Using the Fourier Slice Theorem for Representation of Object Views and Models with application to Face Recognition

A novel method unifying viewer and model centered approaches for representing structurally complex D objects like human faces is presented The uni ed D frequency domain representation called Volumet ric Iconic Spectral Signatures V ISS encapsulates both the spatial structure of the object and a contin uum of its views in the same data structure An ex tension of the Projection Slice Theorem is used to di rectly extract the frequency domain image of an ob ject as viewed from any direction Each such Fourier transformed view is a planar slice of the volumetric frequency representation The V ISS representation is employed for pose invariant recognition of complex objects such as faces The recognition and pose esti mation is based on an e cient matching algorithm in a four dimensional Fourier space Experimental ex amples of pose estimation and recognition of faces are