Fuzzy logic supported corner detection

摘要

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.