The quick and high quality image interpolation for single image using multi-filtering and weighted mean

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

3 Citations (Scopus)

Abstract

Image upsampling from one input image gathers considerable attention in the field of computer vision. The problem is ill-posed because the number of known low-resolution (LR) pixels is less than that of unknown high-resolution (HR) pixels. Therefore, quality of an upsampled image depends on prior assumptions. Image interpolation methods are one of the image upsampling technologies and are faster than other image upsampling technologies such as Super-Resolution. However, these methods tend to cause jaggies and blurs in edge and texture regions. We use the idea of Multi-surface Fitting (MF) to solve these problems. MF uses plural local functions to estimate an HR pixel and it reduces blurs. Moreover, we utilize filtering instead of calculation of each local function in order to reduce a computational cost. And we introduce new weights to estimate edge directions. By these ideas, our method has both high quality and a low computational cost.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages2841-2845
Number of pages5
Volume2016-August
ISBN (Electronic)9781467399616
DOIs
Publication statusPublished - 2016 Aug 3
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: 2016 Sep 252016 Sep 28

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
CountryUnited States
CityPhoenix
Period16/9/2516/9/28

Fingerprint

Image quality
Interpolation
Pixels
Computer vision
Costs
Textures

Keywords

  • Filtering
  • Image interpolation
  • Multi-surface fitting
  • Weighted mean

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Yamaguchi, T., & Ikehara, M. (2016). The quick and high quality image interpolation for single image using multi-filtering and weighted mean. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (Vol. 2016-August, pp. 2841-2845). [7532878] IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7532878

The quick and high quality image interpolation for single image using multi-filtering and weighted mean. / Yamaguchi, Takuro; Ikehara, Masaaki.

2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. p. 2841-2845 7532878.

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

Yamaguchi, T & Ikehara, M 2016, The quick and high quality image interpolation for single image using multi-filtering and weighted mean. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. vol. 2016-August, 7532878, IEEE Computer Society, pp. 2841-2845, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 16/9/25. https://doi.org/10.1109/ICIP.2016.7532878
Yamaguchi T, Ikehara M. The quick and high quality image interpolation for single image using multi-filtering and weighted mean. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August. IEEE Computer Society. 2016. p. 2841-2845. 7532878 https://doi.org/10.1109/ICIP.2016.7532878
Yamaguchi, Takuro ; Ikehara, Masaaki. / The quick and high quality image interpolation for single image using multi-filtering and weighted mean. 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. pp. 2841-2845
@inproceedings{19eb31b8bc8146fe97646ea37a8fd5d5,
title = "The quick and high quality image interpolation for single image using multi-filtering and weighted mean",
abstract = "Image upsampling from one input image gathers considerable attention in the field of computer vision. The problem is ill-posed because the number of known low-resolution (LR) pixels is less than that of unknown high-resolution (HR) pixels. Therefore, quality of an upsampled image depends on prior assumptions. Image interpolation methods are one of the image upsampling technologies and are faster than other image upsampling technologies such as Super-Resolution. However, these methods tend to cause jaggies and blurs in edge and texture regions. We use the idea of Multi-surface Fitting (MF) to solve these problems. MF uses plural local functions to estimate an HR pixel and it reduces blurs. Moreover, we utilize filtering instead of calculation of each local function in order to reduce a computational cost. And we introduce new weights to estimate edge directions. By these ideas, our method has both high quality and a low computational cost.",
keywords = "Filtering, Image interpolation, Multi-surface fitting, Weighted mean",
author = "Takuro Yamaguchi and Masaaki Ikehara",
year = "2016",
month = "8",
day = "3",
doi = "10.1109/ICIP.2016.7532878",
language = "English",
volume = "2016-August",
pages = "2841--2845",
booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - The quick and high quality image interpolation for single image using multi-filtering and weighted mean

AU - Yamaguchi, Takuro

AU - Ikehara, Masaaki

PY - 2016/8/3

Y1 - 2016/8/3

N2 - Image upsampling from one input image gathers considerable attention in the field of computer vision. The problem is ill-posed because the number of known low-resolution (LR) pixels is less than that of unknown high-resolution (HR) pixels. Therefore, quality of an upsampled image depends on prior assumptions. Image interpolation methods are one of the image upsampling technologies and are faster than other image upsampling technologies such as Super-Resolution. However, these methods tend to cause jaggies and blurs in edge and texture regions. We use the idea of Multi-surface Fitting (MF) to solve these problems. MF uses plural local functions to estimate an HR pixel and it reduces blurs. Moreover, we utilize filtering instead of calculation of each local function in order to reduce a computational cost. And we introduce new weights to estimate edge directions. By these ideas, our method has both high quality and a low computational cost.

AB - Image upsampling from one input image gathers considerable attention in the field of computer vision. The problem is ill-posed because the number of known low-resolution (LR) pixels is less than that of unknown high-resolution (HR) pixels. Therefore, quality of an upsampled image depends on prior assumptions. Image interpolation methods are one of the image upsampling technologies and are faster than other image upsampling technologies such as Super-Resolution. However, these methods tend to cause jaggies and blurs in edge and texture regions. We use the idea of Multi-surface Fitting (MF) to solve these problems. MF uses plural local functions to estimate an HR pixel and it reduces blurs. Moreover, we utilize filtering instead of calculation of each local function in order to reduce a computational cost. And we introduce new weights to estimate edge directions. By these ideas, our method has both high quality and a low computational cost.

KW - Filtering

KW - Image interpolation

KW - Multi-surface fitting

KW - Weighted mean

UR - http://www.scopus.com/inward/record.url?scp=85006788261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006788261&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7532878

DO - 10.1109/ICIP.2016.7532878

M3 - Conference contribution

VL - 2016-August

SP - 2841

EP - 2845

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

ER -