Corner Detection via Two-Layer Threshold Method

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 135)

Abstract

This paper presents a two-layer threshold method for the corner detection. The method is inspired by the classical Susan corner detection model, and the improvement is two-fold. One is the choice of the self-adaptive threshold, which can be used to detect the possible corner areas. However, since a corner has an arbitrary orientation and sometimes is disturbed by noises, we provide a series of rotate coordinate systems, the second improvement, to enhance the accuracy of our method. Experiment results show that the improved algorithm is robust and is of high efficiency.

Keywords

Corner detection  Self-adaptive threshold  Susan model  

Notes

Acknowledgments

This work was supported by National Natural Science Foundation No. 61170327, Organization Department Program of Beijing for the Talents No.2010D005002000008, Beijing Natural Science Foundation No.1082007, Scientific Research Common Program of Beijing No. KM200410009010, and PHR(IHLB) No.PHR201008199.

References

  1. 1.
    Zhang X, Wang H (2009) Robust image corner detection based on scale evolution difference of planar curves. Pattern Recogn Lett 30:449–455CrossRefGoogle Scholar
  2. 2.
    Trajkovic M, Hedley M (1998) Fast corner detection. Image Vis Comput 16:75–87CrossRefGoogle Scholar
  3. 3.
    Mokhtarian F, Suomela R (1998) Robust image corner detection through curvature scale space. IEEE Transa Pattern Anal Mach Intell 20:1376–1381CrossRefGoogle Scholar
  4. 4.
    Yeh C (2003) Wavelet-based corner detection using eigenvectors of covariance matrices. Patter Recognit Lett 24:2797–2806CrossRefGoogle Scholar
  5. 5.
    Kitchen L, Rosenfeld A (1982) Gray-level corner detection. Pattern Recogn Lett 1:95–102CrossRefGoogle Scholar
  6. 6.
    Harris C, Steven MA (1988) Combined corner and edge detector. In: Proceeding of 4th Alvey vision conference, Manchester, pp 189–192Google Scholar
  7. 7.
    Stephen M, Smith J, Brady Michael (1997) SUSAN-a new approach to low level image processing. Int J Comp Vis 23:45–78CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  1. 1.Institute of Image Processing and Pattern RecognitionNorth China University of TechnologyBeijingPeople’s Republic of China

Personalised recommendations