Edge-oriented two-step interpolation based on training set

Ji Hoon Lee, Jong-Ok Kim, Jong Woo Han, Kang Sun Choi, Sung-Jea Ko

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Preserving the sharpness of edge structures is highly challenging to image interpolation. In this paper, we propose an edge-oriented two-step interpolation method that utilizes an edge training set. For edge interpolation, the LR edge map is converted into the HR edge map by using the training set. Then, an image is classified into smooth and edge regions using the HR edge map, and both regions are interpolated separately. For edge regions, adaptive edgeoriented interpolation is performed by using the detailed edge structures learned from training. The proposed method is extensively evaluated, and its performance is compared with the conventional edge-based methods. Experimental results show that the proposed method can not only reconstruct the missed edge information by the training set, but also significantly reduce blurring and jagging artifacts around edges by separately interpolating smooth and edge regions.

Original languageEnglish
Article number5606336
Pages (from-to)1848-1855
Number of pages8
JournalIEEE Transactions on Consumer Electronics
Volume56
Issue number3
DOIs
Publication statusPublished - 2010 Aug 1

Fingerprint

Interpolation

Keywords

  • Edge Map
  • Edge-Oriented
  • Image Interpolation
  • Training Set

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology

Cite this

Edge-oriented two-step interpolation based on training set. / Lee, Ji Hoon; Kim, Jong-Ok; Han, Jong Woo; Choi, Kang Sun; Ko, Sung-Jea.

In: IEEE Transactions on Consumer Electronics, Vol. 56, No. 3, 5606336, 01.08.2010, p. 1848-1855.

Research output: Contribution to journalArticle

Lee, Ji Hoon ; Kim, Jong-Ok ; Han, Jong Woo ; Choi, Kang Sun ; Ko, Sung-Jea. / Edge-oriented two-step interpolation based on training set. In: IEEE Transactions on Consumer Electronics. 2010 ; Vol. 56, No. 3. pp. 1848-1855.
@article{8e70d2f9b60d40f1882533a52670168a,
title = "Edge-oriented two-step interpolation based on training set",
abstract = "Preserving the sharpness of edge structures is highly challenging to image interpolation. In this paper, we propose an edge-oriented two-step interpolation method that utilizes an edge training set. For edge interpolation, the LR edge map is converted into the HR edge map by using the training set. Then, an image is classified into smooth and edge regions using the HR edge map, and both regions are interpolated separately. For edge regions, adaptive edgeoriented interpolation is performed by using the detailed edge structures learned from training. The proposed method is extensively evaluated, and its performance is compared with the conventional edge-based methods. Experimental results show that the proposed method can not only reconstruct the missed edge information by the training set, but also significantly reduce blurring and jagging artifacts around edges by separately interpolating smooth and edge regions.",
keywords = "Edge Map, Edge-Oriented, Image Interpolation, Training Set",
author = "Lee, {Ji Hoon} and Jong-Ok Kim and Han, {Jong Woo} and Choi, {Kang Sun} and Sung-Jea Ko",
year = "2010",
month = "8",
day = "1",
doi = "10.1109/TCE.2010.5606336",
language = "English",
volume = "56",
pages = "1848--1855",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Edge-oriented two-step interpolation based on training set

AU - Lee, Ji Hoon

AU - Kim, Jong-Ok

AU - Han, Jong Woo

AU - Choi, Kang Sun

AU - Ko, Sung-Jea

PY - 2010/8/1

Y1 - 2010/8/1

N2 - Preserving the sharpness of edge structures is highly challenging to image interpolation. In this paper, we propose an edge-oriented two-step interpolation method that utilizes an edge training set. For edge interpolation, the LR edge map is converted into the HR edge map by using the training set. Then, an image is classified into smooth and edge regions using the HR edge map, and both regions are interpolated separately. For edge regions, adaptive edgeoriented interpolation is performed by using the detailed edge structures learned from training. The proposed method is extensively evaluated, and its performance is compared with the conventional edge-based methods. Experimental results show that the proposed method can not only reconstruct the missed edge information by the training set, but also significantly reduce blurring and jagging artifacts around edges by separately interpolating smooth and edge regions.

AB - Preserving the sharpness of edge structures is highly challenging to image interpolation. In this paper, we propose an edge-oriented two-step interpolation method that utilizes an edge training set. For edge interpolation, the LR edge map is converted into the HR edge map by using the training set. Then, an image is classified into smooth and edge regions using the HR edge map, and both regions are interpolated separately. For edge regions, adaptive edgeoriented interpolation is performed by using the detailed edge structures learned from training. The proposed method is extensively evaluated, and its performance is compared with the conventional edge-based methods. Experimental results show that the proposed method can not only reconstruct the missed edge information by the training set, but also significantly reduce blurring and jagging artifacts around edges by separately interpolating smooth and edge regions.

KW - Edge Map

KW - Edge-Oriented

KW - Image Interpolation

KW - Training Set

UR - http://www.scopus.com/inward/record.url?scp=78149236525&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149236525&partnerID=8YFLogxK

U2 - 10.1109/TCE.2010.5606336

DO - 10.1109/TCE.2010.5606336

M3 - Article

AN - SCOPUS:78149236525

VL - 56

SP - 1848

EP - 1855

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 3

M1 - 5606336

ER -