Robust super-resolution based on pixel-level selectivity

Zoran A. Ivanovski, Ljupcho Panovski, Lina Karam

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

11 Citations (Scopus)

Abstract

In this paper, a new technique for robust super-resolution (SR) from compressed video is presented. The proposed method exploits the differences between low-resolution images at the pixel level, in order to determine the usability of every pixel in the low-resolution images for SR enhancement. Only the pixels, from the lowresolution images, that are determined to be usable, are included in the L 2-norm minimization procedure. Three different usability criterions are proposed, maximum distance from the median - MDM, maximum distance from initial image - MDIM, and maximum distance from the SR estimate - MDSRE. The results obtained with real video sequences demonstrate superior quality of the resulting enhanced image in the presence of outliers and same quality without outliers when compared to existing L 2-norm minimization techniques. At the same time, the proposed scheme produces sharper images as compared to L 1-norm minimization techniques.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume6077
DOIs
StatePublished - 2006
EventVisual Communications and Image Processing 2006 - San Jose, CA, United States
Duration: Jan 17 2006Jan 19 2006

Other

OtherVisual Communications and Image Processing 2006
CountryUnited States
CitySan Jose, CA
Period1/17/061/19/06

Fingerprint

selectivity
Pixels
pixels
norms
Image resolution
image resolution
optimization
video compression
augmentation
estimates

Keywords

  • Compressed video
  • Compression artifacts
  • Motion estimation
  • Super-resolution
  • Video enhancement

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Ivanovski, Z. A., Panovski, L., & Karam, L. (2006). Robust super-resolution based on pixel-level selectivity. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 6077). [607707] https://doi.org/10.1117/12.642722

Robust super-resolution based on pixel-level selectivity. / Ivanovski, Zoran A.; Panovski, Ljupcho; Karam, Lina.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6077 2006. 607707.

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

Ivanovski, ZA, Panovski, L & Karam, L 2006, Robust super-resolution based on pixel-level selectivity. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 6077, 607707, Visual Communications and Image Processing 2006, San Jose, CA, United States, 1/17/06. https://doi.org/10.1117/12.642722
Ivanovski ZA, Panovski L, Karam L. Robust super-resolution based on pixel-level selectivity. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6077. 2006. 607707 https://doi.org/10.1117/12.642722
Ivanovski, Zoran A. ; Panovski, Ljupcho ; Karam, Lina. / Robust super-resolution based on pixel-level selectivity. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 6077 2006.
@inproceedings{5aa13891844749e68b05c6bdf44c5310,
title = "Robust super-resolution based on pixel-level selectivity",
abstract = "In this paper, a new technique for robust super-resolution (SR) from compressed video is presented. The proposed method exploits the differences between low-resolution images at the pixel level, in order to determine the usability of every pixel in the low-resolution images for SR enhancement. Only the pixels, from the lowresolution images, that are determined to be usable, are included in the L 2-norm minimization procedure. Three different usability criterions are proposed, maximum distance from the median - MDM, maximum distance from initial image - MDIM, and maximum distance from the SR estimate - MDSRE. The results obtained with real video sequences demonstrate superior quality of the resulting enhanced image in the presence of outliers and same quality without outliers when compared to existing L 2-norm minimization techniques. At the same time, the proposed scheme produces sharper images as compared to L 1-norm minimization techniques.",
keywords = "Compressed video, Compression artifacts, Motion estimation, Super-resolution, Video enhancement",
author = "Ivanovski, {Zoran A.} and Ljupcho Panovski and Lina Karam",
year = "2006",
doi = "10.1117/12.642722",
language = "English (US)",
isbn = "0819461172",
volume = "6077",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Robust super-resolution based on pixel-level selectivity

AU - Ivanovski, Zoran A.

AU - Panovski, Ljupcho

AU - Karam, Lina

PY - 2006

Y1 - 2006

N2 - In this paper, a new technique for robust super-resolution (SR) from compressed video is presented. The proposed method exploits the differences between low-resolution images at the pixel level, in order to determine the usability of every pixel in the low-resolution images for SR enhancement. Only the pixels, from the lowresolution images, that are determined to be usable, are included in the L 2-norm minimization procedure. Three different usability criterions are proposed, maximum distance from the median - MDM, maximum distance from initial image - MDIM, and maximum distance from the SR estimate - MDSRE. The results obtained with real video sequences demonstrate superior quality of the resulting enhanced image in the presence of outliers and same quality without outliers when compared to existing L 2-norm minimization techniques. At the same time, the proposed scheme produces sharper images as compared to L 1-norm minimization techniques.

AB - In this paper, a new technique for robust super-resolution (SR) from compressed video is presented. The proposed method exploits the differences between low-resolution images at the pixel level, in order to determine the usability of every pixel in the low-resolution images for SR enhancement. Only the pixels, from the lowresolution images, that are determined to be usable, are included in the L 2-norm minimization procedure. Three different usability criterions are proposed, maximum distance from the median - MDM, maximum distance from initial image - MDIM, and maximum distance from the SR estimate - MDSRE. The results obtained with real video sequences demonstrate superior quality of the resulting enhanced image in the presence of outliers and same quality without outliers when compared to existing L 2-norm minimization techniques. At the same time, the proposed scheme produces sharper images as compared to L 1-norm minimization techniques.

KW - Compressed video

KW - Compression artifacts

KW - Motion estimation

KW - Super-resolution

KW - Video enhancement

UR - http://www.scopus.com/inward/record.url?scp=33645973253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645973253&partnerID=8YFLogxK

U2 - 10.1117/12.642722

DO - 10.1117/12.642722

M3 - Conference contribution

SN - 0819461172

SN - 9780819461179

SN - 0819461172

SN - 9780819461179

VL - 6077

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

ER -