| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Flexible Spatial Configuration of Local Image Features
December 2007 (vol. 29 no. 12)
pp. 2089-2104
Local image features have been designed to be informative and repeatable under rigid transformations and illumination deformations. Even though current state-of-the-art local image features present a high degree of repeatability, their local appearance alone usually does not bring enough discriminative power to support a reliable matching, resulting in a relatively high number of mismatches in the correspondence set formed during the data association procedure. As a result, geometric filters, commonly based on global spatial configuration, have been used to reduce this number of mismatches. However, this approach presents a trade off between the effectiveness to reject mismatches and the robustness to non-rigid deformations. In this paper, we propose two geometric filters, based on semilocal spatial configuration of local features, that are designed to be robust to non-rigid deformations and to rigid transformations, without compromising its efficacy to reject mismatches. We compare our methods to the Hough transform, which is an efficient and effective mismatch rejection step based on global spatial configuration of features. In these comparisons, our methods are shown to be more effective in the task of rejecting mismatches for rigid transformations and non-rigid deformations at comparable time complexity figures. Finally, we demonstrate how to integrate these methods in a probabilistic recognition system such that the final verification step uses not only the similarity between features, but also their semi-local configuration.
[1] 2089 S. Agarwal and D. Roth, “Learning a Sparse Representation for Object Detection,” Proc. Seventh European Conf. Computer Vision, pp. 113-130, 2002.[2] Y. Amit and D. Geman, “A Computational Model for Visual Selection,” Neural Computation, vol. 11, pp. 1691-1715, 1999.[3] H. Barrow and R. Popplestone, “Relational Descriptions in Picture Processing,” Machine Intelligence, vol. 6, 1971.[4] S. Belongie, J. Malik, and J. Puzicha, “Shape Matching and Object Recognition Using Shape Contexts,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 4, pp. 509-522, Apr. 2002.[5] A. Berg, T. Berg, and J. Malik, “Shape Matching and Object Recognition Using Low Distortion Correspondences,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005.[6] K.L. Boyer and S. Sarkar, Perceptual Organization for Artificial Vision Systems. Kluwer Academic, 2000.[7] R. Brooks, “Model-Based 3D Interpretations of 2D Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 5, no. 2, pp.140-150, 1983.[8] G. Carneiro and A. Jepson, “Multi-Scale Phase-Based Local Features,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2003.[9] G. Carneiro and A. Jepson, “Flexible Spatial Models for Grouping Local Image Features,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2004.[10] G. Carneiro and A. Jepson, “Pruning Local Feature Correspondences Using Shape Context,” Proc. 17th IEEE Int'l Conf. Pattern Recognition, Aug. 2004.[11] G. Carneiro and A. Jepson, “The Distinctiveness, Detectability, and Robustness of Local Image Features,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2005.[12] C. Huang, O. Camps, and T. Kanungo, “Object Recognition Using Appearance-Based Parts and Relations,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 877-883, 1997.[13] O. Chum, J. Matas, and S. Obdrzalek, “Epipolar Geometry from Three Correspondences,” Proc. Eighth Computer Vision Winter Workshop, 2003.[14] S. Dickinson, A. Pentland, and A. Rosenfeld, “3D Shape Recovery Using Distributed Aspect Matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 174-198, Feb. 1992.[15] P. Felzenszwalb and D. Huttenlocher, “Efficient Matching of Pictorial Structures,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 66-75, 2000.[16] R. Fergus, P. Perona, and A. Zisserman, “Object Class Recognition by Unsupervised Scale-Invariant Learning,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2003.[17] V. Ferrari, T. Tuytelaars, and L.V. Gool, “Simultaneous Object Recognition and Segmentation by Image Exploration,” Proc. Eighth European Conf. Computer Vision, 2004.[18] D. Fleet, Measurement of Image Velocity. Kluwer Academic, 1992.