Cue Integration for Figure/Ground Labeling
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.
Download: pdf
Text Reference
Xiaofeng Ren, 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, pages 1121–1128. MIT Press, Cambridge, MA, 2006.BibTeX Reference
@incollection{RenFM_NIPS_2005,author = "Ren, Xiaofeng and Fowlkes, Charless and Malik, Jitendra",
editor = {Weiss, Y. and Sch\"{o}lkopf, B. and Platt, J.},
title = "Cue Integration for Figure/Ground Labeling",
booktitle = "Advances in Neural Information Processing Systems 18",
publisher = "MIT Press",
address = "Cambridge, MA",
pages = "1121--1128",
year = "2006",
tag = "grouping,object_recognition"
}