Super-resolution image reconstruction with edge adaptive weight in video sequence

Ji Yong Kwon, Du Sic Yoo, Jong Hyun Park, Se Hyeok Park, Moon Gi Kang

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

1 Citation (Scopus)

Abstract

Digital images and videos are used in many digital devices recently. Also, the resolution of display became larger than that of previous years. Image up-scaling algorithm is important issue since original input source is limited in transferring within data bandwidth. Among various up-scaling algorithms, Super-Resolution (SR) image reconstruction method is able to estimate high-resolution (HR) image using multiple low-resolution (LR) images. Conventional approaches to estimate HR image with Least Square (LS) method and Weighted Least Square (WLS) method are not able to reconstruct high-frequency region effectively in case its blur kernel is assumed Gaussian kernel in unknown system. Also, these methods produce jagging artifacts from the deficiency of LR frames. The proposed SR algorithm uses edge adaptive WLS method to reconstruct high-frequency region considering local properties and is applied to video sequence with block process to cope with local motions. Moreover, to apply video sequence with complex motions, we use selectively the correct information of reference frame to avoid errors from incorrect information. For accurate additional information from reference frames, the proposed algorithm determines additional information in reference frame by comparing with current frame and reference frame. The experiments demonstrate the superior performance of the proposed algorithm.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Image Processing
Subtitle of host publicationAlgorithms and Systems X; and Parallel Processing for Imaging Applications II
DOIs
Publication statusPublished - 2012 Mar 5
EventImage Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II - Burlingame, CA, United States
Duration: 2012 Jan 232012 Jan 25

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8295
ISSN (Print)0277-786X

Other

OtherImage Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II
CountryUnited States
CityBurlingame, CA
Period12/1/2312/1/25

Fingerprint

Super-resolution
Image Reconstruction
image reconstruction
Image reconstruction
Image resolution
least squares method
Least Square Method
Upscaling
Weighted Least Squares
High Resolution
Digital devices
scaling
Gaussian Kernel
Digital Video
Motion
high resolution
Local Properties
image resolution
estimates
Digital Image

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Kwon, J. Y., Yoo, D. S., Park, J. H., Park, S. H., & Kang, M. G. (2012). Super-resolution image reconstruction with edge adaptive weight in video sequence. In Proceedings of SPIE-IS and T Electronic Imaging - Image Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II [82950M] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8295). https://doi.org/10.1117/12.905368
Kwon, Ji Yong ; Yoo, Du Sic ; Park, Jong Hyun ; Park, Se Hyeok ; Kang, Moon Gi. / Super-resolution image reconstruction with edge adaptive weight in video sequence. Proceedings of SPIE-IS and T Electronic Imaging - Image Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II. 2012. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{406b8a17ae5e4363a3232fd914bd466b,
title = "Super-resolution image reconstruction with edge adaptive weight in video sequence",
abstract = "Digital images and videos are used in many digital devices recently. Also, the resolution of display became larger than that of previous years. Image up-scaling algorithm is important issue since original input source is limited in transferring within data bandwidth. Among various up-scaling algorithms, Super-Resolution (SR) image reconstruction method is able to estimate high-resolution (HR) image using multiple low-resolution (LR) images. Conventional approaches to estimate HR image with Least Square (LS) method and Weighted Least Square (WLS) method are not able to reconstruct high-frequency region effectively in case its blur kernel is assumed Gaussian kernel in unknown system. Also, these methods produce jagging artifacts from the deficiency of LR frames. The proposed SR algorithm uses edge adaptive WLS method to reconstruct high-frequency region considering local properties and is applied to video sequence with block process to cope with local motions. Moreover, to apply video sequence with complex motions, we use selectively the correct information of reference frame to avoid errors from incorrect information. For accurate additional information from reference frames, the proposed algorithm determines additional information in reference frame by comparing with current frame and reference frame. The experiments demonstrate the superior performance of the proposed algorithm.",
author = "Kwon, {Ji Yong} and Yoo, {Du Sic} and Park, {Jong Hyun} and Park, {Se Hyeok} and Kang, {Moon Gi}",
year = "2012",
month = "3",
day = "5",
doi = "10.1117/12.905368",
language = "English",
isbn = "9780819489425",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Image Processing",