[19] W. Freeman and E. Adelson, “The Design and Use of Steerable Filters,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 9, pp. 891-906, Sept. 1991.[20] C. Harris and M. Stephens, “A Combined Corner and Edge Detector,” Proc. Fourth Alvey Vision Conf., 1988.[21] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge Univ. Press, 2000.[22] B. Huet and E. Hancock, “Relational Object Recognition from Large Structural Libraries,” Pattern Recognition, vol. 35, pp. 1895-1915, 2002.[23] M. Lades, J.C. Vorbruggen, J. Buhmann, J. Lange, C.v.d. Malsburg, R.P. Wurtz, and W. Konen, “Distortion Invariant Object Recognition in the Dynamic Link Architecture,” IEEE Trans. Computers, vol. 42, pp. 300-311, 1993.[24] D. Lowe, “Three-Dimensional Object Recognition from Single Two-Dimensional Images,” Artificial Intelligence, vol. 31, no. 3, pp.355-395, 1987.[25] D. Lowe, “Object Recognition from Local Scale-Invariant Features,” Proc. Seventh Int'l Conf. Computer Vision, pp. 1150-1157, Sept. 1999.[26] D. Lowe, “Local Feature View Clustering for 3D Object Recognition,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2001.[27] K. Mikolajczyk, A. Zisserman, and C. Schmid, “Shape Recognition with Edge-Based Features,” Proc. 14th British Machine Vision Conf., 2003.[28] E. Mortensen, H. Deng, and L. Shapiro, “A Sift Descriptor with Global Context,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '05), 2005.[29] H. Murase and S. Nayar, “Visual Learning and Recognition of 3D Objects from Appearance,” Int'l J. Computer Vision, vol. 14, no. 1, pp. 5-24, 1995.[30] J. Pilet, V. Lepetit, and P. Fua, “Real-Time Non-Rigid Surface Detection,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005.[31] A. Pope and D. Lowe, “Probabilistic Models of Appearance for 3D Object Recognition,” Int'l J. Computer Vision, vol. 40, no. 2, pp. 149-167, 2000.[32] P. Pritchett and A. Zisserman, “Wide Baseline Stereo Matching,” Proc. Sixth Int'l Conf. Computer Vision, pp. 754-760, 1998.[33] F. Schaffalitzky and A. Zisserman, “Automated Scene Matching in Movies,” Proc. Int'l Conf. Image and Video Retrieval, pp. 186-197, 2002.[34] C. Schmid, “A Structured Probabilistic Model for Recognition,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 485-490, 1999.[35] C. Schmid and R. Mohr, “Local Grayvalue Invariants for Image Retrieval,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 5, pp. 530-535, May 1997.[36] A. Shokoufandeh, S. Dickinson, C. Jonsson, L. Bretzner, and T. Lindeberg, “On the Representation and Matching of Qualitative Shape at Multiple Scales,” Proc. Seventh European Conf. Computer Vision, 2002.[37] A. Shokoufandeh, I. Marsic, and S. Dickinson, “View-Based Object Recognition Using Saliency Maps,” Image and Vision Computing, vol. 17, pp. 445-460, 1999.[38] J. Sivic, F. Schaffalitzky, and A. Zisserman, “Object Level Grouping for Video Shots,” Proc. Eighth European Conf. Computer Vision, 2004.[39] D. Tell and S. Carlsson, “Wide Baseline Point Matching Using Affine Invariants Computed from Intensity Profiles,” Proc. Sixth European Conf. Computer Vision, pp. 814-828, 2000.[40] D. Tell and S. Carlsson, “Combining Appearance and Topology for Wide Baseline Matching,” Proc. Seventh European Conf. Computer Vision, pp. 68-81, 2002.[41] P. Torr and D. Murray, “The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix,” Int'l J.Computer Vision, vol. 24, no. 3, pp. 271-300, 1997.[42] T. Tuytelaars and L. Van Gool, “Wide Baseline Stereo Matching Based on Local, Affinely Invariant Regions,” Proc. 11th British Machine Vision Conf., 2000.[43] M. Weber, M. Welling, and P. Perona, “Unsupervised Learning of Models for Recognition,” Proc. Sixth European Conf. Computer Vision, pp. 18-32, 2000.[44] S. Yu, R. Gross, and J. Shi, “Concurrent Object Recognition and Segmentation by Graph Partitioning,” Neural Information Processing Systems, Dec. 2002.[45] Z. Zhang, R. Deriche, O.D. Faugeras, and Q. Luong, “A Robust Technique for Matching Two Uncalibrated Images through the Recovery of the Unknown Epipolar Geometry,” Artificial Intelligence, vol. 78, nos. 1-2, pp. 87-119, 1995.
Index Terms:
Local image feature, Feature clustering, Visual object recognition, Wide baseline matching, Long range matching
Citation:
Gustavo Carneiro, Allan D. Jepson, "Flexible Spatial Configuration of Local Image Features," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 12, pp. 2089-2104, June 2007, doi:10.1109/TPAMI.2007.1126
