An efficient selective perceptual-based super-resolution estimator

Lina Karam, Nabil G. Sadaka, Rony Ferzli, Zoran A. Ivanovski

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this paper, a selective perceptual-based (SELP) framework is presented to reduce the complexity of popular super-resolution (SR) algorithms while maintaining the desired quality of the enhanced images/video. A perceptual human visual system model is proposed to compute local contrast sensitivity thresholds. The obtained thresholds are used to select which pixels are super-resolved based on the perceived visibility of local edges. Processing only a set of perceptually significant pixels reduces significantly the computational complexity of SR algorithms without losing the achievable visual quality. The proposed SELP framework is integrated into a maximum-a posteriori-based SR algorithm as well as a fast two-stage fusion-restoration SR estimator. Simulation results show a significant reduction on average in computational complexity with comparable signal-to-noise ratio gains and visual quality.

Original languageEnglish (US)
Article number5873150
Pages (from-to)3470-3482
Number of pages13
JournalIEEE Transactions on Image Processing
Volume20
Issue number12
DOIs
StatePublished - Dec 2011

Fingerprint

Computational complexity
Pixels
Visibility
Restoration
Signal to noise ratio
Fusion reactions
Processing

Keywords

  • Edge detection
  • Human visual system (HVS)
  • Maximum a posteriori (MAP) estimator
  • Maximum-likelihood estimator
  • Perceptual quality
  • Reduced complexity
  • Super-resolution (SR)

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

An efficient selective perceptual-based super-resolution estimator. / Karam, Lina; Sadaka, Nabil G.; Ferzli, Rony; Ivanovski, Zoran A.

In: IEEE Transactions on Image Processing, Vol. 20, No. 12, 5873150, 12.2011, p. 3470-3482.

Research output: Contribution to journalArticle

Karam, Lina ; Sadaka, Nabil G. ; Ferzli, Rony ; Ivanovski, Zoran A. / An efficient selective perceptual-based super-resolution estimator. In: IEEE Transactions on Image Processing. 2011 ; Vol. 20, No. 12. pp. 3470-3482.
@article{d222c634580a4daa99a953b6f269b860,
title = "An efficient selective perceptual-based super-resolution estimator",
abstract = "In this paper, a selective perceptual-based (SELP) framework is presented to reduce the complexity of popular super-resolution (SR) algorithms while maintaining the desired quality of the enhanced images/video. A perceptual human visual system model is proposed to compute local contrast sensitivity thresholds. The obtained thresholds are used to select which pixels are super-resolved based on the perceived visibility of local edges. Processing only a set of perceptually significant pixels reduces significantly the computational complexity of SR algorithms without losing the achievable visual quality. The proposed SELP framework is integrated into a maximum-a posteriori-based SR algorithm as well as a fast two-stage fusion-restoration SR estimator. Simulation results show a significant reduction on average in computational complexity with comparable signal-to-noise ratio gains and visual quality.",
keywords = "Edge detection, Human visual system (HVS), Maximum a posteriori (MAP) estimator, Maximum-likelihood estimator, Perceptual quality, Reduced complexity, Super-resolution (SR)",
author = "Lina Karam and Sadaka, {Nabil G.} and Rony Ferzli and Ivanovski, {Zoran A.}",
year = "2011",
month = "12",
doi = "10.1109/TIP.2011.2159324",
language = "English (US)",
volume = "20",
pages = "3470--3482",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12",

}

TY - JOUR

T1 - An efficient selective perceptual-based super-resolution estimator

AU - Karam, Lina

AU - Sadaka, Nabil G.

AU - Ferzli, Rony

AU - Ivanovski, Zoran A.

PY - 2011/12

Y1 - 2011/12

N2 - In this paper, a selective perceptual-based (SELP) framework is presented to reduce the complexity of popular super-resolution (SR) algorithms while maintaining the desired quality of the enhanced images/video. A perceptual human visual system model is proposed to compute local contrast sensitivity thresholds. The obtained thresholds are used to select which pixels are super-resolved based on the perceived visibility of local edges. Processing only a set of perceptually significant pixels reduces significantly the computational complexity of SR algorithms without losing the achievable visual quality. The proposed SELP framework is integrated into a maximum-a posteriori-based SR algorithm as well as a fast two-stage fusion-restoration SR estimator. Simulation results show a significant reduction on average in computational complexity with comparable signal-to-noise ratio gains and visual quality.

AB - In this paper, a selective perceptual-based (SELP) framework is presented to reduce the complexity of popular super-resolution (SR) algorithms while maintaining the desired quality of the enhanced images/video. A perceptual human visual system model is proposed to compute local contrast sensitivity thresholds. The obtained thresholds are used to select which pixels are super-resolved based on the perceived visibility of local edges. Processing only a set of perceptually significant pixels reduces significantly the computational complexity of SR algorithms without losing the achievable visual quality. The proposed SELP framework is integrated into a maximum-a posteriori-based SR algorithm as well as a fast two-stage fusion-restoration SR estimator. Simulation results show a significant reduction on average in computational complexity with comparable signal-to-noise ratio gains and visual quality.

KW - Edge detection

KW - Human visual system (HVS)

KW - Maximum a posteriori (MAP) estimator

KW - Maximum-likelihood estimator

KW - Perceptual quality

KW - Reduced complexity

KW - Super-resolution (SR)

UR - http://www.scopus.com/inward/record.url?scp=82055197385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82055197385&partnerID=8YFLogxK

U2 - 10.1109/TIP.2011.2159324

DO - 10.1109/TIP.2011.2159324

M3 - Article

C2 - 21672677

AN - SCOPUS:82055197385

VL - 20

SP - 3470

EP - 3482

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 12

M1 - 5873150

ER -