IEICE TRANSACTIONS on Information
Exemplar-Based Inpainting Driven by Feature Vectors and Region Segmentation
Summary :
A new exemplar-based inpainting method which effectively preserves global structures and textures in the restored region driven by feature vectors is presented. Exemplars that belong to the source region are segmented based on their features. To express characteristics of exemplars such as shapes of structures and smoothness of textures, the Harris corner response and the variance of pixel values are employed as a feature vector. Enhancements on restoration plausibility and processing speedup are achieved as shown in the experiments.
- Publication
- IEICE TRANSACTIONS on Information Vol.E98-D No.4 pp.972-975
- Publication Date
- 2015/04/01
- Publicized
- 2015/01/09
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2014EDL8201
- Type of Manuscript
- LETTER
- Category
- Image Processing and Video Processing
Authors
Jinki PARK
Chung-Ang University
Jaehwa PARK
Chung-Ang University
Young-Bin KWON
Chung-Ang University
Chan-Gun LEE
Chung-Ang University
Ho-Hyun PARK
Chung-Ang University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Jinki PARK, Jaehwa PARK, Young-Bin KWON, Chan-Gun LEE, Ho-Hyun PARK, "Exemplar-Based Inpainting Driven by Feature Vectors and Region Segmentation" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 4, pp. 972-975, April 2015, doi: 10.1587/transinf.2014EDL8201.
Abstract: A new exemplar-based inpainting method which effectively preserves global structures and textures in the restored region driven by feature vectors is presented. Exemplars that belong to the source region are segmented based on their features. To express characteristics of exemplars such as shapes of structures and smoothness of textures, the Harris corner response and the variance of pixel values are employed as a feature vector. Enhancements on restoration plausibility and processing speedup are achieved as shown in the experiments.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8201/_p
Copy
@ARTICLE{e98-d_4_972,
author={Jinki PARK, Jaehwa PARK, Young-Bin KWON, Chan-Gun LEE, Ho-Hyun PARK, },
journal={IEICE TRANSACTIONS on Information},
title={Exemplar-Based Inpainting Driven by Feature Vectors and Region Segmentation},
year={2015},
volume={E98-D},
number={4},
pages={972-975},
abstract={A new exemplar-based inpainting method which effectively preserves global structures and textures in the restored region driven by feature vectors is presented. Exemplars that belong to the source region are segmented based on their features. To express characteristics of exemplars such as shapes of structures and smoothness of textures, the Harris corner response and the variance of pixel values are employed as a feature vector. Enhancements on restoration plausibility and processing speedup are achieved as shown in the experiments.},
keywords={},
doi={10.1587/transinf.2014EDL8201},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Exemplar-Based Inpainting Driven by Feature Vectors and Region Segmentation
T2 - IEICE TRANSACTIONS on Information
SP - 972
EP - 975
AU - Jinki PARK
AU - Jaehwa PARK
AU - Young-Bin KWON
AU - Chan-Gun LEE
AU - Ho-Hyun PARK
PY - 2015
DO - 10.1587/transinf.2014EDL8201
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2015
AB - A new exemplar-based inpainting method which effectively preserves global structures and textures in the restored region driven by feature vectors is presented. Exemplars that belong to the source region are segmented based on their features. To express characteristics of exemplars such as shapes of structures and smoothness of textures, the Harris corner response and the variance of pixel values are employed as a feature vector. Enhancements on restoration plausibility and processing speedup are achieved as shown in the experiments.
ER -
English
