This Article 
 Bibliographic References 
 Add to: 
A Dual Decomposition Approach to Feature Correspondence
Feb. 2013 (vol. 35 no. 2)
pp. 259-271
L. Torresani, Dept. of Comput. Sci., Dartmouth Coll., Hanover, NH, USA
V. Kolmogorov, Inst. of Sci. & Technol., IST Austria, Klosterneuburg, Austria
C. Rother, Microsoft Res. Cambridge, Cambridge, UK
In this paper, we present a new approach for establishing correspondences between sparse image features related by an unknown nonrigid mapping and corrupted by clutter and occlusion, such as points extracted from images of different instances of the same object category. We formulate this matching task as an energy minimization problem by defining an elaborate 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 an 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.
Index Terms:
minimisation,computational complexity,feature extraction,graph theory,image matching,learned model,dual decomposition approach,feature correspondence,sparse image features,unknown nonrigid mapping,extracted image points,object category,energy minimization problem,matching task,objective function,NP-hard problem,graph matching optimization technique,dual decomposition,DD,Vectors,Optimization,Labeling,Computational modeling,Indexes,Feature extraction,Minimization,dual decomposition,Graph matching,feature correspondence
L. Torresani, V. Kolmogorov, C. Rother, "A Dual Decomposition Approach to Feature Correspondence," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 2, pp. 259-271, Feb. 2013, doi:10.1109/TPAMI.2012.105
Usage of this product signifies your acceptance of the Terms of Use.