An efficient example-based approach for image super-resolution

Xiaoguang Li; Kin Man Lam; Guoping Qiu; Lansun Shen; Suyu Wang

doi:10.1109/ICNNSP.2008.4590416

An efficient example-based approach for image super-resolution

Xiaoguang Li, Kin Man Lam, Guoping Qiu, Lansun Shen, Suyu Wang

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

14 Citations (Scopus)

Abstract

A novel algorithm for image super-resolution with class-specific predictors is proposed in this paper. In our algorithm, the training example images are classified into several classes, and each patch of a low-resolution image is classified into one of these classes. Each class has its high-frequency information inferred using a class-specific predictor, which is trained via the training samples from the same class. In this paper, two different types of training sets are employed to investigate the impact of the training database to be used. Experimental results have shown the superior performance of our method.

Original language	English
Title of host publication	2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP
Pages	575-580
Number of pages	6
DOIs	https://doi.org/10.1109/ICNNSP.2008.4590416
Publication status	Published - 22 Sept 2008
Event	2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP - Zhenjiang, China Duration: 7 Jun 2008 → 11 Jun 2008

Conference

Conference	2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP
Country/Territory	China
City	Zhenjiang
Period	7/06/08 → 11/06/08

Keywords

Class-specific predictor
Example-based Super-resolution
Human face magnification

ASJC Scopus subject areas

Artificial Intelligence
Signal Processing

More information

10.1109/ICNNSP.2008.4590416

Cite this

@inproceedings{1cfdc4d3bb8046528fcc773cb4d05bd1,

title = "An efficient example-based approach for image super-resolution",

abstract = "A novel algorithm for image super-resolution with class-specific predictors is proposed in this paper. In our algorithm, the training example images are classified into several classes, and each patch of a low-resolution image is classified into one of these classes. Each class has its high-frequency information inferred using a class-specific predictor, which is trained via the training samples from the same class. In this paper, two different types of training sets are employed to investigate the impact of the training database to be used. Experimental results have shown the superior performance of our method.",

keywords = "Class-specific predictor, Example-based Super-resolution, Human face magnification",

author = "Xiaoguang Li and Lam, {Kin Man} and Guoping Qiu and Lansun Shen and Suyu Wang",

year = "2008",

month = sep,

day = "22",

doi = "10.1109/ICNNSP.2008.4590416",

language = "English",

isbn = "9781424423118",

pages = "575--580",

booktitle = "2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP",

note = "2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP ; Conference date: 07-06-2008 Through 11-06-2008",

}

Li, X, Lam, KM, Qiu, G, Shen, L & Wang, S 2008, An efficient example-based approach for image super-resolution. in 2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP., 4590416, pp. 575-580, 2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP, Zhenjiang, China, 7/06/08. https://doi.org/10.1109/ICNNSP.2008.4590416

An efficient example-based approach for image super-resolution. / Li, Xiaoguang; Lam, Kin Man; Qiu, Guoping et al.
2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP. 2008. p. 575-580 4590416.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - An efficient example-based approach for image super-resolution

AU - Li, Xiaoguang

AU - Lam, Kin Man

AU - Qiu, Guoping

AU - Shen, Lansun

AU - Wang, Suyu

PY - 2008/9/22

Y1 - 2008/9/22

N2 - A novel algorithm for image super-resolution with class-specific predictors is proposed in this paper. In our algorithm, the training example images are classified into several classes, and each patch of a low-resolution image is classified into one of these classes. Each class has its high-frequency information inferred using a class-specific predictor, which is trained via the training samples from the same class. In this paper, two different types of training sets are employed to investigate the impact of the training database to be used. Experimental results have shown the superior performance of our method.

AB - A novel algorithm for image super-resolution with class-specific predictors is proposed in this paper. In our algorithm, the training example images are classified into several classes, and each patch of a low-resolution image is classified into one of these classes. Each class has its high-frequency information inferred using a class-specific predictor, which is trained via the training samples from the same class. In this paper, two different types of training sets are employed to investigate the impact of the training database to be used. Experimental results have shown the superior performance of our method.

KW - Class-specific predictor

KW - Example-based Super-resolution

KW - Human face magnification

UR - http://www.scopus.com/inward/record.url?scp=51849116781&partnerID=8YFLogxK

U2 - 10.1109/ICNNSP.2008.4590416

DO - 10.1109/ICNNSP.2008.4590416

M3 - Conference article published in proceeding or book

SN - 9781424423118

SP - 575

EP - 580

BT - 2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP

T2 - 2008 IEEE International Conference Neural Networks and Signal Processing, ICNNSP

Y2 - 7 June 2008 through 11 June 2008

ER -

An efficient example-based approach for image super-resolution

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this