Computational Vision at UC Irvine

We present a model of edge and region grouping using a conditional random field built over a scale-invariant representation of images to inte- grate multiple cues. Our model includes potentials that capture low-level similarity, mid-level curvilinear continuity and high-level object shape. Maximum likelihood parameters for the model are learned from human labeled groundtruth on a large collection of horse images using belief propagation. Using held out test data, we quantify the information gained by incorporating generic mid-level cues and high-level shape.

[RFM06]

Ren, Xiaofeng, Charless Fowlkes and Jitendra Malik. Cue integration for figure/ground labeling. In Y. Weiss, B. Schölkopf and J. Platt, editors, Advances in neural information processing systems 18. MIT Press, Cambridge, MA, 2006.