Balanced feature matching in probabilistic framework and its application on object localisation

A new algorithm of feature matching is proposed after balancing analysis of adjacency matrix of the matching model in a probabilistic framework. Considering all the interaction of the two feature point sets, a probabilistic model is established and solved using random walks with restart RWR. To reduce the influence of deformation, and increase the accuracy of feature matching algorithm, a balancing analysis to the adjacency matrix of RWR is taken. Then an efficient method for bidirectional balance is presented, which makes the relevance weight between each two correspondence candidates balanced. The approach considers not only all the correspondence candidates of the two feature point sets, but also the geometrical relation between each pair of candidates. It improves the discriminative and accuracy performance of matching. Compared with other state-of-the-art algorithms, the method is more robust to outliers and geometric deformation, and is accurate in terms of matching rate in various matching applications, such as object localisation.

[1]  Vladimir Kolmogorov,et al.  Feature Correspondence Via Graph Matching: Models and Global Optimization , 2008, ECCV.

[2]  Hoi-Jun Yoo,et al.  A 345 mW Heterogeneous Many-Core Processor With an Intelligent Inference Engine for Robust Object Recognition , 2011, IEEE J. Solid State Circuits.

[3]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[4]  Amnon Shashua,et al.  Probabilistic graph and hypergraph matching , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Jean-Francois Mangin,et al.  Multisubject Non-rigid Registration of Brain MRI Using Intensity and Geometric Features , 2001, MICCAI.

[6]  Qing Wang,et al.  Partially occluded object recognition , 2011, Int. J. Comput. Appl. Technol..

[7]  Roberto Marcondes Cesar Junior,et al.  Sparse Representations for Efficient Shape Matching , 2010, 2010 23rd SIBGRAPI Conference on Graphics, Patterns and Images.

[8]  Sujoy Roy,et al.  Region-based image registration for mosaicking , 2010, Int. J. Comput. Appl. Technol..

[9]  Hong Wei Gao,et al.  Image Mosaics Algorithm Based on PSO and SIFT , 2011 .

[10]  Wesley E. Snyder,et al.  Global registration of overlapping images using accumulative image features , 2010, Pattern Recognit. Lett..

[11]  Zhang Guimin,et al.  An automatic method for image mosaic based on feature matching , 2011, 2011 International Conference on Electric Information and Control Engineering.

[12]  Christos Faloutsos,et al.  Random walk with restart: fast solutions and applications , 2008, Knowledge and Information Systems.

[13]  Jianbo Shi,et al.  Balanced Graph Matching , 2006, NIPS.

[14]  Guillermo Sapiro,et al.  A Gromov-Hausdorff Framework with Diffusion Geometry for Topologically-Robust Non-rigid Shape Matching , 2010, International Journal of Computer Vision.

[15]  Sang Uk Lee,et al.  A Probabilistic Model for Correspondence Problems Using Random Walks with Restart , 2009, ACCV.

[16]  Xiaojie Guo,et al.  Monomodal registration with adaptive parameter computing , 2011, Int. J. Comput. Appl. Technol..

[17]  M. Fatih Demirci,et al.  Efficient many-to-many feature matching under the l1 norm , 2011, Comput. Vis. Image Underst..

[18]  Richard Sinkhorn,et al.  Concerning nonnegative matrices and doubly stochastic matrices , 1967 .

[19]  Esa Rahtu,et al.  Object recognition and segmentation by non-rigid quasi-dense matching , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.