Deformed Lattice Detection via Mean-Shift Belief Propagation - Robotics Institute Carnegie Mellon University

Deformed Lattice Detection via Mean-Shift Belief Propagation

Minwoo Park, Robert Collins, and Yanxi Liu
Conference Paper, Proceedings of (ECCV) European Conference on Computer Vision, pp. 474 - 485, October, 2008

Abstract

A regular wallpaper pattern can be generated by two basis vectors, (t1, t2). The lattice generated by (t1, t2) divides a 2D plane into identical parallelograms, called tiles. Given the natural match between tiles/basis-vectors in wallpaper theory, and observable nodes/edges in probabilistic graph models, we can encode domain knowledge from wallpaper theory into the observation model and pairwise compatibility function of a degree-4 Markov Random Field (MRF). Belief Propagation (BP) can then be used to locate a deformed lattice in an unsegmented image.

BibTeX

@conference{Park-2008-10109,
author = {Minwoo Park and Robert Collins and Yanxi Liu},
title = {Deformed Lattice Detection via Mean-Shift Belief Propagation},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2008},
month = {October},
pages = {474 - 485},
}