Advertisement

Signal, Image and Video Processing

, Volume 9, Issue 5, pp 1009–1019 | Cite as

Performance evaluation of keypoint detection and matching techniques on grayscale data

  • Hugo Proença
Original Paper

Abstract

The extraction of local photometric descriptors from images has been extensively reported in the computer vision literature. The main purpose of this paper is to provide an objective comparison between the performance of four of the most popular algorithms of this kind: SIFT, SURF, BRIEF and DAISY. Constraining our analysis to grayscale data, several major points distinguish this work from the previous evaluation initiatives: (1) A large amount of data were used, representing a broad range of real-world scenes; (2) an automated evaluation procedure was devised, in order to minimize subjectivity; and (3) we analyze the reliability of each algorithm not only in terms of the distances between corresponding feature descriptors but also of their order statistics. Also, the public availability of a new annotated data set is reported, which is suitable for the automated and statistically significant evaluation of keypoint detection and matching strategies.

Keywords

Image registration Feature extraction  Local descriptors Interest points 

Notes

Acknowledgments

The financial support given by “FCT-Fundação para a Ciência e Tecnologia” and “FEDER” in the scope of the PTDC/EIA/103945/2008 research project “NECOVID: Negative Covert Biometric Recognition” is acknowledged.

References

  1. 1.
    Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: SURF: speeded Up robust features. Comput. Vis. Image Underst. 110(3), 346–359 (2008)CrossRefGoogle Scholar
  2. 2.
    Calonder, M., Lepetit, V., Ozuysal, M., Trzcinski, T., Strecha, C., Fua, P.: BRIEF: computing a local binary descriptor very fast. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1281–1298 (2012)CrossRefGoogle Scholar
  3. 3.
    Carneiro, G., Jepson, A.: Phase-based local features. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 282–296 (2002) Google Scholar
  4. 4.
    Duy-Nguyen, T., Wei-Chao, C., Gelfand, N., Pulli, K.: SURFTrac: Efficient tracking and continuous object recognition using local feature descriptors. In: Proceedings of the IEEE Conference On Computer Vision and. Pattern Recognition (2009). doi: 10.1109/CVPR.2009.5206831
  5. 5.
    Hajek, J., Sidak, Z.: Theory of rank tests, 1st edn. Academic Press, New York (2000)Google Scholar
  6. 6.
    Hanajik, M., Ravas, R., Smiesko, V.: Interest point detection for vision based mobile robot navigation. In: Proceedings of the IEEE 9th International Symposium on Applied Machine Intelligence and Informatics, pp. 207–211 (2011). doi: 10.1109/SAMI.2011.5738876
  7. 7.
    Harris, C., Stephens, M.J.: A combined corner and edge detector. In Proceedings of the Alvey Vision Conference, pp. 147–152 (1988)Google Scholar
  8. 8.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003) ISBN: 0-521-54051-8Google Scholar
  9. 9.
    Huang, C., Chen, C., Chung, P.: Contrast context histogram: an efficient discriminating local descriptor for object recognition and image matching. Pattern Recognit. 41, 3071–3077 (2008)zbMATHCrossRefGoogle Scholar
  10. 10.
    Itti, L., Koch, C., Niebur, E.: Model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)CrossRefGoogle Scholar
  11. 11.
    Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. Proc. Int. Conf. Comput. Vis. Pattern Recognit. 2, 506–513 (2004)Google Scholar
  12. 12.
    Liu, C., Yuen, J., Torralba, A., Freeman, W.: SIFT flow: dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2011)CrossRefGoogle Scholar
  13. 13.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  14. 14.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition, pp. 257–264 (2003)Google Scholar
  15. 15.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)CrossRefGoogle Scholar
  16. 16.
    Ozuysal, M., Calonder, M., Lepetit, V., Fua, P.: Fast keypoint recognition using random ferns. IEEE Trans. Pattern Anal. Mach. Intell. 32(3), 448–461 (2010)CrossRefGoogle Scholar
  17. 17.
    Quelhas, P., Monay, F., Odobez, J.-M., Gatica-Perez, D., Tuytelaars, T.: A thousand words in a scene. IEEE Trans. Pattern Anal. Mach. Intell. 29(9), 1575–1589 (2007)CrossRefGoogle Scholar
  18. 18.
    Randen, T., Husoy, J.: Filtering for texture classification: a comparative study. IEEE Trans. Pattern Anal. Mach. Intell. 21(4), 291–310 (1999)CrossRefGoogle Scholar
  19. 19.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. Int. J. Comput. Vis. 37(2), 151–172 (2000)zbMATHCrossRefGoogle Scholar
  20. 20.
    Tao, Y., Skubic, M., Han, T., Xia, Y., Chi, X.: Evaluating color descriptors for object and scene recognition. Computer 2(2), 17–20 (2010)Google Scholar
  21. 21.
    Tola, E., Lepetit, V., Fua, P.: DAISY: an efficient dense descriptor applied to wide-baseline stereo. IEEE Trans. Pattern Anal. Mach. Intell. 32(5), 815–830 (2010)CrossRefGoogle Scholar
  22. 22.
    van de Sande, E., Gevers, T., Snoek, C.: Evaluation of color descriptors for object and scene recognition. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
  23. 23.
    van de Sande, E., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1582–1596 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  1. 1.Department of Computer Science, IT, Instituto de TelecomunicaçõesUniversity of Beira InteriorCovilhãPortugal

Personalised recommendations