Fuzzy logic supported corner detection

Issue title: Soft Computing and Applications

Article type: Research Article

Authors: Várkonyi-Kóczy, Annamária R.^;

Affiliations: Department of Measurement and Information Systems, Budapest University of Technology and Economics, Hungary | Integrated Intelligent Systems- Japanese-Hungarian Laboratory Magyar Tudósok krt. 2., H-1521 Budapest, Hungary. Tel.: +3614632057; Fax: +3614634112; E-mail: koczy@mit.bme.hu

Abstract: Corner detection plays an important role in computer vision, as well as in 3D reconstruction of a scene. Based on the corners we can determine the most characteristic points of an object and so reconstruct it. Corners are useful in case of pattern recognition, as well. In this paper, a new corner detection technique is introduced which is based on fuzzy reasoning and applies a special local structure matrix. Furthermore, by introducing a new attribute associated to the corners, the method efficiently supports the further processing, e.g. point correspondence matching in stereo images or 3D reconstruction of schemes.

Keywords: Corner detection, fuzzy image processing, noise elimination, noise smoothing, 3D modeling

Journal: Journal of Intelligent & Fuzzy Systems, vol. 19, no. 1, pp. 41-50, 2008