Section: New Results
A Graph-matching Kernel for Object Categorization
Participant : Armand Joulin.
Collaboration with: Olivier Duchenne and Jean Ponce (Willow project-team, INRIA Paris-Rocquencourt).
In [13] , we address the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is presented. This algorithm is used to construct a kernel appropriate for SVM-based image classification, and experiments with the Caltech 101, Caltech 256, and Scenes datasets demonstrate performance that matches or exceeds the state of the art for methods using a single type of features.