Hybrid MPI-OpenMP Parallelization of Image Reconstruction

Perceptual coding should take full advantage of the results from human visual system (HVS) studies. In this paper, we exploit an image reconstruction algorithm, which can simply and reliably represent images using regional shape and texture information and effectually eliminate perceptual redundancy. But real-time application of the algorithm is limited due to its inherent complex and intensive computation. Therefore, we implement image reconstruction with a hybrid message passing interface (MPI) and OpenMP approach on the basis of a standard MPI implementation. Experimental results confirm our image reconstruction algorithm can get optimal restoration results. Compared with JPEG and JPEG2000 compression, this algorithm can not only get more coding gain but remain most information people care. Our hybrid MPI-OpenMP approach can significantly improve time performance of image reconstruction algorithm.