Detecting Rotational Symmetry Under Affine Projection

Abstract

A new method is presented for detecting planar rotational symmetry under affine projection. The method can deal with partial occlusion and is able to detect multiple rotationally symmetric surfaces in complex backgrounds. The order of rotational symmetry can be estimated, and if it is greater than two, the tilt and orientation of the rotationally symmetric surface can be found and the symmetric region segmented. Local features robust to local affine distortion are matched to obtain pairs of features. Each feature pair hypothesis a set of centres of rotation for different tilts and orientations and the centres of rotation that are close to each other are grouped together to find the dominant rotational symmetries in the image. The method is posed independently of a specific feature detector and descriptor. Results are presented on natural images