Feature correspondence via graph matching: Models and global optimization Conference Paper

Author(s): Torresani, Lorenzo; Kolmogorov, Vladimir; Rother, Carsten
Title: Feature correspondence via graph matching: Models and global optimization
Title Series: LNCS
Abstract: In this paper we present a new approach for establishing correspondences between sparse image features related by an unknown non-rigid mapping and corrupted by clutter and occlusion, such as points extracted from a pair of images containing a human figure in distinct poses. We formulate this matching task as an energy minimization problem by defining a complex objective function of the appearance and the spatial arrangement of the features. Optimization of this energy is an instance of graph matching, which is in general a NP-hard problem. We describe a novel graph matching optimization technique, which we refer to as dual decomposition (DD), and demonstrate on a variety of examples that this method outperforms existing graph matching algorithms. In the majority of our examples DD is able to find the global minimum within a minute. The ability to globally optimize the objective allows us to accurately learn the parameters of our matching model from training examples. We show on several matching tasks that our learned model yields results superior to those of state-of-the-art methods.
Keywords: Image processing; computational geometry; Optimization; Computer vision; Pattern matching
Conference Title: ECCV: European Conference on Computer Vision
Volume: 5303
Conference Dates: October 12-18, 2008
Conference Location: Marseille, France
Publisher: Springer  
Date Published: 2008-01-01
Start Page: 596
End Page: 609
DOI: 10.1007/978-3-540-88688-4_44
Open access: no
IST Austria Authors
Related IST Austria Work