Robust and Fast Spatial Verification

Abstract:

Spatial verification for object retrieval is often time-consuming and susceptible to viewpoint changes. In this paper, we propose a novel spatial verification method that is robust to viewpoint changes. Firstly, the affine covariant neighborhoods (ACNs) of corresponding local regions are matched to eliminate possible false matches. Secondly, the RANSAC is performed to estimate the affine transformation from each single pair of corresponding local regions without the gravity vector assumption used in previous spatial verification methods. Experimental results demonstrate that this method is more robust and fast than previous spatial verification methods.

• Periodical: Applied Mechanics and Materials (Volume 109)
• Pages: 466-470
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.109.466
• Online since: October 2011
• Authors: Wen Ying Wang, Ru Jiang Guo, Hui Yu, Si Rui Tian
• Keywords: Affine Transformation, Object Retrieval, Spatial Verification, Visual Words

References

[1] J. Sivic and A. Zisserman, "Efficient Visual Search of Videos Cast as Text Retrieval," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, pp.591-606, 2009.

DOI: 10.1109/tpami.2008.111

[2] J. Sivic and A. Zisserman, "Video Google: a text retrieval approach to object matching in videos," in International Conference on Computer Vision, Washington D C, 2003, pp.1470-1477.

DOI: 10.1109/iccv.2003.1238663

[3] D. Nister and H. Stewenius, "Scalable recognition with a vocabulary tree," in IEEE Conference on Computer Vision and Pattern Recognition, New York 2006, pp.2161-2168.

DOI: 10.1109/cvpr.2006.264

[4] O. Chum, M. Perdoch, and J. Matas, "Geometric min-Hashing- Finding a (Thick) Needle in a Haystack," in IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009, pp.17-24.

DOI: 10.1109/cvpr.2009.5206531

[5] H. Jegou, M. Douze, and C. Schmid, "Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search," in 10th European Conference on Computer Vision, Marseille, France 2008, pp.304-317.

DOI: 10.1007/978-3-540-88682-2_24

[6] Wenying Wang, D. Zhang, Y. Zhang, and J. Li, "Fast and Robust Spatial Matching for Object Retrieval," in IEEE International Conference on Acoustics, Speech, and Signal Processing, 2010.

DOI: 10.1109/icassp.2010.5495402

[7] Wenying Wang, D. Zhang, Y. Zhang, and J. Li "Parallel spatial matching for object retrieval implemented on GPU," in IEEE International Conference on Multimedia & Expo 2010.

DOI: 10.1109/icme.2010.5582930

[8] D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," International Journal of Computer Vision, vol. 60, pp.91-110, 2004.

DOI: 10.1023/b:visi.0000029664.99615.94

[9] J. Philbin, O. Chum, M. Isard, J. Sivic, and A. Zisserman, "Object retrieval with large vocabularies and fast spatial matching," in Conference on Computer Vision and Pattern Recognition, Minneapolis, 2007, pp.1-8.

DOI: 10.1109/cvpr.2007.383172

[10] O. Chum and J. Matas, "Locally Optimized RANSAC " presented at the DAGM symposium Magdeburg, 2003.

[11] M. Perd'och, O. Chum, and J. Matas, "Efficient representation of local geometry for large scale object retrieval," in IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009.

DOI: 10.1109/cvpr.2009.5206529

[12] M. A. Fischler and R. C. Bolles, "Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography," Communications of ACM, vol. 24, p.381–395, 1981.

DOI: 10.1145/358669.358692

[13] D. G. Lowe, "Object recognition from local scale-invariant features," in International Conference on Computer Vision, Kerkyra, 1999, pp.1150-1157.

DOI: 10.1109/iccv.1999.790410

[14] D. H. Ballarda, "Generalizing the Hough transform to detect arbitrary shapes," Pattern Recognition, vol. 13, pp.111-122, 1981.

DOI: 10.1016/0031-3203(81)90009-1