}

Kwon, JY, Yoo, DS, Park, JH, Park, SH & Kang, MG 2012, Super-resolution image reconstruction with edge adaptive weight in video sequence. in Proceedings of SPIE-IS and T Electronic Imaging - Image Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II., 82950M, Proceedings of SPIE - The International Society for Optical Engineering, vol. 8295, Image Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II, Burlingame, CA, United States, 12/1/23. https://doi.org/10.1117/12.905368

Super-resolution image reconstruction with edge adaptive weight in video sequence. / Kwon, Ji Yong; Yoo, Du Sic; Park, Jong Hyun; Park, Se Hyeok; Kang, Moon Gi.

Proceedings of SPIE-IS and T Electronic Imaging - Image Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II. 2012. 82950M (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8295).

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

TY - GEN

T1 - Super-resolution image reconstruction with edge adaptive weight in video sequence

AU - Kwon, Ji Yong

AU - Yoo, Du Sic

AU - Park, Jong Hyun

AU - Park, Se Hyeok

AU - Kang, Moon Gi

PY - 2012/3/5

Y1 - 2012/3/5

N2 - Digital images and videos are used in many digital devices recently. Also, the resolution of display became larger than that of previous years. Image up-scaling algorithm is important issue since original input source is limited in transferring within data bandwidth. Among various up-scaling algorithms, Super-Resolution (SR) image reconstruction method is able to estimate high-resolution (HR) image using multiple low-resolution (LR) images. Conventional approaches to estimate HR image with Least Square (LS) method and Weighted Least Square (WLS) method are not able to reconstruct high-frequency region effectively in case its blur kernel is assumed Gaussian kernel in unknown system. Also, these methods produce jagging artifacts from the deficiency of LR frames. The proposed SR algorithm uses edge adaptive WLS method to reconstruct high-frequency region considering local properties and is applied to video sequence with block process to cope with local motions. Moreover, to apply video sequence with complex motions, we use selectively the correct information of reference frame to avoid errors from incorrect information. For accurate additional information from reference frames, the proposed algorithm determines additional information in reference frame by comparing with current frame and reference frame. The experiments demonstrate the superior performance of the proposed algorithm.

AB - Digital images and videos are used in many digital devices recently. Also, the resolution of display became larger than that of previous years. Image up-scaling algorithm is important issue since original input source is limited in transferring within data bandwidth. Among various up-scaling algorithms, Super-Resolution (SR) image reconstruction method is able to estimate high-resolution (HR) image using multiple low-resolution (LR) images. Conventional approaches to estimate HR image with Least Square (LS) method and Weighted Least Square (WLS) method are not able to reconstruct high-frequency region effectively in case its blur kernel is assumed Gaussian kernel in unknown system. Also, these methods produce jagging artifacts from the deficiency of LR frames. The proposed SR algorithm uses edge adaptive WLS method to reconstruct high-frequency region considering local properties and is applied to video sequence with block process to cope with local motions. Moreover, to apply video sequence with complex motions, we use selectively the correct information of reference frame to avoid errors from incorrect information. For accurate additional information from reference frames, the proposed algorithm determines additional information in reference frame by comparing with current frame and reference frame. The experiments demonstrate the superior performance of the proposed algorithm.

UR - http://www.scopus.com/inward/record.url?scp=84863136800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863136800&partnerID=8YFLogxK

U2 - 10.1117/12.905368

DO - 10.1117/12.905368

M3 - Conference contribution

AN - SCOPUS:84863136800

SN - 9780819489425

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Proceedings of SPIE-IS and T Electronic Imaging - Image Processing

ER -

Kwon JY, Yoo DS, Park JH, Park SH, Kang MG. Super-resolution image reconstruction with edge adaptive weight in video sequence. In Proceedings of SPIE-IS and T Electronic Imaging - Image Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II. 2012. 82950M. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.905368