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.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Rachid Deriche. Recursively implementing the gaussian and its derivatives. INRIA Research report, 1993.
Rachid Deriche and Gérard Giraudon. Accurate Corner Detection: an analytical study. ICCV, 1990.
Rachid Deriche and Gérard Giraudon. On corner and vertex detection CVPR, 1993.
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.
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.
J. Alison Noble. Finding corners. Image and Vision Computing, vol 6, May 1988, pp 121–128.
A. Witkin. A multi-scale approach to extract zero-crossings of the laplacian. In Proceedings of International Joint Conference on Artificial Intelligence, 1982.
Author information
Authors and Affiliations
Editor information
Rights 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