Graphics processing unit-accelerated double random phase encoding for fast image encryption

We propose a fast double random phase encoding (DRPE) algorithm using a graphics processing unit (GPU)-based stream-processing model. A performance analysis of the accelerated DRPE implementation that employs the Compute Unified Device Architecture programming environment is presented. We show that the proposed methodology executed on a GPU can dramatically increase encryption speed compared with central processing unit sequential computing. Our experimental results demonstrate that in encryption data of an image with a pixel size of 1000×1000, where one pixel has a 32-bit depth, our GPU version of the DRPE scheme can be approximately two times faster than the advanced encryption standard algorithm implemented on a GPU. In addition, the quality of parallel processing on the presented DRPE acceleration method is evaluated with performance parameters, such as speedup, efficiency, and redundancy.