A Scale and Rotation Invariant Interest Points Detector Based on Gabor Filters

Abstract

This paper presents a new method for detecting scale and rotation invariant interest points. The method is based on a representation of the image that involves both spatial and spatial-frequency variables in its description. The method is based on two main conclusions: 1) Interest points can be extracted based on the local maxima of the normalized local energy maps. 2) Local extrema over scale of a new established Gabor scale-space indicate the presence of characteristic local structures. Our method first extract interest points at multi-scales from the local energy map constructed by Gabor filter responses, and then select points at which a local measure is maximal over scales. This allows a selection of distinctive points for which the characteristic scale is known. The interest points are invariant to scale and rotation and give repeatable results (geometric stable). Comparative evaluation using the repeatability criteria shows the good performance of our approach.