JOINT IMAGE REGISTRATION AND EXAMPLE-BASED SUPER-RESOLUTION ALGORITHM
H. Kim, J. Shin, and R. Park. Advanced Computational Intelligence: An International Journal (ACII), 2 (2):
9(April 2015)
Abstract
Supper-resolution (SR) methods are classified into two different methods: image registration (IR)-based
methods and example-based methods. The proposed joint SR method is focused on estimating highresolution
(HR) video sequences from low-resolution (LR) ones by combining the two different methods.
The IR-based SR method collects information from adjacent frames to reconstruct HR images in the video
sequence. Example-based SR methods give good textures and strong edges in the result HR video. In this
paper, IR-based and example-based SR methods are fused based on the gradient features. The proposed
joint SR method gives smaller peak signal to noise ratio than the example-based method, however it shows
better reconstruction results on high-level features such as characters in images. Experimental result of the
proposed joint SR method shows less noise and higher contrast than the example-based method.
%0 Journal Article
%1 noauthororeditor
%A Kim, Hyo-Song
%A Shin, Jeyong
%A Park, Rae-Hong
%D 2015
%J Advanced Computational Intelligence: An International Journal (ACII)
%K Coding Compensation Estimation Example-Based Image Learning Motion Neigborhood Registration Regression Sparse Super-Resolution
%N 2
%P 9
%T JOINT IMAGE REGISTRATION AND EXAMPLE-BASED SUPER-RESOLUTION ALGORITHM
%U http://airccse.org/journal/acii/papers/2215acii05.pdf
%V 2
%X Supper-resolution (SR) methods are classified into two different methods: image registration (IR)-based
methods and example-based methods. The proposed joint SR method is focused on estimating highresolution
(HR) video sequences from low-resolution (LR) ones by combining the two different methods.
The IR-based SR method collects information from adjacent frames to reconstruct HR images in the video
sequence. Example-based SR methods give good textures and strong edges in the result HR video. In this
paper, IR-based and example-based SR methods are fused based on the gradient features. The proposed
joint SR method gives smaller peak signal to noise ratio than the example-based method, however it shows
better reconstruction results on high-level features such as characters in images. Experimental result of the
proposed joint SR method shows less noise and higher contrast than the example-based method.
@article{noauthororeditor,
abstract = {Supper-resolution (SR) methods are classified into two different methods: image registration (IR)-based
methods and example-based methods. The proposed joint SR method is focused on estimating highresolution
(HR) video sequences from low-resolution (LR) ones by combining the two different methods.
The IR-based SR method collects information from adjacent frames to reconstruct HR images in the video
sequence. Example-based SR methods give good textures and strong edges in the result HR video. In this
paper, IR-based and example-based SR methods are fused based on the gradient features. The proposed
joint SR method gives smaller peak signal to noise ratio than the example-based method, however it shows
better reconstruction results on high-level features such as characters in images. Experimental result of the
proposed joint SR method shows less noise and higher contrast than the example-based method.},
added-at = {2017-12-20T04:32:04.000+0100},
author = {Kim, Hyo-Song and Shin, Jeyong and Park, Rae-Hong},
biburl = {https://www.bibsonomy.org/bibtex/27bc71367d2e76d74b4a4242d1e211b99/janakirob},
interhash = {7da9b14bb76bcfa39d2fe7555d9b5462},
intrahash = {7bc71367d2e76d74b4a4242d1e211b99},
issn = {2454 - 3934},
journal = {Advanced Computational Intelligence: An International Journal (ACII)},
keywords = {Coding Compensation Estimation Example-Based Image Learning Motion Neigborhood Registration Regression Sparse Super-Resolution},
language = {English},
month = {April},
number = 2,
pages = 9,
timestamp = {2017-12-20T04:32:04.000+0100},
title = {JOINT IMAGE REGISTRATION AND EXAMPLE-BASED SUPER-RESOLUTION ALGORITHM},
url = {http://airccse.org/journal/acii/papers/2215acii05.pdf},
volume = 2,
year = 2015
}