Edge-based matching pursuit for compressive image reconstruction

The prior information of image plays an important role in compressive sensing (CS) reconstruction. The edge is one of the important information which exists in the image to be recovered. In this work, the edge of images is used as a prior information and extracted from CS measurements in the wavelet-based CS inversion. An edge-based matching pursuit algorithm is developed by merging edge information to guide the pursuit process. Edge information well defines the locations of the significant coefficients to be recovered, thus it contributes so much to the reconstruction quality. Experiment results demonstrate that the proposed algorithm returns superior reconstruction performance for the images with obvious edges and high sparsity compared with other CS algorithms.