Compressing Encrypted Images by Using 2D Compressed Sensing

Bo Zhang, Di Xiao, Zhenyu Zhang, Lei Yang

Abstract: Compressing encrypted images by using compressed sensing (CS) has received more and more interests in recent years. However, the existing CS-based coding schemes for encrypted images cannot achieve the low computational complexity and high security at the same time. To address this problem, a novel image encryption-then-compression (ETC) system by using 2D CS (2DCS) is proposed in this paper. Firstly, for high security purpose, the entire image is encrypted by using global random permutation. Secondly, for low computational complexity purpose, the encrypted image is compressed by using 2DCS. Lastly, a 2D projected Landweber (2DPL) algorithm is proposed for image reconstruction. Compared with the state-of-the-art CS-based ETC methods, it has two advantages. Firstly, it achieves the low computational complexity and high security at the same time. Secondly, it obtains a significant gain of peak signal-to-noise ratio (PSNR) of the reconstructed-images.