Finite Ridgelet Transform for low bit rate image compression

Abstract

The finite Ridgelet transform (FRIT) was widely used as a sparse representation for images that with linear singularities. Unfortunately, the ldquowrap aroundrdquo effect restricts its application in image compression and denoising. In this paper, The MAP estimator is applied to the coefficients in the finite Radon transform (FRAT) in order to select the fitted FRAT columns for 1-DCT and 1-DWT. Furthermore, the ldquowrap aroundrdquo effect could be made more clearly if we interpret it in the time domain. Experiments show that this algorithm can concentrate the coefficients energy more greatly and outperforms the other methods in approximating images with straight edges.