Object recognition as many-to-many feature matching
International Journal of Computer Vision, cilt.69, sa.2, ss.203-222, 2006 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 69 Sayı: 2
- Basım Tarihi: 2006
- Doi Numarası: 10.1007/s11263-006-6993-y
- Dergi Adı: International Journal of Computer Vision
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
- Sayfa Sayıları: ss.203-222
- Anahtar Kelimeler: Earth Mover's Distance (EMD), Graph embedding, Graph matching, Object recognition
- Ankara Yıldırım Beyazıt Üniversitesi Adresli: Hayır
Özet
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. © 2006 Springer Science + Business Media, LLC.