Abstract
The main objective in content-based image retrieval is to find images similar to a query image in an image collection. Matching using descriptors computed from regions centered at local invariant interest points (keypoints) have become popular because of their robustness to changes in viewpoint and occlusion. However, local descriptor matching can produce many false matches. To improve the retrieval results, geometric verification is usually performed as a post-pocessing step. RANSAC can robustly fit a model to data in presence of outliers and has been widely used for the geometric verification stage. But obtaining a good hypothesis may require many trial runs, particularly when the proportion of inliers in the data is low. We introduce a novel geometric verification scheme called DT-RANSAC based on topological information in the Delaunay Triangulation of putatively matched keypoints to construct a refined set of matches, that is presented to the RANSAC algorithm to fit a homography. Experiments reveal that DT-RANSAC is able to converge to correct hypothesis in very few trial runs and the retrieval results are consistently better than geometric verification based on plain RANSAC.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Beaudet, P.R.: Rotationally invariant image operators. In: International Joint Conference on Pattern Recognition, pp. 579–583 (1978)
Bhattacharya, P., Gavrilova, M.L.: Voronoi diagram in optimal path planning. In: ISVD, pp. 38–47 (2007)
Bhattachariya, P., Gavrilova, M.L.: Roadmap-Based Path Planning - Using the Voronoi Diagram for a Clearance-Based Shortest Path. IEEE Robotics and Automation Magazine (IEEE RAM), Special Issue on Computational Geometry in Robotics 15(2), 58–66 (2008)
Bhattacharya, P., Gavrilova, M.L.: CRYSTAL - A new density-based fast and efficient clustering algorithm. In: ISVD, pp. 102–111 (2006)
Brown, M., Szeliski, R., Winder, S.: Multi-image matching using multi-scale oriented patches. In: CVPR (2005)
Chum, O., Matas, J., Kittler, J.: Locally optimized RANSAC. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 236–243. Springer, Heidelberg (2003)
Mikolajczyk, K., et al.: A comparison of affine region detectors. IJCV 65, 43–72 (2005)
Fischler, M.A., Bolles, R.C.: Random Sample Consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 304–317. Springer, Heidelberg (2008)
Kovesi, P.D.: MATLAB and Octave functions for computer vision and image processing. Centre for Exploration Targeting, School of Earth and Environment, The University of Western Australia, http://www.csse.uwa.edu.au/~pk/research/matlabfns/
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV, 91–110 (2004)
Luchnikov, V.A., Gavrilova, M.L., Medvedev, N.N., Voloshin, V.P.: The Voronoi-Delaunay approach for the free volume analysis of a packing of balls in a cylindrical container. Future Generation Comp. Syst. 18(5), 673–679 (2002)
Mikolajczyk, K.: Scale and affine invariant interest point detectors. PhD thesis (2002)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: CVPR (2003)
Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. IJCV 60(1), 63–86 (2004)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR (2007)
Raguram, R., Frahm, J.-M., Pollefeys, M.: A comparative analysis of RANSAC techniques leading to adaptive real-time Random Sample Consensus. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 500–513. Springer, Heidelberg (2008)
Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: ICCV, pp. 1470–1477 (2003)
Turcot, P., Lowe, D.G.: Better matching with fewer features: The selection of useful features in large database recognition problems. In: ICCV Workshop on Emergent Issues in Large Amounts of Visual Data, WS-LAVD (2009)
Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: A survey. Foundations and Trends in Computer Graphics and Vision 3(3), 177–280 (2008)
Vedaldi, A., Fulkerson, B.: VlFeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/ (last accessed 2012)
Xuan, K., Zhao, G., Taniar, D., Srinivasan, B., Safar, M., Gavrilova, M.L.: Network Voronoi Diagram Based Range Search. In: International Conference on Advanced Information Networking and Applications, pp. 741–748 (2009)
Zhang, Y., Jia, Z., Chen, T.: Image retrieval with geometry-preserving visual phrases. In: CVPR, pp. 809–816 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Bhattacharya, P., Gavrilova, M. (2013). DT-RANSAC: A Delaunay Triangulation Based Scheme for Improved RANSAC Feature Matching. In: Gavrilova, M.L., Tan, C.J.K., Kalantari, B. (eds) Transactions on Computational Science XX. Lecture Notes in Computer Science, vol 8110. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41905-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-41905-8_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41904-1
Online ISBN: 978-3-642-41905-8
eBook Packages: Computer ScienceComputer Science (R0)