Steganalysis of watermarking techniques using image quality metrics

I. Avcibaş, N. Memon, B. Sankur

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

Abstract

In this paper, we present techniques for steganalysis of images that have been potentially subjected to a watermarking algorithm. Our hypothesis is that a particular watermarking scheme leaves statistical evidence or structure that can be exploited for detection with the aid of proper selection of image features and multivariate regression analysis. We use some sophisticated image quality metrics as the feature set to distinguish between watermarked and unwatermarked images. To identify specific quality measures, which provide the best discriminative power, we use analysis of variance (ANOVA) techniques. The multivariate regression analysis is used on the selected quality metrics to build the optimal classifier using images and their blurred versions. The idea behind blurring is that the distance between an unwatermarked image and its blurred version is less than the distance between a watermarked image and its blurred version. Simulation results with a specific feature set and a well-known and commercially available watermarking technique indicates that our approach is able to accurately distinguish between watermarked and unwatermarked images.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsP.W. Wong, E.J. Delp
Pages523-531
Number of pages9
Volume4314
DOIs
StatePublished - 2001
EventSecurity and Watermarking of Multimedia Contents III - San Jose, CA, United States
Duration: Jan 22 2001Jan 25 2001

Other

OtherSecurity and Watermarking of Multimedia Contents III
CountryUnited States
CitySan Jose, CA
Period1/22/011/25/01

Fingerprint

Watermarking
Image quality
Regression analysis
Analysis of variance (ANOVA)
Classifiers
regression analysis
analysis of variance
blurring
classifiers
leaves

Keywords

  • Image quality measures
  • Multivariate regression analysis
  • Steganalysis
  • Watermarking

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Avcibaş, I., Memon, N., & Sankur, B. (2001). Steganalysis of watermarking techniques using image quality metrics. In P. W. Wong, & E. J. Delp (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 4314, pp. 523-531) https://doi.org/10.1117/12.435436

Steganalysis of watermarking techniques using image quality metrics. / Avcibaş, I.; Memon, N.; Sankur, B.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / P.W. Wong; E.J. Delp. Vol. 4314 2001. p. 523-531.

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

Avcibaş, I, Memon, N & Sankur, B 2001, Steganalysis of watermarking techniques using image quality metrics. in PW Wong & EJ Delp (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 4314, pp. 523-531, Security and Watermarking of Multimedia Contents III, San Jose, CA, United States, 1/22/01. https://doi.org/10.1117/12.435436
Avcibaş I, Memon N, Sankur B. Steganalysis of watermarking techniques using image quality metrics. In Wong PW, Delp EJ, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 4314. 2001. p. 523-531 https://doi.org/10.1117/12.435436
Avcibaş, I. ; Memon, N. ; Sankur, B. / Steganalysis of watermarking techniques using image quality metrics. Proceedings of SPIE - The International Society for Optical Engineering. editor / P.W. Wong ; E.J. Delp. Vol. 4314 2001. pp. 523-531
@inproceedings{deae0ee2be724966a7b65d26b9a71536,
title = "Steganalysis of watermarking techniques using image quality metrics",
abstract = "In this paper, we present techniques for steganalysis of images that have been potentially subjected to a watermarking algorithm. Our hypothesis is that a particular watermarking scheme leaves statistical evidence or structure that can be exploited for detection with the aid of proper selection of image features and multivariate regression analysis. We use some sophisticated image quality metrics as the feature set to distinguish between watermarked and unwatermarked images. To identify specific quality measures, which provide the best discriminative power, we use analysis of variance (ANOVA) techniques. The multivariate regression analysis is used on the selected quality metrics to build the optimal classifier using images and their blurred versions. The idea behind blurring is that the distance between an unwatermarked image and its blurred version is less than the distance between a watermarked image and its blurred version. Simulation results with a specific feature set and a well-known and commercially available watermarking technique indicates that our approach is able to accurately distinguish between watermarked and unwatermarked images.",
keywords = "Image quality measures, Multivariate regression analysis, Steganalysis, Watermarking",
author = "I. Avcibaş and N. Memon and B. Sankur",
year = "2001",
doi = "10.1117/12.435436",
language = "English (US)",
volume = "4314",
pages = "523--531",
editor = "P.W. Wong and E.J. Delp",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Steganalysis of watermarking techniques using image quality metrics

AU - Avcibaş, I.

AU - Memon, N.

AU - Sankur, B.

PY - 2001

Y1 - 2001

N2 - In this paper, we present techniques for steganalysis of images that have been potentially subjected to a watermarking algorithm. Our hypothesis is that a particular watermarking scheme leaves statistical evidence or structure that can be exploited for detection with the aid of proper selection of image features and multivariate regression analysis. We use some sophisticated image quality metrics as the feature set to distinguish between watermarked and unwatermarked images. To identify specific quality measures, which provide the best discriminative power, we use analysis of variance (ANOVA) techniques. The multivariate regression analysis is used on the selected quality metrics to build the optimal classifier using images and their blurred versions. The idea behind blurring is that the distance between an unwatermarked image and its blurred version is less than the distance between a watermarked image and its blurred version. Simulation results with a specific feature set and a well-known and commercially available watermarking technique indicates that our approach is able to accurately distinguish between watermarked and unwatermarked images.

AB - In this paper, we present techniques for steganalysis of images that have been potentially subjected to a watermarking algorithm. Our hypothesis is that a particular watermarking scheme leaves statistical evidence or structure that can be exploited for detection with the aid of proper selection of image features and multivariate regression analysis. We use some sophisticated image quality metrics as the feature set to distinguish between watermarked and unwatermarked images. To identify specific quality measures, which provide the best discriminative power, we use analysis of variance (ANOVA) techniques. The multivariate regression analysis is used on the selected quality metrics to build the optimal classifier using images and their blurred versions. The idea behind blurring is that the distance between an unwatermarked image and its blurred version is less than the distance between a watermarked image and its blurred version. Simulation results with a specific feature set and a well-known and commercially available watermarking technique indicates that our approach is able to accurately distinguish between watermarked and unwatermarked images.

KW - Image quality measures

KW - Multivariate regression analysis

KW - Steganalysis

KW - Watermarking

UR - http://www.scopus.com/inward/record.url?scp=0034775171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034775171&partnerID=8YFLogxK

U2 - 10.1117/12.435436

DO - 10.1117/12.435436

M3 - Conference contribution

AN - SCOPUS:0034775171

VL - 4314

SP - 523

EP - 531

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

A2 - Wong, P.W.

A2 - Delp, E.J.

ER -