Advertisement

Interpreting the Ratio Criterion for Matching SIFT Descriptors

  • Avi KaplanEmail author
  • Tamar Avraham
  • Michael Lindenbaum
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9909)

Abstract

Matching keypoints by minimizing the Euclidean distance between their SIFT descriptors is an effective and extremely popular technique. Using the ratio between distances, as suggested by Lowe, is even more effective and leads to excellent matching accuracy. Probabilistic approaches that model the distribution of the distances were found effective as well. This work focuses, for the first time, on analyzing Lowe’s ratio criterion using a probabilistic approach. We provide two alternative interpretations of this criterion, which show that it is not only an effective heuristic but can also be formally justified. The first interpretation shows that Lowe’s ratio corresponds to a conditional probability that the match is incorrect. The second shows that the ratio corresponds to the Markov bound on this probability. The interpretations make it possible to slightly increase the effectiveness of the ratio criterion, and to obtain matching performance that exceeds all previous (non-learning based) results.

Keywords

SIFT Matching a contrario 

References

  1. 1.
    Abdel-Hakim, A.E., Farag, A.A.: CSIFT: a SIFT descriptor with color invariant characteristics. CVPR 2, 1978–1983 (2006)Google Scholar
  2. 2.
    Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Speeded-up robust features (SURF). Comput. Vis. Image Underst. 110(3), 346–359 (2008)CrossRefGoogle Scholar
  3. 3.
    Desolneux, A., Moisan, L., Morel, J.M.: Meaningful alignments. Int. J. Comput. Vision 40(1), 7–23 (2000)CrossRefzbMATHGoogle Scholar
  4. 4.
    Desolneux, A., Moisan, L., Morel, J.M.: From Gestalt Theory to Image Analysis: A Probabilistic Approach, vol. 34. Springer Science & Business Media, New York (2007)Google Scholar
  5. 5.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106(1), 59–70 (2007)CrossRefGoogle Scholar
  6. 6.
    Fischer, P., Dosovitskiy, A., Brox, T.: Descriptor matching with convolutional neural networks: a comparison to SIFT. arXiv preprint arXiv:1405.5769 (2014)
  7. 7.
    Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. In: CVPR 2004, vol. 2, p. II-506 (2004)Google Scholar
  8. 8.
    Lowe, D.G.: Object recognition from local scale-invariant features. ICCV 2, 1150–1157 (1999)Google Scholar
  9. 9.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  10. 10.
    Mikolajczyk, K., Matas, J.: Improving descriptors for fast tree matching by optimal linear projection. In: ICCV 2007, pp. 1–8 (2007)Google Scholar
  11. 11.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)CrossRefGoogle Scholar
  12. 12.
    Miksik, O., Mikolajczyk, K.: Evaluation of local detectors and descriptors for fast feature matching. In: ICPR, pp. 2681–2684 (2012)Google Scholar
  13. 13.
    Moreels, P., Perona, P.: Evaluation of features detectors and descriptors based on 3D objects. Int. J. Comput. Vision 73(3), 263–284 (2007)CrossRefGoogle Scholar
  14. 14.
    Morel, J.M., Yu, G.: ASIFT: a new framework for fully affine invariant image comparison. SIAM J. Imaging Sci. 2(2), 438–469 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Mottalli, M., Tepper, M., Mejail, M.: A contrario detection of false matches in iris recognition. In: Bloch, I., Cesar, R.M. (eds.) CIARP 2010. LNCS, vol. 6419, pp. 442–449. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-16687-7_59 CrossRefGoogle Scholar
  16. 16.
    Muja, M., Lowe, D.G.: Fast approximate nearest neighbors with automatic algorithm configuration. In: VISAPP (1), vol. 2, pp. 331–340, 2 (2009)Google Scholar
  17. 17.
    Musé, P., Sur, F., Cao, F., Gousseau, Y., Morel, J.M.: An a contrario decision method for shape element recognition. Int. J. Comput. Vision 69(3), 295–315 (2006)CrossRefzbMATHGoogle Scholar
  18. 18.
    Myaskouvskey, A., Gousseau, Y., Lindenbaum, M.: Beyond independence: an extension of the a contrario decision procedure. Int. J. Comput. Vision 101(1), 22–44 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  19. 19.
    Pele, O., Werman, M.: A linear time histogram metric for improved SIFT matching. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 495–508. Springer, Heidelberg (2008). doi: 10.1007/978-3-540-88690-7_37 CrossRefGoogle Scholar
  20. 20.
    Rabin, J., Delon, J., Gousseau, Y.: Circular earth movers distance for the comparison of local features. In: ICPR, pp. 1–4 (2008)Google Scholar
  21. 21.
    Rabin, J., Delon, J., Gousseau, Y.: A contrario matching of SIFT-like descriptors. In: ICPR, pp. 1–4 (2008)Google Scholar
  22. 22.
    Sande, K., Gevers, T., Snoek, C.G.: Evaluating color descriptors for object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1582–1596 (2010)CrossRefGoogle Scholar
  23. 23.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. Int. J. Comput. Vision 37(2), 151–172 (2000)CrossRefzbMATHGoogle Scholar
  24. 24.
    Silverman, B.W.: Density Estimation for Statistics and Data Analysis, vol. 26. CRC Press, Boca Raton (1986)CrossRefzbMATHGoogle Scholar
  25. 25.
    Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: a survey. Found. Trends Comput. Graph. Vis. 3(3), 177–280 (2008)CrossRefGoogle Scholar
  26. 26.
    Vedaldi, A., Fulkerson, B.: VLFeat: an open and portable library of computer vision algorithms (2008). http://www.vlfeat.org/
  27. 27.
    Zagoruyko, S., Komodakis, N.: Learning to compare image patches via convolutional neural networks. In: CVPR, pp. 4353–4361 (2015)Google Scholar
  28. 28.
    Zhang, J., Marszałek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: a comprehensive study. Int. J. Comput. Vision 73(2), 213–238 (2007)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Computer Science DepartmentTechnion - I.I.T.HaifaIsrael

Personalised recommendations