Cargando…

Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack

This paper proposes a method to embed and extract a watermark on a digital hologram using a deep neural network. The entire algorithm for watermarking digital holograms consists of three sub-networks. For the robustness of watermarking, an attack simulation is inserted inside the deep neural network...

Descripción completa

Detalles Bibliográficos
Autores principales: Kang, Ji-Won, Lee, Jae-Eun, Choi, Jang-Hwan, Kim, Woosuk, Kim, Jin-Kyum, Kim, Dong-Wook, Seo, Young-Ho
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8347406/
https://www.ncbi.nlm.nih.gov/pubmed/34372214
http://dx.doi.org/10.3390/s21154977
_version_ 1783735081971482624
author Kang, Ji-Won
Lee, Jae-Eun
Choi, Jang-Hwan
Kim, Woosuk
Kim, Jin-Kyum
Kim, Dong-Wook
Seo, Young-Ho
author_facet Kang, Ji-Won
Lee, Jae-Eun
Choi, Jang-Hwan
Kim, Woosuk
Kim, Jin-Kyum
Kim, Dong-Wook
Seo, Young-Ho
author_sort Kang, Ji-Won
collection PubMed
description This paper proposes a method to embed and extract a watermark on a digital hologram using a deep neural network. The entire algorithm for watermarking digital holograms consists of three sub-networks. For the robustness of watermarking, an attack simulation is inserted inside the deep neural network. By including attack simulation and holographic reconstruction in the network, the deep neural network for watermarking can simultaneously train invisibility and robustness. We propose a network training method using hologram and reconstruction. After training the proposed network, we analyze the robustness of each attack and perform re-training according to this result to propose a method to improve the robustness. We quantitatively evaluate the results of robustness against various attacks and show the reliability of the proposed technique.
format Online
Article
Text
id pubmed-8347406
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83474062021-08-08 Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack Kang, Ji-Won Lee, Jae-Eun Choi, Jang-Hwan Kim, Woosuk Kim, Jin-Kyum Kim, Dong-Wook Seo, Young-Ho Sensors (Basel) Article This paper proposes a method to embed and extract a watermark on a digital hologram using a deep neural network. The entire algorithm for watermarking digital holograms consists of three sub-networks. For the robustness of watermarking, an attack simulation is inserted inside the deep neural network. By including attack simulation and holographic reconstruction in the network, the deep neural network for watermarking can simultaneously train invisibility and robustness. We propose a network training method using hologram and reconstruction. After training the proposed network, we analyze the robustness of each attack and perform re-training according to this result to propose a method to improve the robustness. We quantitatively evaluate the results of robustness against various attacks and show the reliability of the proposed technique. MDPI 2021-07-22 /pmc/articles/PMC8347406/ /pubmed/34372214 http://dx.doi.org/10.3390/s21154977 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kang, Ji-Won
Lee, Jae-Eun
Choi, Jang-Hwan
Kim, Woosuk
Kim, Jin-Kyum
Kim, Dong-Wook
Seo, Young-Ho
Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack
title Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack
title_full Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack
title_fullStr Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack
title_full_unstemmed Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack
title_short Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack
title_sort digital hologram watermarking based on multiple deep neural networks training reconstruction and attack
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8347406/
https://www.ncbi.nlm.nih.gov/pubmed/34372214
http://dx.doi.org/10.3390/s21154977
work_keys_str_mv AT kangjiwon digitalhologramwatermarkingbasedonmultipledeepneuralnetworkstrainingreconstructionandattack
AT leejaeeun digitalhologramwatermarkingbasedonmultipledeepneuralnetworkstrainingreconstructionandattack
AT choijanghwan digitalhologramwatermarkingbasedonmultipledeepneuralnetworkstrainingreconstructionandattack
AT kimwoosuk digitalhologramwatermarkingbasedonmultipledeepneuralnetworkstrainingreconstructionandattack
AT kimjinkyum digitalhologramwatermarkingbasedonmultipledeepneuralnetworkstrainingreconstructionandattack
AT kimdongwook digitalhologramwatermarkingbasedonmultipledeepneuralnetworkstrainingreconstructionandattack
AT seoyoungho digitalhologramwatermarkingbasedonmultipledeepneuralnetworkstrainingreconstructionandattack