Massive parallel computing of super-resolution with sparse representation

Hao Rong Ding, Chih Hung Kuo, Po Hung Kuo, Yan Tse Chuang

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

Abstract

Among Super-Resolution reconstruction methods, the patch-based computation to find the sparse prior can achieve better reconstruction results. The computing for this method is time-consuming. To overcome this problem, we propose a GPU(Graphic Processing Unit) based algorithm to speed up the process and achieve 7.2 times faster than the original method. We also implement the method of modified LASSO(Least Absolute Shrinkage and Selection Operator) to find sparse priors, which can achieve 13.9 times faster.

Original languageEnglish
Title of host publicationIntelligent Systems and Applications - Proceedings of the International Computer Symposium, ICS 2014
EditorsWilliam Cheng-Chung Chu, Stephen Jenn-Hwa Yang, Han-Chieh Chao
PublisherIOS Press
Pages1043-1051
Number of pages9
ISBN (Electronic)9781614994831
DOIs
Publication statusPublished - 2015
EventInternational Computer Symposium, ICS 2014 - Taichung, Taiwan
Duration: 2014 Dec 122014 Dec 14

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume274
ISSN (Print)0922-6389

Other

OtherInternational Computer Symposium, ICS 2014
CountryTaiwan
CityTaichung
Period14-12-1214-12-14

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Massive parallel computing of super-resolution with sparse representation'. Together they form a unique fingerprint.

Cite this