A FRAMEWORK TO IMPROVE MATCHING RESULTS OF WIDELY SEPARATED VIEWS

Cosmin Ancuti, Codruta Orniana Ancuti, Philippe Bekaert

2010

Abstract

Matching images is a crucial step in many computer vision applications. In this paper we present an alternative strategy built on the SIFT operator to solve the problem of wide-baseline matching. We first show how to add the color information to the SIFT descriptors of extracted keypoints. Practically, the SIFT descriptor vector is blended with the main parameters (contrast, correlation and energy) of the color co-occurrence histogram computed in the same image patch. Afterward, in order to better improve the matching results of images taken under large variations of the camera viewpoint angle, the valid matches obtained by the previous strategy are employed to estimate the geometry between patches of corresponding keypoints. This overcomes the lack of affine invariance of the existing operators (including SIFT), allowing to use a more appropriate region shape where descriptors will be calculated for better preciseness. In our experiments the proposed method shows a substantial improvement of the matching results compared with the results obtained by the original local operator.

References

  1. Abdel-Hakim, A. E. and Farag, A. A. (2006). CSIFT: A sift descriptor with color invariant characteristics. IEEE CVPR.
  2. Baumberg, A. (2000). Reliable feature matching across widely separated views. IEEE Conf. on Computer Vision and Pattern Recog., CVPR.
  3. Bay, H., Tuytelaars, T., and Gool, L. V. (2006). SURF: Speeded up robust features. in Proceedings of European Conference on Computer Vision, pages 404-417.
  4. Belongie, S., Malik, J., and Puzicha, J. (2002). Shape matching and object recognition using shape contexts. IEEE Tran. on Patt. Anal. and Mach. Intell.
  5. C.G.Harris and Stephens, M. (1988). A combined corner and edge detector. in Proceedings of Fourth Alvey Vision Conference, 18:147-151.
  6. Chang, P. and Krumm, J. (1999). Object recognition with color cooccurrence histograms. IEEE Conf. on Computer Vision and Pattern Recog., CVPR.
  7. Forssén, P.-E. and Lowe, D. (2007). Shape descriptors for maximally stable extremal regions. In IEEE International Conference on Computer Vision.
  8. Freeman, W. and Adelson, E. (1991). The design and use of steerable filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13:891-906.
  9. Haralick, R. M., Shanmugam, K., and Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics.
  10. Ke, Y. and Sukthankar, R. (2004). PCA-SIFT: A more distinctive representation for local image descriptors. IEEE CVPR.
  11. Lindeberg, T. (1999). Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2):77-116.
  12. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. In International Journal of Computer Vision, volume 20, pages 91-110.
  13. Matas, J., Chum, O., Martin, U., and Pajdla, T. (2002). Robust wide baseline stereo from maximally stable extremal regions. In BMVC.
  14. Mikolajczyk, K. and Schmid, C. (2004a). A performance evaluation of local descriptors. IEEE Conf. on Comp. Vision and Pattern Recog.
  15. Mikolajczyk, K. and Schmid, C. (2004b). Scale & affine invariant interest point detectors. Int. J. Comput. Vision, 60(1).
  16. Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., and Gool, L. V. (2005). A comparison of affine region detectors. Int. J. Comp. Vision,.
  17. Moreels, P. and Perona, P. (2007). Evaluation of features detectors and descriptors based on 3d objects. Int. J. Comput. Vision, 73(3):263-284.
  18. Pritchett, P. and Zisserman, A. (1998). Wide baseline stereo matching. In IEEE ICCV.
  19. Schmid, C., Mohr, R., and Bauckhage, C. (2000). Evaluation of interest point detectors. International Journal of Computer Vision, pages 151-172.
  20. Tuytelaars, T. and Gool, L. V. (2000). Wide baseline stereo matching based on local, affinely invariant regions. In Proceedings of British Machine Vision Conference.
  21. Tuytelaars, T. and Gool, L. V. (2004). Matching widely separated views based on affine invariant regions. Int. J. Comput. Vision, 59(1).
  22. Xiao, J. and Shah, M. (2003). Two-frame wide baseline matching. IEEE Int. Conf. on Comp. Vision.
Download


Paper Citation


in Harvard Style

Ancuti C., Orniana Ancuti C. and Bekaert P. (2010). A FRAMEWORK TO IMPROVE MATCHING RESULTS OF WIDELY SEPARATED VIEWS . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 475-479. DOI: 10.5220/0002843004750479


in Bibtex Style

@conference{visapp10,
author={Cosmin Ancuti and Codruta Orniana Ancuti and Philippe Bekaert},
title={A FRAMEWORK TO IMPROVE MATCHING RESULTS OF WIDELY SEPARATED VIEWS},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={475-479},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002843004750479},
isbn={978-989-674-028-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - A FRAMEWORK TO IMPROVE MATCHING RESULTS OF WIDELY SEPARATED VIEWS
SN - 978-989-674-028-3
AU - Ancuti C.
AU - Orniana Ancuti C.
AU - Bekaert P.
PY - 2010
SP - 475
EP - 479
DO - 10.5220/0002843004750479