set of initial curves is propagated toward the segmentation result under the in uence of boundary and region-based segmentation forces, and being constrained by a regularity force....

• Type: Conference
• Year: 2000
• Where: ECCV
• Authors: Nikos Paragios, Rachid Deriche
• Keywords: Computer Vision, ECCV 2000, Exclusive Propagating Curves, Level Set Approach, Level Set Implementation, Method Forimage Segmentation, Region-based Segmentation Forces