Multi-Graph Matching via Affinity Optimization with Graduated Consistency Regularization
Year: 2015
Type: article
Abstract: This paper addresses the problem of matching common node correspondences among multiple graphs referring to an identical or related structure. This multi-graph matching problem involves two correlated components: i) the local pairwise matching affinity across pairs of graphs; ii) the global matching consistency that measures the uniqueness of the pairwise matchings by different composition orders. Previous studies typically either enforce the matching consistency constraints in the beginning of an iterative optimization, which may propagate matching error both over iterations and across graph pairs; or separate affinity optimization and consistency enforcement into two steps. This paper is motivated by the observation that matching consistency can serve as a regularizer in the affinity objective function especially when the function is biased due to noises or inappropriate modeling. We propose composition-based multi-graph matching methods to incorporate the two aspects by optimizing the affinity score, meanwhile gradually infusing the consistency. We also propose two mechanisms to elicit the common inliers against outliers. Compelling results on synthetic and real images show the competency of our algorithms.
Institutions: IBM (United States), Shanghai Jiao Tong University, Shanghai Key Laboratory of Digital Media Processing and Transmission, Institut national de recherche en sciences et technologies du numérique, WILLOW: Vision par ordinateur incarnée, Georgia Institute of Technology, East China Normal University, IBM Research - Thomas J. Watson Research Center
Language: English
Topic: Graph Theory and Algorithms
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Keywords: outlier removal, inlier selection, graph matching
Open Access status: hybrid
Estimated APC paid: $2,645
OpenAlex ID: W2369976370
