We present a parameter free approach that utilizes multiple cues for image segmentation. Beginning with an image, we execute a sequence of bottom-up aggregation steps in which pix...
In this paper we propose a new segmentation algorithm which combines patch-based information with edge cues under a probabilistic framework. We use a mixture of multiple Gaussians...
This paper studies the problem of learning a full range of pairwise affinities gained by integrating local grouping cues for spectral segmentation. The overall quality of the spect...
Tae Hoon Kim (Seoul National University), Kyoung M...
We propose an information-theoretic method for multi-phase image segmentation, in an active contour-based framework. Our approach is based on nonparametric density estimates, and ...
Alan S. Willsky, Anthony J. Yezzi, John W. Fisher ...
We propose a two-class classification model for grouping. Human segmented natural images are used as positive examples. Negative examples of grouping are constructed by randomly m...