Advertisement

Keypoint Detection Based on the Unimodality Test of HOGs

  • M. A. Cataño
  • J. Climent
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7431)

Abstract

We present a new method for keypoint detection. The main drawback of existing methods is their lack of robustness to image distortions. Small variations of the image lead to big differences in keypoint localizations.

The present work shows a way of determining singular points in an image using histograms of oriented gradients (HOGs). Although HOGs are commonly used as keypoint descriptors, they have not been used in the detection stage before. We show that the unimodality of HOGs can be used as a measure of significance of the interest points. We show that keypoints detected using HOGs present higher robustness to image distortions, and we compare the results with existing methods, using the repeatability criterion.

Keywords

HOG salient feature keypoint detection repeatability unimodality test 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Ke, Y., Sukthankar, R.: PCA-SIFT: A More Distinctive Representation for Local Image Descriptors. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 506–513 (2004)Google Scholar
  3. 3.
    Bay, H.: From Wide-baseline Point and Line Correspondences to 3D. PhD thesis, Swiss Federal Institute of Technology (2006)Google Scholar
  4. 4.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence 27, 1615–1630 (2005)CrossRefGoogle Scholar
  5. 5.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 886–893 (2005)Google Scholar
  6. 6.
    Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence 32, 1627–1645 (2010)CrossRefGoogle Scholar
  7. 7.
    Moravec, H.P.: Obstacle avoidance and navigation in the real world by a seeing robot rover. PhD thesis, Stanford, CA, USA, AAI8024717 (1980)Google Scholar
  8. 8.
    Beaudet, P.R.: Rotationally invariant image operators. In: Proceedings of the International Joint Conference on Pattern Recognition, vol. 579, pp. 579–583 (1978)Google Scholar
  9. 9.
    Harris, C., Stephens, M.I.: A combined corner and edge detector, Manchester, UK, vol. 15, pp. 147–151 (1988)Google Scholar
  10. 10.
    Smith, S.M., Brady, J.M.: SUSAN - a new approach to low level image processing. Int. Journal of Computer Vision 23, 45–78 (1997)CrossRefGoogle Scholar
  11. 11.
    Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: Proceedings of Eighth IEEE International Conference on Computer Vision, ICCV 2001, vol. 1, pp. 525–531 (2001)Google Scholar
  12. 12.
    Mikolajczyk, K., Schmid, C.: Scale and Affine Invariant Interest Point Detectors. International Journal of Computer Vision 1, 63–86 (2004)CrossRefGoogle Scholar
  13. 13.
    Rosten, E., Porter, R., Drummond, T.: Faster and better: A machine learning approach to corner detection. IEEE Trans. Pattern Analysis and Machine Intelligence 32, 105–119 (2010)CrossRefGoogle Scholar
  14. 14.
    Lowe, D.G.: Object Recognition from Local Scale-Invariant Features. In: IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157 (1999)Google Scholar
  15. 15.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of Interest Point Detectors. International Journal of Computer Vision 37, 151–172 (2000)zbMATHCrossRefGoogle Scholar
  16. 16.
    Porikli, F.: Integral histogram: A fast way to extract histograms in cartesian spaces. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 829–836 (2005)Google Scholar
  17. 17.
    Hartigan, J.A., Hartigan, P.M.: The dip test of unimodality. The Annals of Statistics 13, 70–84 (1985)MathSciNetzbMATHCrossRefGoogle Scholar
  18. 18.
    Hellwig, B., Hengstler, J., Schmidt, M., Gehrmann, M., Schormann, W., Rahnenfuhrer, J.: Comparison of scores for bimodality of gene expression distributions and genome-wide evaluation of the prognostic relevance of high-scoring genes. BMC Bioinformatics 11, 276 (2010)CrossRefGoogle Scholar
  19. 19.
    DeCarlo, L.T.: On the meaning and use of kurtosis. Psychological Methods 2, 292–307 (1997)CrossRefGoogle Scholar
  20. 20.
    Wang, J., Wen, S., Symmans, W.F., Pusztai, L., Coombes, K.R.: The bimodality index: a criterion for discovering and ranking bimodal signatures from cancer gene expression profiling data. Cancer Informatics 7, 199–216 (2009)Google Scholar
  21. 21.
    Wolfe, J.H.: Pattern Clustering by Multivariate Mixture Analysis. Multivariate Behavioral Research 5, 329–350 (1970)CrossRefGoogle Scholar
  22. 22.
    Hartigan, P.M.: Algorithm as 217: Computation of the dip statistic to test for unimodality. Journal of the Royal Statistical Society. Series C (Applied Statistics) 34, 320–325 (1985)Google Scholar
  23. 23.
    Vachier, C., Meyer, F.: Extinction value: a new measurement of persistence. In: IEEE Workshop on Nonlinear Signal and Image Processing, vol. 1, pp. 254–257 (1995)Google Scholar
  24. 24.
    Schmid, C., Mohr, R., Bauckhage, C.: Comparing and evaluating interest points. In: Sixth International Conference on Computer Vision, pp. 230–235 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • M. A. Cataño
    • 1
  • J. Climent
    • 2
  1. 1.Pontificia Universidad Catolica del PeruPeru
  2. 2.Universitat Politecnica de Catalunya, Barcelona TechSpain

Personalised recommendations