Abstract

In recent years, dictionary learning approaches have been used in image super-resolution, achieving promising results. Such approaches train a dictionary from image patches and reconstruct a new patch by sparse combination of the atoms of the dictionary. Typical training methods do not constrain the dictionary atoms. In this paper, we propose a convex dictionary learning (CDL) algorithm by constraining the dictionary atoms to be formed by non-negative linear combination of the training data, which is a natural, desired property. We evaluate our approach by demonstrating its performance gain over typical approaches.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages4058-4062
Number of pages5
Volume2017-September
ISBN (Electronic)9781509021758
DOIs
StatePublished - Feb 20 2018
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: Sep 17 2017Sep 20 2017

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period9/17/179/20/17

Fingerprint

Glossaries
Atoms
Learning algorithms

Keywords

  • Dictionary learning
  • Sparse representation
  • Super-resolution

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Ding, P. L. K., Li, B., & Chang, K. (2018). Convex dictionary learning for single image super-resolution. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (Vol. 2017-September, pp. 4058-4062). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8297045

Convex dictionary learning for single image super-resolution. / Ding, Pak Lun Kevin; Li, Baoxin; Chang, Kan.

2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. p. 4058-4062.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ding, PLK, Li, B & Chang, K 2018, Convex dictionary learning for single image super-resolution. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. vol. 2017-September, IEEE Computer Society, pp. 4058-4062, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 9/17/17. https://doi.org/10.1109/ICIP.2017.8297045
Ding PLK, Li B, Chang K. Convex dictionary learning for single image super-resolution. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September. IEEE Computer Society. 2018. p. 4058-4062 https://doi.org/10.1109/ICIP.2017.8297045
Ding, Pak Lun Kevin ; Li, Baoxin ; Chang, Kan. / Convex dictionary learning for single image super-resolution. 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. pp. 4058-4062
@inproceedings{182895570e2b40c19474deefd6d6f143,
title = "Convex dictionary learning for single image super-resolution",
abstract = "In recent years, dictionary learning approaches have been used in image super-resolution, achieving promising results. Such approaches train a dictionary from image patches and reconstruct a new patch by sparse combination of the atoms of the dictionary. Typical training methods do not constrain the dictionary atoms. In this paper, we propose a convex dictionary learning (CDL) algorithm by constraining the dictionary atoms to be formed by non-negative linear combination of the training data, which is a natural, desired property. We evaluate our approach by demonstrating its performance gain over typical approaches.",
keywords = "Dictionary learning, Sparse representation, Super-resolution",
author = "Ding, {Pak Lun Kevin} and Baoxin Li and Kan Chang",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/ICIP.2017.8297045",
language = "English (US)",
volume = "2017-September",
pages = "4058--4062",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Convex dictionary learning for single image super-resolution

AU - Ding, Pak Lun Kevin

AU - Li, Baoxin

AU - Chang, Kan

PY - 2018/2/20

Y1 - 2018/2/20

N2 - In recent years, dictionary learning approaches have been used in image super-resolution, achieving promising results. Such approaches train a dictionary from image patches and reconstruct a new patch by sparse combination of the atoms of the dictionary. Typical training methods do not constrain the dictionary atoms. In this paper, we propose a convex dictionary learning (CDL) algorithm by constraining the dictionary atoms to be formed by non-negative linear combination of the training data, which is a natural, desired property. We evaluate our approach by demonstrating its performance gain over typical approaches.

AB - In recent years, dictionary learning approaches have been used in image super-resolution, achieving promising results. Such approaches train a dictionary from image patches and reconstruct a new patch by sparse combination of the atoms of the dictionary. Typical training methods do not constrain the dictionary atoms. In this paper, we propose a convex dictionary learning (CDL) algorithm by constraining the dictionary atoms to be formed by non-negative linear combination of the training data, which is a natural, desired property. We evaluate our approach by demonstrating its performance gain over typical approaches.

KW - Dictionary learning

KW - Sparse representation

KW - Super-resolution

UR - http://www.scopus.com/inward/record.url?scp=85045324615&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045324615&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8297045

DO - 10.1109/ICIP.2017.8297045

M3 - Conference contribution

VL - 2017-September

SP - 4058

EP - 4062

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

ER -