Files and links (1)
SubmittedOpen Access (License Unspecified), Open
Journal article
Object Recognition as Many-to-Many Feature Matching
International journal of computer vision, v 69(2)
Aug 2006
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
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.
Metrics
Details
- Title
- Object Recognition as Many-to-Many Feature Matching
- Creators
- M Demirci - Department of Computer Science Drexel University Philadelphia PA 19104 USAAli Shokoufandeh - Department of Computer Science Drexel University Philadelphia PA 19104 USAYakov Keselman - School of Computer Science, Telecommunications and Information Systems DePaul University Chicago IL 60604 USALars Bretzner - Department of Numerical Analysis and Computer Science, KTH Computational Vision and Active Perception Laboratory Stockholm SwedenSven Dickinson - Department of Computer Science University of Toronto Toronto Ontario Canada M5S 3G4
- Publication Details
- International journal of computer vision, v 69(2)
- Publisher
- Kluwer Academic Publishers; Boston
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:000239162400003
- Scopus ID
- 2-s2.0-33744551438
- Other Identifier
- 991014877752304721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence