Unified Model for Contrast Enhancement and Denoising

Alex Pappachen James, Olga Krestinskaya, Joshin John Mathew

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

3 Citations (Scopus)

Abstract

In this paper, we attempt a challenging task to unify two important complementary operations, i.e. contrast enhancement and denoising, that is required in most image processing applications. The proposed method is implemented using practical analog circuit configurations that can lead to near real-time processing capabilities useful to be integrated with vision sensors. Metrics used for performance includes estimation of Residual Noise Level (RNL), Structural Similarity Index Measure (SSIM), Output-to-Input Contrast Ratio (CRo-i), and its combined score (SCD). The class of contrast stretching methods has resulted in higher noise levels (RNL ≥ 7) along with increased contrast measures (CRo-i ≥ eight times than that of the input image) and SSIM ≤ 0.52. Denoising methods generates images with lesser noise levels (RNL ≤ 0.2308), poor contrast enhancements (CRo-i ≤ 1.31) and with best structural similarity (SSIM ≥ 0.85). In contrast, the proposed model offers best contrast stretching (CRo-i = 5.83), least noise (RNL = 0.02), a descent structural similarity (SSIM = 0.6453) and the highest combined score (SCD = 169).

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017
PublisherIEEE Computer Society
Pages379-384
Number of pages6
Volume2017-July
ISBN (Electronic)9781509067626
DOIs
Publication statusPublished - Jul 20 2017
Externally publishedYes
Event2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017 - Bochum, North Rhine-Westfalia, Germany
Duration: Jul 3 2017Jul 5 2017

Conference

Conference2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017
CountryGermany
CityBochum, North Rhine-Westfalia
Period7/3/177/5/17

Fingerprint

Stretching
Analog circuits
Image processing
Sensors
Processing

Keywords

  • Analog Circuits
  • Contrast Enhancement
  • Denoising
  • Filter

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

James, A. P., Krestinskaya, O., & Mathew, J. J. (2017). Unified Model for Contrast Enhancement and Denoising. In Proceedings - 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017 (Vol. 2017-July, pp. 379-384). [7987549] IEEE Computer Society. https://doi.org/10.1109/ISVLSI.2017.73

Unified Model for Contrast Enhancement and Denoising. / James, Alex Pappachen; Krestinskaya, Olga; Mathew, Joshin John.

Proceedings - 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017. Vol. 2017-July IEEE Computer Society, 2017. p. 379-384 7987549.

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

James, AP, Krestinskaya, O & Mathew, JJ 2017, Unified Model for Contrast Enhancement and Denoising. in Proceedings - 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017. vol. 2017-July, 7987549, IEEE Computer Society, pp. 379-384, 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017, Bochum, North Rhine-Westfalia, Germany, 7/3/17. https://doi.org/10.1109/ISVLSI.2017.73
James AP, Krestinskaya O, Mathew JJ. Unified Model for Contrast Enhancement and Denoising. In Proceedings - 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017. Vol. 2017-July. IEEE Computer Society. 2017. p. 379-384. 7987549 https://doi.org/10.1109/ISVLSI.2017.73
James, Alex Pappachen ; Krestinskaya, Olga ; Mathew, Joshin John. / Unified Model for Contrast Enhancement and Denoising. Proceedings - 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017. Vol. 2017-July IEEE Computer Society, 2017. pp. 379-384
@inproceedings{f7d75e7e6bac48099adcc70e2e580163,
title = "Unified Model for Contrast Enhancement and Denoising",
abstract = "In this paper, we attempt a challenging task to unify two important complementary operations, i.e. contrast enhancement and denoising, that is required in most image processing applications. The proposed method is implemented using practical analog circuit configurations that can lead to near real-time processing capabilities useful to be integrated with vision sensors. Metrics used for performance includes estimation of Residual Noise Level (RNL), Structural Similarity Index Measure (SSIM), Output-to-Input Contrast Ratio (CRo-i), and its combined score (SCD). The class of contrast stretching methods has resulted in higher noise levels (RNL ≥ 7) along with increased contrast measures (CRo-i ≥ eight times than that of the input image) and SSIM ≤ 0.52. Denoising methods generates images with lesser noise levels (RNL ≤ 0.2308), poor contrast enhancements (CRo-i ≤ 1.31) and with best structural similarity (SSIM ≥ 0.85). In contrast, the proposed model offers best contrast stretching (CRo-i = 5.83), least noise (RNL = 0.02), a descent structural similarity (SSIM = 0.6453) and the highest combined score (SCD = 169).",
keywords = "Analog Circuits, Contrast Enhancement, Denoising, Filter",
author = "James, {Alex Pappachen} and Olga Krestinskaya and Mathew, {Joshin John}",
year = "2017",
month = "7",
day = "20",
doi = "10.1109/ISVLSI.2017.73",
language = "English",
volume = "2017-July",
pages = "379--384",
booktitle = "Proceedings - 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Unified Model for Contrast Enhancement and Denoising

AU - James, Alex Pappachen

AU - Krestinskaya, Olga

AU - Mathew, Joshin John

PY - 2017/7/20

Y1 - 2017/7/20

N2 - In this paper, we attempt a challenging task to unify two important complementary operations, i.e. contrast enhancement and denoising, that is required in most image processing applications. The proposed method is implemented using practical analog circuit configurations that can lead to near real-time processing capabilities useful to be integrated with vision sensors. Metrics used for performance includes estimation of Residual Noise Level (RNL), Structural Similarity Index Measure (SSIM), Output-to-Input Contrast Ratio (CRo-i), and its combined score (SCD). The class of contrast stretching methods has resulted in higher noise levels (RNL ≥ 7) along with increased contrast measures (CRo-i ≥ eight times than that of the input image) and SSIM ≤ 0.52. Denoising methods generates images with lesser noise levels (RNL ≤ 0.2308), poor contrast enhancements (CRo-i ≤ 1.31) and with best structural similarity (SSIM ≥ 0.85). In contrast, the proposed model offers best contrast stretching (CRo-i = 5.83), least noise (RNL = 0.02), a descent structural similarity (SSIM = 0.6453) and the highest combined score (SCD = 169).

AB - In this paper, we attempt a challenging task to unify two important complementary operations, i.e. contrast enhancement and denoising, that is required in most image processing applications. The proposed method is implemented using practical analog circuit configurations that can lead to near real-time processing capabilities useful to be integrated with vision sensors. Metrics used for performance includes estimation of Residual Noise Level (RNL), Structural Similarity Index Measure (SSIM), Output-to-Input Contrast Ratio (CRo-i), and its combined score (SCD). The class of contrast stretching methods has resulted in higher noise levels (RNL ≥ 7) along with increased contrast measures (CRo-i ≥ eight times than that of the input image) and SSIM ≤ 0.52. Denoising methods generates images with lesser noise levels (RNL ≤ 0.2308), poor contrast enhancements (CRo-i ≤ 1.31) and with best structural similarity (SSIM ≥ 0.85). In contrast, the proposed model offers best contrast stretching (CRo-i = 5.83), least noise (RNL = 0.02), a descent structural similarity (SSIM = 0.6453) and the highest combined score (SCD = 169).

KW - Analog Circuits

KW - Contrast Enhancement

KW - Denoising

KW - Filter

UR - http://www.scopus.com/inward/record.url?scp=85027269244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027269244&partnerID=8YFLogxK

U2 - 10.1109/ISVLSI.2017.73

DO - 10.1109/ISVLSI.2017.73

M3 - Conference contribution

VL - 2017-July

SP - 379

EP - 384

BT - Proceedings - 2017 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2017

PB - IEEE Computer Society

ER -