PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Robust Near-Isometric Matching via Structured Learning of Graphical Models
Julian J. McAuley, Tiberio S. Caetano and Alex J. Smola
In: NIPS 2008, Vancouver(2008).


Models for near-rigid shape matching are typically based on distance-related features, in order to infer matches that are consistent with the isometric assumption. However, real shapes from image datasets, even when expected to be related by ``almost isometric'' transformations, are actually subject not only to noise but also, to some limited degree, to variations in appearance and scale. In this paper, we introduce a graphical model that parameterises appearance, distance, and angle features and we learn all of the involved parameters via structured prediction. The outcome is a model for near-rigid shape matching which is \emph{robust} in the sense that it is able to capture the possibly limited but still important scale and appearance variations. Our experimental results reveal substantial improvements upon recent successful models, while maintaining similar running times.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:5272
Deposited By:Tiberio Caetano
Deposited On:24 March 2009