Options
2007
Journal Article
Titel
Rotations- und skalierungsinvariante Objekterkennung mittels Gaborfilter
Abstract
Invariant object localization is one of the challenging tasks in computer vision research. In this paper we present a robust rotation and scale invariant object recognition method. A local Gabor filter space is treated as the core of this method. Image rotation and scaling operations were transformed into shift operations along the Gabor filter space dimensions. This property enables efficient scale and rotation estimation. The Gabor filter space allows a comparison of local environments and is used as the basis of the invariant object recognition method. After introducing the basics of the object localization method, two examples are shown. The examples clarify the potentialities of the object recognition method and show its flexibility and robustness.