Graphical Models for Structural Pattern Recognition

Tiberio Caetano (National ICT Australia)

NICTA SML SEMINAR

DATE: 2005-11-15
TIME: 11:00:00 - 12:00:00
LOCATION: RSISE Seminar Room, ground floor, building 115, cnr. North and Daley Roads, ANU
CONTACT: JavaScript must be enabled to display this email address.

ABSTRACT:
In the "structural" paradigm for visual pattern recognition, or what some call "strong" pattern recognition, one is not satisfied with simply assigning a class label to an input object, but instead we aim at finding exactly which parts of the template object correspond to which parts of the scene. This is a much harder problem in principle, because it is inherently combinatorial on the number of parts (features) involved, both in the template object and in the scene. This talk describes a summary of our research efforts in setting this as a mathematical optimization problem and solving it efficiently by exploiting geometric constraints. The key insight involves encoding geometric constraints as conditional independency assumptions in a probabilistic graphical model. Due to some geometric facts, it is possible to show that such models are very well behaved: they allow for exact probabilistic inference in polynomial time. The result is a unified framework for structural visual pattern recognition that is able to handle in a principled way a variety of problems, including point pattern matching in its many instances: invariant to translations, isometries, scalings, affine or projective transformations. Attributed graph matching problems, such as matching road networks, can also be solved within such framework. Limitations and future directions will be discussed.

BIO:
Tiberio Caetano is currently a post-doctoral fellow at the Autonomous Systems and Sensing Technology program at National ICT Australia (NICTA). He received his BSc in Electrical Engineering from the Federal University of Rio Grande do Sul (UFRGS), Brazil, in 1997. He started his research career in the area of Theoretical Physics, as an undergraduate. After some years in the industry, he received his PhD in Computer Science, with highest distinction, from UFRGS in 2004. Part of the PhD program was undertaken at the University of Alberta, Canada. He held a post-doctoral position at the University of Alberta in 2004. Since January 2005, he has been working with NICTA.