A Graph-matching Kernel for Object Categorization

Olivier Duchenne (1) , Armand Joulin (1, 2) , Jean Ponce (1)

1 WILLOW - Models of visual object recognition and scene understanding
2 SIERRA - Statistical Machine Learning and Parsimony

This paper addresses 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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Olivier Duchenne, Armand Joulin, Jean Ponce. A Graph-matching Kernel for Object Categorization. ICCV 2011 - 13th International Conference on Computer Vision, Nov 2011, Barcelona, Spain. pp.1056. ⟨hal-00650345⟩