DMCA
Object Recognition as Many-to-Many Feature Matching (2006)
| Citations: | 48 - 4 self |
BibTeX
@MISC{Demirci06objectrecognition,
author = {M. Fatih Demirci and Ali Shokoufandeh and Yakov Keselman and Lars Bretzner and Sven Dickinson},
title = { Object Recognition as Many-to-Many Feature Matching},
year = {2006}
}
Share
 |
 |
 |
 |
||
OpenURL
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-tomany. 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.
Keyphrases
object recognition many-to-many feature matching many-to-many matching normed vector space many-to-many correspondence initial weighted graph match one-to-one distance framework recognition trial matching algorithm overall approach low distortion matching image feature within-class deformation model feature segmentation error graph structure spherical encoding scale difference earth mover graph-based representation feature correspondence many-to-many vector correspondence weighted graph graph node empirical evaluation novel embedding technique extensive set weighted point set
