DocumentCode
3431892
Title
Blind super-resolution using a learning-based approach
Author
Bégin, Isabelle ; Ferrie, Frank P.
Author_Institution
Centre for Intelligent Machines, McGill Univ., Montreal, Que., Canada
Volume
2
fYear
2004
fDate
23-26 Aug. 2004
Firstpage
85
Abstract
The super-resolution of a single image of unknown point spread-function (PSF) is addressed by extending a learning framework using blind deconvolution with an uncertainty around the resulting PSF. Results indicate success in refining the estimate of the PSF as well as to restoring the image. A novel disparity measure is also proposed to quantify the results.
Keywords
deconvolution; image resolution; learning (artificial intelligence); optical transfer function; blind deconvolution; blind super-resolution; image resolution; learning-based approach; point spread-function; Cameras; Deconvolution; Degradation; Image databases; Image reconstruction; Image resolution; Image restoration; Learning systems; Machine learning; Principal component analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
ISSN
1051-4651
Print_ISBN
0-7695-2128-2
Type
conf
DOI
10.1109/ICPR.2004.1334046
Filename
1334046
Link To Document