F. DiMaio & J. Shavlik (2006).
Belief Propagation in Large, Highly Connected Graphs for 3D Part-Based Object Recognition. Proceedings of the Sixth IEEE International Conference on Data Mining (ICDM'06), pp. 845-850, Hong Kong.
A longer version of this paper appears as UW Machine Learning Research Group Working Paper 06-1.
Slides (PPT). Code. Data.

This publication is available in PDF.

The slides for this publication are available in Microsoft PowerPoint.

The software and data associated with this publication are available online.

Abstract:

We describe a part-based object-recognition framework, specialized to mining complex 3D objects from detailed 3D images. Objects are modeled as a collection of parts together with a pairwise potential function. An efficient inference algorithm - based on belief propagation (BP) - finds the optimal layout of parts, given some input image. We introduce AggBP, a message aggregation scheme for BP, in which groups of messages are approximated as a single message. For objects consisting of N parts, we reduce CPU time and memory requirements from O(N^2) to O(N). We apply AggBP on synthetic data as well as a real-world task identifying protein fragments in three-dimensional images. These experiments show that our improvements result in minimal loss in accuracy in significantly less time.

Return to the publications of the Univ. of Wisconsin Machine Learning Research Group.