21 March 2017 Hybrid sparse-representation-based approach to image super-resolution reconstruction
Author Affiliations +
Abstract
This paper presents a hybrid sparse-representation-based approach to single-image super-resolution reconstruction. Our main contribution is threefold: (1) jointly utilize nonlocal similarity of intensity image and low-rank property of gradient image under the framework of sparse representation; (2) incorporate both the high-resolution (HR) and low-resolution dictionaries into the reconstruction process; and (3) incorporate both the unknown HR image and the sparse coefficients into a single objective function. By alternatively minimizing the objective function with respect to the unknown HR image and the sparse coefficients, we get an estimate of the target HR image. Extensive experiments validate that compared with many state-of-the-art algorithms the proposed method yields comparable results for noiseless images and achieves much better results for noisy images.
© 2017 SPIE and IS&T
Di Zhang, Jiazhong He, "Hybrid sparse-representation-based approach to image super-resolution reconstruction," Journal of Electronic Imaging 26(2), 023008 (21 March 2017). https://doi.org/10.1117/1.JEI.26.2.023008 . Submission: Received: 19 August 2016; Accepted: 1 March 2017
Received: 19 August 2016; Accepted: 1 March 2017; Published: 21 March 2017
JOURNAL ARTICLE
9 PAGES


SHARE
Back to Top