A Method for Blur and Affine Invariant Object Recognition Using Phase-Only Bispectrum

In this paper, we propose a novel method for recognizing objects in images in a way that is invariant to blur and affine transformation of the images. The method is based on a set of rotated and log-log sampled phase-only bispectrum slices of the images and their phase correlation. The method is invariant to centrally symmetric blur, such as linear motion or out of focus blur. Because of the normalization of the amplitude information, the method is also invariant to uniform illumination changes. The only known method having similar invariance properties is based on image moments. According to the experiments conducted, the proposed method outperforms the moment based method in the presence of various degradations.