Multiple geometrical filters for 3D scale-invariant image representation of planar objects

A low-level approach for 3-D invariant recognition of planar object from a centered monocular view is presented. The proposed scheme uses a distributed bank of filters that perform geometrical mapping on spatial image domain to generate a multidimensional (4-D) description. This image representation achieves invariance to 2-D rotation, scaling and perspective projection. Invariant classification and pose estimation, in terms of slant and tilt of the planar object, are obtained by direct matching between the representation and an undistorted reference model.