Non-maximum Suppression Using Fewer than Two Comparisons per Pixel

  • Tuan Q. Pham
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6474)

Abstract

Non-Maximum Suppression (NMS) is the task of finding all local maxima in an image. This is often solved using gray-scale image dilation, which requires at least 6 comparisons per pixel in 2-D. We present two solutions that use fewer than 2 comparisons per pixel with little memory overhead. The first algorithm locates 1-D peaks along the image’s scan-line and compares each of these peaks against its 2-D neighborhood in a spiral scan order. The second algorithm selects local maximum candidates from the maxima of non-overlapping blocks of one-fourth the neighborhood size. Both algorithms run considerably faster than current best methods in the literature when applied to feature point detection. Matlab code of the proposed algorithms is provided for evaluation purposes.

Keywords

Neighborhood Size Central Pixel Straightforward Method Corner Detection Interest Point Detector 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rosenfeld, A., Kak, A.: Digital Picture Processing, 2nd edn. Academic Press, London (1976)MATHGoogle Scholar
  2. 2.
    Kitchen, L., Rosenfeld, A.: Gray-level corner detection. Pattern Recognition Letters 1, 92–102 (1982)Google Scholar
  3. 3.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. of the Fourth Alvey Vision Conference, pp. 147–151 (1988)Google Scholar
  4. 4.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  5. 5.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. IJCV 60, 63–86 (2004)CrossRefGoogle Scholar
  6. 6.
    van Herk, M.: A fast algorithm for local minimum and maximum filters on rectangular and octagonal kernels. Pattern Recognition Letters 13, 517–521 (1992)CrossRefGoogle Scholar
  7. 7.
    Gil, J., Werman, M.: Computing 2-d min, median, and max filters. IEEE Trans. on PAMI 15, 504–507 (1993)CrossRefGoogle Scholar
  8. 8.
    Neubeck, A., Van Gool, L.: Efficient non-maximum suppression. In: Proc. of ICPR, vol. 3, pp. 850–855 (2006)Google Scholar
  9. 9.
    Förstner, W., Gülch, E.: A fast operator for detection and precise locations of distinct points, corners, and centres of circular features. In: Proc. of Intercommission Conf. on Fast Processing of Photogrammetric Data, pp. 281–305 (1987)Google Scholar
  10. 10.
    Soille, P.: Morphological Image Analysis: Principles and Applications. Springer, Heidelberg (1999)CrossRefMATHGoogle Scholar
  11. 11.
    Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. IJCV 37, 151–172 (2000)CrossRefMATHGoogle Scholar
  12. 12.
    Brown, M., Szeliski, R., Winder, S.: Multi-image matching using multi-scale oriented patches. In: Proc. of CVPR, vol. 1, pp. 510–517 (2005)Google Scholar
  13. 13.
    Coltuc, D., Bolon, P.: Fast computation of rank order statistics. In: Proc. of EUSIPCO, pp. 2425–2428 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Tuan Q. Pham
    • 1
  1. 1.Canon Information Systems Research Australia (CiSRA)North RydeAustralia

Personalised recommendations