Self-learning-based single image super-resolution of a highly compressed image

Li Wei Kang, Bo Chi Chuang, Chih Chung Hsu, Chia Wen Lin, Chia Hung Yeh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Low-quality images are usually not only with low-resolution, but also suffer from compression artifacts (blocking artifact is treated as an example in this paper). Directly performing image super-resolution (SR) to a highly compressed (low-quality) image would also simultaneously magnify the blocking artifacts, resulting in unpleasing visual quality. In this paper, we propose a self-learning-based SR framework to simultaneously achieve single-image SR and compression artifact removal for a highly-compressed image. We argue that individually performing deblocking first, followed by SR to an image, would usually inevitably lose some image details induced by deblocking, which may be useful for SR, resulting in worse SR result. In our method, we propose to self-learn image sparse representation for modeling the relationship between low and high-resolution image patches in terms of the learned dictionaries, respectively, for image patches with and without blocking artifacts. As a result, image SR and deblocking can be simultaneously achieved via sparse representation and MCA (morphological component analysis)-based image decomposition. Experimental results demonstrate the efficacy of the proposed algorithm.

Original languageEnglish
Title of host publication2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013
Pages224-229
Number of pages6
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 IEEE 15th International Workshop on Multimedia Signal Processing, MMSP 2013 - Pula, Sardinia, Italy
Duration: 2013 Sep 302013 Oct 2

Publication series

Name2013 IEEE International Workshop on Multimedia Signal Processing, MMSP 2013

Conference

Conference2013 IEEE 15th International Workshop on Multimedia Signal Processing, MMSP 2013
Country/TerritoryItaly
CityPula, Sardinia
Period2013/09/302013/10/02

ASJC Scopus subject areas

  • Signal Processing

Fingerprint

Dive into the research topics of 'Self-learning-based single image super-resolution of a highly compressed image'. Together they form a unique fingerprint.

Cite this