Non-purposive perceptual region grouping

Non-purposive or general-purpose region grouping (NPG) plays a significant role in bridging image segmentation and high-level image understanding. We propose a probabilistic model for the NPG problem by defining the regions as a Markov random field (MRF). A collection of energy functions is used to characterize single-region properties and pair-wise region properties. The single-region properties include region area, region convexity, region compactness, and color variances in one region. The pair-wise properties include color mean differences between two regions; edge strength along the shared boundary; color variance of the cross-boundary area; and contour continuity between two regions. Experiments have been performed on hundreds of images to show the effectiveness of the grouping algorithm.