Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/20907
Title: Example-based image super-resolution with class-specific predictors
Authors: Li, X
Lam, KM 
Qiu, G
Shen, L
Wang, S
Keywords: Class-specific predictor
Content-based encoding
Domain-specific training set
Example-based super-resolution
General-purpose training set
Human face magnification
Self-specific training set
Vector quantization
Issue Date: 2009
Publisher: Academic Press Inc Elsevier Science
Source: Journal of visual communication and image representation, 2009, v. 20, no. 5, p. 312-322 How to cite?
Journal: Journal of Visual Communication and Image Representation 
Abstract: Example-based super-resolution is a promising approach to solving the image super-resolution problem. However, the learning process can be slow and prediction can be inaccurate. In this paper, we present a novel learning-based algorithm for image super-resolution to improve the computational speed and prediction accuracy. Our new method classifies image patches into several classes, for each class, a class-specific predictor is designed. A class-specific predictor takes a low-resolution image patch as input and predicts a corresponding high-resolution patch as output. The performances of the class-specific predictors are evaluated using different datasets formed by face images and natural-scene images. We present experimental results which demonstrate that the new method provides improved performances over existing methods.
URI: http://hdl.handle.net/10397/20907
DOI: 10.1016/j.jvcir.2009.03.008
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

35
Last Week
1
Last month
0
Citations as of Apr 25, 2017

WEB OF SCIENCETM
Citations

28
Last Week
0
Last month
Citations as of Apr 27, 2017

Page view(s)

26
Last Week
1
Last month
Checked on Apr 23, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.