Object recognition by combined invariants of orthogonal Fourier-Mellin moments

摘要

Orthogonal moments are successfully used in the field of image analysis in the past decades. In this paper, two sets of invariants which are invariant to convolution with circularly symmetric point spread function (PSF) are introduced for object recognition and image classification using orthogonal Fourier-Mellin moments and quaternion Fourier-Mellin moments, respectively. The theoretic frameworks for deriving the orthogonal Fourier-Mellin moments of a blurred gray image are provided. Similarly, this study presents a method to construct quaternion Fourier-Mellin moments of a blurred color image. The experimental results are presented to illustrate the performance of the invariants for deformed gray or color images.