DocumentCode :
693283
Title :
Graph regularized dictionary for single image super-resolution
Author :
Lei Zeng ; Shiqi Ma ; Xiaofeng Li
Author_Institution :
Sch. of Commun. & Inf. Eng., UESTC, Chengdu, China
fYear :
2013
fDate :
26-28 Oct. 2013
Firstpage :
257
Lastpage :
259
Abstract :
Super-resolution (SR) for single image is wild used in image processing areas. The learning-based methods use the co-trained dictionaries which contain low resolution and corresponding high resolution images to conduct SR. In this paper, a new dictionary for SR is proposed which adds the graph information between patches. Simulation results show that our scheme improved the dictionary and outperforms the existing classic SR algorithms in both subjective visually and quantitative evaluations.
Keywords :
compressed sensing; graph theory; image resolution; learning systems; co-trained dictionaries; graph regularized dictionary; high resolution images; image processing; learning-based methods; single image super resolution; Dictionaries; Feature extraction; Image reconstruction; Image resolution; Joints; Simulation; Training; graph regularized dictionary; joint dictionary training; sparse representation; super resolution;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Problem-solving (ICCP), 2013 International Conference on
Conference_Location :
Jiuzhai
Type :
conf
DOI :
10.1109/ICCPS.2013.6893557
Filename :
6893557
Link To Document :
بازگشت