A flexible Bayesian framework for image segmentation
Thomas Meier, King Ngi Ngan · 2003
This paper presents a new Bayesian framework for image segmentation. The major contribution is a novel optimization strategy that can be applied to any cost function derived from the MAP criterion. Classical Bayesian techniques normally minimize this cost using ICM together with a K-label approach that assigns each pixel a label m/spl isin/{0,1,...,K-1}. Several shortcomings of this approach are pointed out. Our proposed method first extracts initial seeds that represent the interior of regions. The boundary location is then determined by a modified HCF method that labels pixels in the order of decreasing confidence. There is no need for an initial estimate of the segmentation, and no parameter K is required. Moreover, the presented framework can be viewed as a combination of the elegant morphological segmentation approach with the spatial continuity constraints inherent to Markov random fields in Bayesian techniques. Experimental results demonstrate the significant improvements achieved by our optimization strategy.