Watermarking-based image authentication with recovery capability using halftoning technique

Research output: Contribution to journalArticleResearchpeer-review

45 Citations (Scopus)

Abstract

In this paper two watermarking algorithms for image content authentication with localization and recovery capability of the tampered regions are proposed. In both algorithms, a halftone version of the original gray-scale image is used as an approximated version of the host image (image digest) which is then embedded as a watermark sequence into given transform domains of the host image. In the first algorithm, the Integer Wavelet Transform (IWT) is used for watermark embedding which is denominated WIA-IWT (Watermarking-based Image Authentication using IWT), while in the second one, the Discrete Cosine Transform (DCT) domain is used for this purpose, we call this algorithm WIA-DCT (Watermarking-based Image Authentication using DCT). In the authentication stage the tampered regions are detected using the Structural Similarity index (SSIM) criterion, which are then recovered using the extracted halftone image. In the recovery stage, a Multilayer Perceptron (MLP) neural network is used to carry out an inverse halftoning process to improve the recovered image quality. The experimental results demonstrate the robustness of both algorithms against content preserved modifications, such as JPEG compression, as well as an effective authentication and recovery capability. Also the proposed algorithms are compared with some previously proposed content authentication algorithms with recovery capability to show the better performance of the proposed algorithms. © 2012 Elsevier B.V.
Original languageAmerican English
Pages (from-to)69-83
Number of pages60
JournalSignal Processing: Image Communication
DOIs
StatePublished - 1 Jan 2013

Fingerprint

Watermarking
Authentication
Recovery
transform
Discrete cosine transforms
Wavelet transforms
wavelet
Multilayer neural networks
similarity index
Image quality
Neural networks
compression

Cite this

@article{506f11a8593d4af892bfe85973f4c686,
title = "Watermarking-based image authentication with recovery capability using halftoning technique",
abstract = "In this paper two watermarking algorithms for image content authentication with localization and recovery capability of the tampered regions are proposed. In both algorithms, a halftone version of the original gray-scale image is used as an approximated version of the host image (image digest) which is then embedded as a watermark sequence into given transform domains of the host image. In the first algorithm, the Integer Wavelet Transform (IWT) is used for watermark embedding which is denominated WIA-IWT (Watermarking-based Image Authentication using IWT), while in the second one, the Discrete Cosine Transform (DCT) domain is used for this purpose, we call this algorithm WIA-DCT (Watermarking-based Image Authentication using DCT). In the authentication stage the tampered regions are detected using the Structural Similarity index (SSIM) criterion, which are then recovered using the extracted halftone image. In the recovery stage, a Multilayer Perceptron (MLP) neural network is used to carry out an inverse halftoning process to improve the recovered image quality. The experimental results demonstrate the robustness of both algorithms against content preserved modifications, such as JPEG compression, as well as an effective authentication and recovery capability. Also the proposed algorithms are compared with some previously proposed content authentication algorithms with recovery capability to show the better performance of the proposed algorithms. {\circledC} 2012 Elsevier B.V.",
author = "Luis Rosales-Roldan and Manuel Cedillo-Hernandez and Mariko Nakano-Miyatake and Hector Perez-Meana and Brian Kurkoski",
year = "2013",
month = "1",
day = "1",
doi = "10.1016/j.image.2012.11.006",
language = "American English",
pages = "69--83",
journal = "Signal Processing: Image Communication",
issn = "0923-5965",
publisher = "Elsevier",

}

Watermarking-based image authentication with recovery capability using halftoning technique. / Rosales-Roldan, Luis; Cedillo-Hernandez, Manuel; Nakano-Miyatake, Mariko; Perez-Meana, Hector; Kurkoski, Brian.

In: Signal Processing: Image Communication, 01.01.2013, p. 69-83.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Watermarking-based image authentication with recovery capability using halftoning technique

AU - Rosales-Roldan, Luis

AU - Cedillo-Hernandez, Manuel

AU - Nakano-Miyatake, Mariko

AU - Perez-Meana, Hector

AU - Kurkoski, Brian

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this paper two watermarking algorithms for image content authentication with localization and recovery capability of the tampered regions are proposed. In both algorithms, a halftone version of the original gray-scale image is used as an approximated version of the host image (image digest) which is then embedded as a watermark sequence into given transform domains of the host image. In the first algorithm, the Integer Wavelet Transform (IWT) is used for watermark embedding which is denominated WIA-IWT (Watermarking-based Image Authentication using IWT), while in the second one, the Discrete Cosine Transform (DCT) domain is used for this purpose, we call this algorithm WIA-DCT (Watermarking-based Image Authentication using DCT). In the authentication stage the tampered regions are detected using the Structural Similarity index (SSIM) criterion, which are then recovered using the extracted halftone image. In the recovery stage, a Multilayer Perceptron (MLP) neural network is used to carry out an inverse halftoning process to improve the recovered image quality. The experimental results demonstrate the robustness of both algorithms against content preserved modifications, such as JPEG compression, as well as an effective authentication and recovery capability. Also the proposed algorithms are compared with some previously proposed content authentication algorithms with recovery capability to show the better performance of the proposed algorithms. © 2012 Elsevier B.V.

AB - In this paper two watermarking algorithms for image content authentication with localization and recovery capability of the tampered regions are proposed. In both algorithms, a halftone version of the original gray-scale image is used as an approximated version of the host image (image digest) which is then embedded as a watermark sequence into given transform domains of the host image. In the first algorithm, the Integer Wavelet Transform (IWT) is used for watermark embedding which is denominated WIA-IWT (Watermarking-based Image Authentication using IWT), while in the second one, the Discrete Cosine Transform (DCT) domain is used for this purpose, we call this algorithm WIA-DCT (Watermarking-based Image Authentication using DCT). In the authentication stage the tampered regions are detected using the Structural Similarity index (SSIM) criterion, which are then recovered using the extracted halftone image. In the recovery stage, a Multilayer Perceptron (MLP) neural network is used to carry out an inverse halftoning process to improve the recovered image quality. The experimental results demonstrate the robustness of both algorithms against content preserved modifications, such as JPEG compression, as well as an effective authentication and recovery capability. Also the proposed algorithms are compared with some previously proposed content authentication algorithms with recovery capability to show the better performance of the proposed algorithms. © 2012 Elsevier B.V.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84871721013&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84871721013&origin=inward

U2 - 10.1016/j.image.2012.11.006

DO - 10.1016/j.image.2012.11.006

M3 - Article

SP - 69

EP - 83

JO - Signal Processing: Image Communication

JF - Signal Processing: Image Communication

SN - 0923-5965

ER -