Image Reconstruction of Compressed Sensing Based on the Double Density Circular Symmetric Contourlet Transform and Bivariate Model

Abstract

Compressed sensing uses the sparse prior of image representation,it can reconstruct image from samples much less than Nyquist rate.The sparse image representation and sparseness measure are two key ingredients which have important role on image reconstruction performance.To achieve the better sparse image representation,we split one octave scale of circular symmetric contourlet transform into two scales according to the characteristic of simple cell receptive field,and yield the double density circular symmetric contourlet transform(DDCSCT).The radial bandwidth ratio of the DDCSCT is 1.414.According to the characteristics of the DDCSCT joint distribution,we deduce the second order sparseness measure of image reconstruction from bivariate model.The experiment results show that proposed image reconstruction algorithm which combine DDCSCT and second order sparseness measure outperforms the classical algorithms in terms of both peak signal-to-noise ratio and visual quality.