Damageless digital watermarking by machine learning: A method of key generation for information extraction using artificial neural networks

Kensuke Naoe, Hideyasu Sasaki, Yoshiyasu Takefuji

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

Abstract

Soft computing in the area of information security is a promising field for the creation of intelligent solutions. This paper discusses a method for digital watermarking using artificial neural networks to realize secure copyright protection of visual information without any damage. The discussed watermark extraction keys and feature extraction keys identify the secure and unique hidden patterns for proper digital watermarks. In the experiments, we have shown that the proposed method is robust to high pass filtering and JPEG compression of visual information, only for those watermark extraction keys which were able to identify the proper hidden bit patterns from original visual information using corresponding feature extraction keys. The proposed method is to contribute to secure visual digital watermarking without damaging or losing any detailed data of visual information.

Original languageEnglish
Title of host publicationSoCPaR 2009 - Soft Computing and Pattern Recognition
Pages545-550
Number of pages6
DOIs
Publication statusPublished - 2009
EventInternational Conference on Soft Computing and Pattern Recognition, SoCPaR 2009 - Malacca, Malaysia
Duration: 2009 Dec 42009 Dec 7

Other

OtherInternational Conference on Soft Computing and Pattern Recognition, SoCPaR 2009
CountryMalaysia
CityMalacca
Period09/12/409/12/7

Fingerprint

Digital watermarking
Learning systems
Feature extraction
Neural networks
Soft computing
Security of data
Experiments

Keywords

  • Artificial neural networks
  • Digital rights management
  • Digital watermarking
  • Information hiding
  • Machine learning

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Damageless digital watermarking by machine learning : A method of key generation for information extraction using artificial neural networks. / Naoe, Kensuke; Sasaki, Hideyasu; Takefuji, Yoshiyasu.

SoCPaR 2009 - Soft Computing and Pattern Recognition. 2009. p. 545-550 5368676.

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

Naoe, K, Sasaki, H & Takefuji, Y 2009, Damageless digital watermarking by machine learning: A method of key generation for information extraction using artificial neural networks. in SoCPaR 2009 - Soft Computing and Pattern Recognition., 5368676, pp. 545-550, International Conference on Soft Computing and Pattern Recognition, SoCPaR 2009, Malacca, Malaysia, 09/12/4. https://doi.org/10.1109/SoCPaR.2009.109
Naoe, Kensuke ; Sasaki, Hideyasu ; Takefuji, Yoshiyasu. / Damageless digital watermarking by machine learning : A method of key generation for information extraction using artificial neural networks. SoCPaR 2009 - Soft Computing and Pattern Recognition. 2009. pp. 545-550
@inproceedings{64d165524f5a4afdb27486dc24337798,
title = "Damageless digital watermarking by machine learning: A method of key generation for information extraction using artificial neural networks",
abstract = "Soft computing in the area of information security is a promising field for the creation of intelligent solutions. This paper discusses a method for digital watermarking using artificial neural networks to realize secure copyright protection of visual information without any damage. The discussed watermark extraction keys and feature extraction keys identify the secure and unique hidden patterns for proper digital watermarks. In the experiments, we have shown that the proposed method is robust to high pass filtering and JPEG compression of visual information, only for those watermark extraction keys which were able to identify the proper hidden bit patterns from original visual information using corresponding feature extraction keys. The proposed method is to contribute to secure visual digital watermarking without damaging or losing any detailed data of visual information.",
keywords = "Artificial neural networks, Digital rights management, Digital watermarking, Information hiding, Machine learning",
author = "Kensuke Naoe and Hideyasu Sasaki and Yoshiyasu Takefuji",
year = "2009",
doi = "10.1109/SoCPaR.2009.109",
language = "English",
isbn = "9780769538792",
pages = "545--550",
booktitle = "SoCPaR 2009 - Soft Computing and Pattern Recognition",

}

TY - GEN

T1 - Damageless digital watermarking by machine learning

T2 - A method of key generation for information extraction using artificial neural networks

AU - Naoe, Kensuke

AU - Sasaki, Hideyasu

AU - Takefuji, Yoshiyasu

PY - 2009

Y1 - 2009

N2 - Soft computing in the area of information security is a promising field for the creation of intelligent solutions. This paper discusses a method for digital watermarking using artificial neural networks to realize secure copyright protection of visual information without any damage. The discussed watermark extraction keys and feature extraction keys identify the secure and unique hidden patterns for proper digital watermarks. In the experiments, we have shown that the proposed method is robust to high pass filtering and JPEG compression of visual information, only for those watermark extraction keys which were able to identify the proper hidden bit patterns from original visual information using corresponding feature extraction keys. The proposed method is to contribute to secure visual digital watermarking without damaging or losing any detailed data of visual information.

AB - Soft computing in the area of information security is a promising field for the creation of intelligent solutions. This paper discusses a method for digital watermarking using artificial neural networks to realize secure copyright protection of visual information without any damage. The discussed watermark extraction keys and feature extraction keys identify the secure and unique hidden patterns for proper digital watermarks. In the experiments, we have shown that the proposed method is robust to high pass filtering and JPEG compression of visual information, only for those watermark extraction keys which were able to identify the proper hidden bit patterns from original visual information using corresponding feature extraction keys. The proposed method is to contribute to secure visual digital watermarking without damaging or losing any detailed data of visual information.

KW - Artificial neural networks

KW - Digital rights management

KW - Digital watermarking

KW - Information hiding

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=77649324871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649324871&partnerID=8YFLogxK

U2 - 10.1109/SoCPaR.2009.109

DO - 10.1109/SoCPaR.2009.109

M3 - Conference contribution

AN - SCOPUS:77649324871

SN - 9780769538792

SP - 545

EP - 550

BT - SoCPaR 2009 - Soft Computing and Pattern Recognition

ER -