The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.09 - September (2010 vol.32)
pp: 1568-1581
Jan Čech , Czech Technical University, Prague
Jiří Matas , Czech Technical University, Prague
Michal Perdoch , Czech Technical University, Prague
ABSTRACT
In many retrieval, object recognition, and wide-baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that 1) has high precision (is highly discriminative), 2) has good recall, and 3) is fast. The sequential decision on the correctness of a correspondence is based on simple statistics of a modified dense stereo matching algorithm. The statistics are projected on a prominent discriminative direction by SVM. Wald's sequential probability ratio test is performed on the SVM projection computed on progressively larger cosegmented regions. We show experimentally that the proposed sequential correspondence verification (SCV) algorithm significantly outperforms the standard correspondence selection method based on SIFT distance ratios on challenging matching problems.
INDEX TERMS
Correspondence, matching, verification, sequential decision, growing, cosegmentation, stereo, image retrieval, learning.
CITATION
Jan Čech, Jiří Matas, Michal Perdoch, "Efficient Sequential Correspondence Selection by Cosegmentation", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.32, no. 9, pp. 1568-1581, September 2010, doi:10.1109/TPAMI.2009.176
REFERENCES
[1] D. Lowe, "Distinctive Image Features from Scale Invariant Keypoints," Int'l J. Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[2] J. Sivic and A. Zisserman, "Video Google: A Text Retrieval Approach to Object Matching in Videos," Proc. IEEE Int'l Conf. Computer Vision, pp. 1470-1477, 2003.
[3] B. Leibe, K. Mikolajczyk, and B. Schiele, "Efficient Clustering and Matching for Object Class Recognition," Proc. British Machine Vision Conf., 2006.
[4] D. Nister and H. Stewenius, "Scalable Recognition with a Vocabulary Tree," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 2161-2168, 2006.
[5] J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman, "Object Retrieval with Large Vocabularies and Fast Spatial Matching," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007.
[6] O. Chum, J. Philbin, J. Sivic, M. Isard, and A. Zisserman, "Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval," Proc. IEEE Int'l Conf. Computer Vision, 2007.
[7] T. Tuytelaars and L.V. Gool, "Wide Baseline Stereo Matching Based on Local, Affinely Invariant Regions," Proc. British Machine Vision Conf., pp. 412-425, 2000.
[8] J. Matas, O. Chum, M. Urban, and T. Pajdla, "Robust Wide Baseline Stereo from Maximally Stable Extremal Regions," Image and Vision Computing, vol. 22, no. 10, pp. 761-767, 2004.
[9] A. Vedaldi and S. Soatto, "Local Features, All Grown Up," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1753-1760, 2006.
[10] V. Ferrari, T. Tuytelaars, and L. van Gool, "Simultaneous Object Recognition and Segmentation from Single or Multiple Image Views," Int'l J. Computer Vision, vol. 67, no. 2, pp. 159-188, 2006.
[11] G. Yang, C.V. Stewart, M. Sofka, and C.-L. Tsai, "Registration of Challenging Image Pairs: Initialization, Estimation, and Decision," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 11, pp. 1973-1989, Nov. 2007.
[12] C.V. Stewart, C.-L. Tsai, and B. Roysam, "The Dual-Bootstrap Iterative Closest Point Algorithm with Application to Retinal Image Registration," Medical Imaging, vol. 22, no. 11, pp. 1379-1394, 2003.
[13] M. Lhuillier and L. Quan, "Match Propagation for Image-Based Modeling and Rendering," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 8, pp. 1140-1146, Aug. 2002.
[14] C. Rother, V. Kolmogorov, T. Minka, and A. Blake, "Cosegmentation of Image Pairs by Histogram Matching—Incorporating a Global Constraint into MRFs," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2006.
[15] J. Cech, J. Matas, and M. Perdoch, "Efficient Sequential Correspondence Selection by Cosegmentation," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[16] J. Cech and R. Sara, "Efficient Sampling of Disparity Space for Fast and Accurate Matching," Proc. BenCOS Workshop at IEEE Conf. Computer Vision and Pattern Recognition, 2007.
[17] G.P. Otto and T.K.W. Chau, "'Region-Growing' Algorithm for Matching of Terrain Images," Image and Vision Computing, vol. 7, no. 2, pp. 83-94, 1989.
[18] Z. Megyesi, G. Kos, and D. Chetverikov, "Dense 3D Reconstruction from Images by Normal Aided Matching," Machine Graphics and Vision, vol. 15, pp. 3-28, 2006.
[19] S. Obdrzalek and J. Matas, "Sub-Linear Indexing for Large Scale Object Recognition," Proc. British Machine Vision Conf., 2005.
[20] J. Matas, O. Chum, M. Urban, and T. Pajdla, "Robust Wide Baseline Stereo from Maximally Stable Extremal Regions," Proc. British Machine Vision Conf., pp. 384-393, 2002.
[21] F. Schaffalitzky and A. Zisserman, "Multi-View Matching for Unordered Image Sets, or How Do I Organize My Holiday Snaps?" Proc. European Conf. Computer Vision, pp. 414-431, 2002.
[22] H.P. Moravec, "Towards Automatic Visual Obstacle Avoidance," Proc. Int'l Joint Conf. Artificial Intelligence, p. 584, 1977.
[23] J. Kannala, E. Rahtu, S.S. Brandt, and J. Heikkila, "Object Recognition and Segmentation by Non-Rigid Quasi-Dense Matching," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007.
[24] V. Kolmogorov and R. Zabih, "Computing Visual Correspondence with Occlusions Using Graph Cuts," Proc. IEEE Int'l Conf. Computer Vision, pp. 508-515, 2001.
[25] V.N. Vapnik, The Nature of Statistical Learning Theory. Springer Verlag, 1995.
[26] J.C. Platt, "Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods," Advances in Large Margin Classifiers, pp. 61-74, MIT Press, 1999.
[27] A. Wald, Sequential Analysis. Dover, 1947.
[28] V. Franc and S. Sonnenburg, "OCAS Optimized Cutting Plane Algorithm for Support Vector Machines," Proc. Int'l Machine Learning Conf., 2008.
[29] O. Chum and J. Matas, "Matching with PROSAC—Progressive Sample Consensus," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 220-226, 2005.
[30] K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. Van Gool, "A Comparison of Affine Region Detectors," Int'l J. Computer Vision, vol. 65, nos. 1/2, pp. 43-72, 2005.
[31] K. Mikolajczyk and C. Schmid, "A Performance Evaluation of Local Descriptors," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 10, pp. 1615-1630, Oct. 2005.
[32] O. Chum, M. Perdoch, and J. Matas, "Geometric Min-Hashing: Finding a (Thick) Needle in a Haystack," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009.
14 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool