Two methods for a reliable corner detection in 2D images
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.
KeywordsGrey Level Edge Point Candidate Point Grey Level Image Curvature Derivative
Unable to display preview. Download preview PDF.
- Rachid Deriche. Recursively implementing the gaussian and its derivatives. INRIA Research report, 1993.Google Scholar
- Rachid Deriche and Gérard Giraudon. Accurate Corner Detection: an analytical study. ICCV, 1990.Google Scholar
- Rachid Deriche and Gérard Giraudon. On corner and vertex detection CVPR, 1993.Google Scholar
- 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
- 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
- J. Alison Noble. Finding corners. Image and Vision Computing, vol 6, May 1988, pp 121–128.Google Scholar
- 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