Applications of Bipartite Matching to Problems in Object Recognition
Ali Shokoufandeh, Sven Dickinson · 2009
The matching of hierarchical (e.g., multiscale or multilevel) image features is a common problem in object recognition. Such structures are often represented as trees or directed acyclic graphs, where nodes represent image feature abstractions and arcs represent spatial relations, mappings across resolution levels, component parts, etc. Such matching problems can be formulated as largest isomorphic subgraph or largest isomorphic subtree problems, for which a wealth of literature exists in the graph algorithms community. However, the nature of the vision instantiation of this problem often precludes the direct application of these methods. Due to occlusion and noise, no significant isomorphisms may exists between two graphs or trees. In this paper, we review our application of a more general class of matching methods, called bipartite matching, to two problems in object recognition. 1