[Paper] Inferring Segmentation Label and Color Distribution in a Unified Framework using Global Constraints

Abstract

In this paper, we propose a unified framework for inferring the segmentation label and color distribution of an image region of interest. Recent studies have shown that segmentation with global consistency measures outperforms conventional techniques based on pixelwise measures. However, such global approaches require a precise input distribution to obtain the correct extraction. To overcome this strict assumption, we propose a new approach in which the given reference distribution plays a guiding role in inferring the latent distribution and its consistent region. The inference is based on an assumption that the latent distribution resembles the distribution of the consistent region but is distinct from the distribution of the complement region. We state the problem as the minimization of an energy function consisting of global similarities and implement an iterative scheme for jointly optimizing distribution and segmentation. Rich experimental results demonstrate the advantages of using our approach with various segmentation problems.