Object recognition as many-to-many feature matching
2006 (English)In: International Journal of Computer Vision, ISSN 0920-5691, E-ISSN 1573-1405, Vol. 69, no 2, 203-222 p.Article in journal (Refereed) Published
Object recognition can be formulated as matching image features to model features. When recognition is exemplar-based, feature correspondence is one-to-one. However, segmentation errors, articulation, scale difference, and within-class deformation can yield image and model features which don't match one-to-one but rather many-to-many. Adopting a graph-based representation of a set of features, we present a matching algorithm that establishes many-to-many correspondences between the nodes of two noisy, vertex-labeled weighted graphs. Our approach reduces the problem of many-to-many matching of weighted graphs to that of many-to-many matching of weighted point sets in a normed vector space. This is accomplished by embedding the initial weighted graphs into a normed vector space with low distortion using a novel embedding technique based on a spherical encoding of graph structure. Many-to-many vector correspondences established by the Earth Mover's Distance framework are mapped back into many-to-many correspondences between graph nodes. Empirical evaluation of the algorithm on an extensive set of recognition trials, including a comparison with two competing graph matching approaches, demonstrates both the robustness and efficacy of the overall approach.
Place, publisher, year, edition, pages
2006. Vol. 69, no 2, 203-222 p.
graph matching. graph embedding, Earth Mover's Distance (EMD), object recognition, earth movers distance, algorithm, graphs
IdentifiersURN: urn:nbn:se:kth:diva-15856DOI: 10.1007/s11263-006-6993-yISI: 000239162400003ScopusID: 2-s2.0-33744551438OAI: oai:DiVA.org:kth-15856DiVA: diva2:333898
QC 201005252010-08-052010-08-05Bibliographically approved