Method and system for reconstructing super-resolution image

Abstract

A method for reconstructing a super-resolution image, including: 1) reducing the resolution of an original high-resolution image to obtain an equal low-resolution image, respectively expressed as matrix forms yand y; 2) respectively conducting dictionary training on yand yto obtain a low-resolution image dictionary D; 3) dividing the sparse representation coefficients αand αinto training sample coefficients αand αand test sample coefficients αand α; 4) constructing an L-layer deep learning network using a root-mean-square error as a cost function; 5) iteratively optimizing network parameters so as to minimize the cost function by using the low-resolution image sparse coefficient αas the input of the deep learning network; 6) inputting the low-resolution image sparse coefficient αas the test portion into the trained deep learning network in 5), outputting to obtain a predicted difference image sparse coefficient {circumflex over (α)}, computing an error between the {circumflex over (α)}.