Skip to main content
SpringerLink
Log in

Two methods for a reliable corner detection in 2D images

  • Session IA1b — Feature Matching & Detection
  • Conference paper
  • First Online:
Image Analysis Applications and Computer Graphics (ICSC 1995)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1024))

Included in the following conference series:

  • 211 Accesses

Abstract

In this paper, we apply successively two methods for corner detection in two-dimensional images, i.e. a differential geometrybased approach relying on multi-scale curvature computation and curvature extrema extraction, and a connexionist approach based on neural networks. We point out the limits of each method and we investigate the way to combine those two strategies in order to get more accurate and more reliable results. This methodology is tested on an indoor scene.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Rachid Deriche. Recursively implementing the gaussian and its derivatives. INRIA Research report, 1993.

    Google Scholar 

  2. Rachid Deriche and Gérard Giraudon. Accurate Corner Detection: an analytical study. ICCV, 1990.

    Google Scholar 

  3. Rachid Deriche and Gérard Giraudon. On corner and vertex detection CVPR, 1993.

    Google Scholar 

  4. Olivier Monga, Serge Benayoun, and Olivier D. Faugeras. Using third order derivatives to extract ridge lines in 3d images. In IEEE Conference on Vision and Pattern Recognition, Urbana Champaign, June 1992.

    Google Scholar 

  5. Olivier Monga, Richard Lengagne, and Rachid Deriche. Extraction of the zero-crossings of the curvature derivative in volumic 3D medical images: a multi-scale approach. INRIA Research report, 1994.

    Google Scholar 

  6. J. Alison Noble. Finding corners. Image and Vision Computing, vol 6, May 1988, pp 121–128.

    Google Scholar 

  7. A. Witkin. A multi-scale approach to extract zero-crossings of the laplacian. In Proceedings of International Joint Conference on Artificial Intelligence, 1982.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Domaine de Voluceau - Rocquencourt, INRIA, BP. 105, 78153, Le Chesnay Cedex, France

    Richard Lengagne & Olivier Monga

  2. NLPR, Institute of Automation, Chinese Academy of Sciences, Zhong Guan Cun, P.O.Box 2728, 100080, Beijing, China

    Cong Ge & Ma Song De

Authors
  1. Richard Lengagne
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Olivier Monga
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Cong Ge
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ma Song De
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Roland T. Chin Horace H. S. Ip Avi C. Naiman Ting-Chuen Pong

Rights and permissions

Reprints and permissions

Copyright information

© 1995 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Lengagne, R., Monga, O., Ge, C., De, M.S. (1995). Two methods for a reliable corner detection in 2D images. In: Chin, R.T., Ip, H.H.S., Naiman, A.C., Pong, TC. (eds) Image Analysis Applications and Computer Graphics. ICSC 1995. Lecture Notes in Computer Science, vol 1024. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60697-1_90

Download citation

  • DOI: https://doi.org/10.1007/3-540-60697-1_90

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-60697-0

  • Online ISBN: 978-3-540-49298-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation