Summary
Credibility of individual keypoint correspondences is very low when images of unpredictable contents are matched. The paper proposes a method which dramatically improves it with very small memory overheads in the database image representation. Assuming that affine-invariant (i.e. elliptical) keypoints are used, we introduce the idea of keypoint co-affinity based on properties of elliptical keypoint pairs. Experimental results show the probability that pairs of similar co-affine keypoints belong to near-duplicate objects in the matched images is 15-30 times higher than for pairs of keypoints which are just similar.
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.
Similar content being viewed by others
References
Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. 7th IEEE Int. Conf. Computer Vision, vol. 2, pp. 1150–1157 (1999)
Islam, M.S., Śluzek, A.: Relative scale method to locate an object in cluttered environment. Image and Vision Computing 26(2), 259–274 (2008)
Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. IEEE Trans. PAMI 19(5), 530–535 (1997)
Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. Int. J. of Comp. Vision 60(2), 63–86 (2004)
Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. British Machine Vision Conf. BMVC 2002, pp. 384–393 (2002)
Paradowski, M., Śluzek, A.: Local keypoints and global affine geometry: Triangles and ellipses for image fragment matching. In: Kwaśnicka, H., Jain, L.C. (eds.) Innovations in Intelligent Image Analysis. SCI, vol. 339, pp. 195–224. Springer, Heidelberg (2011)
Xiao, J., Shah, M.: Two-frame wide baseline matching. In: Proc. 9th IEEE Int. Conf. on Computer Vision, pp. 603–609 (2003)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. of Comp. Vision 60(2), 91–110 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Śluzek, A., Paradowski, M. (2011). Improved Credibility of Keypoint Matching by Using Co-affine Pairs of Ellipses. In: Choraś, R.S. (eds) Image Processing and Communications Challenges 3. Advances in Intelligent and Soft Computing, vol 102. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23154-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-23154-4_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23153-7
Online ISBN: 978-3-642-23154-4
eBook Packages: EngineeringEngineering (R0)