PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Learning Class Specific Graph Prototypes
Shengping Xia and Edwin Hancock
In: ICIAP 2009, Sept8-11, 2009, Vietri sul Mare, Italy.

Abstract

This paper describes how to construct a graph prototype model from a large corpus of multi-view images using local invariant features. We commence by representing each image with a graph, which is constructed from a group of selected SIFT features. We then propose a new pairwise clustering method based on a graph matching similarity measure. The positive example graphs of a specific class accompanied with a set of negative example graphs are clustered into one or more clusters, which minimize an entropy function. Each cluster is simplified into a tree structure composed of a series of irreducible graphs, and for each of which a node co-occurrence probability matrix is obtained. Finally, a recognition oriented class specific graph prototype (CSGP) is automatically generated from the given graph set. Experiments are performed on over 50K training images spanning ~500 objects and over 20K test images of 68 objects. This demonstrates the scalability and recognition performance of our model.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:6866
Deposited By:Edwin Hancock
Deposited On:08 April 2010