A robust image zero-watermarking using convolutional neural networks

Atoany Fierro-Radilla; Mariko Nakano-Miyatake; Manuel Cedillo-Hernandez; Laura Cleofas-Sanchez; Hector Perez-Meana

doi:10.1109/IWBF.2019.8739245

A robust image zero-watermarking using convolutional neural networks

Atoany Fierro-Radilla, Mariko Nakano-Miyatake, Manuel Cedillo-Hernandez, Laura Cleofas-Sanchez, Hector Perez-Meana

Escuela Superior de Ingeniería Mecánica y Eléctrica (ESIME), Unidad Culhuacán

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

39 Scopus citations

Abstract

In the image zero-watermarking techniques, a watermark sequence is not physically embedded into the host image but has a logical linkage with the host image. This property of zero-watermarking is desirable for some kinds of images in which a minimum distortion may cause serious detection or diagnostic errors, such as medical images and remote sensing images. In this paper, we propose a robust zero-watermarking algorithm based on the Convolutional Neural Networks (CNN) and deep learning algorithm, in which robust inherent features of image is generated by the CNN, and it is combined with the owner's watermark sequence using XOR operation. The experimental results show the watermark robustness against several attacks and common image processing.

Original language	English
Title of host publication	2019 7th International Workshop on Biometrics and Forensics, IWBF 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728106229
DOIs	https://doi.org/10.1109/IWBF.2019.8739245
State	Published - May 2019
Event	7th International Workshop on Biometrics and Forensics, IWBF 2019 - Cancun, Mexico Duration: 2 May 2019 → 3 May 2019

Publication series

Name	2019 7th International Workshop on Biometrics and Forensics, IWBF 2019

Conference

Conference	7th International Workshop on Biometrics and Forensics, IWBF 2019
Country/Territory	Mexico
City	Cancun
Period	2/05/19 → 3/05/19

Keywords

Convolutional Neural Networks
Deep Learning
Robust Features
Zero-watermarking

Access to Document

10.1109/IWBF.2019.8739245

Cite this

Fierro-Radilla, A., Nakano-Miyatake, M., Cedillo-Hernandez, M., Cleofas-Sanchez, L., & Perez-Meana, H. (2019). A robust image zero-watermarking using convolutional neural networks. In 2019 7th International Workshop on Biometrics and Forensics, IWBF 2019 Article 8739245 (2019 7th International Workshop on Biometrics and Forensics, IWBF 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IWBF.2019.8739245

@inproceedings{53ffd6d59a334cf19081ef12a2bac342,

title = "A robust image zero-watermarking using convolutional neural networks",

abstract = "In the image zero-watermarking techniques, a watermark sequence is not physically embedded into the host image but has a logical linkage with the host image. This property of zero-watermarking is desirable for some kinds of images in which a minimum distortion may cause serious detection or diagnostic errors, such as medical images and remote sensing images. In this paper, we propose a robust zero-watermarking algorithm based on the Convolutional Neural Networks (CNN) and deep learning algorithm, in which robust inherent features of image is generated by the CNN, and it is combined with the owner's watermark sequence using XOR operation. The experimental results show the watermark robustness against several attacks and common image processing.",

keywords = "Convolutional Neural Networks, Deep Learning, Robust Features, Zero-watermarking",

author = "Atoany Fierro-Radilla and Mariko Nakano-Miyatake and Manuel Cedillo-Hernandez and Laura Cleofas-Sanchez and Hector Perez-Meana",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 7th International Workshop on Biometrics and Forensics, IWBF 2019 ; Conference date: 02-05-2019 Through 03-05-2019",

year = "2019",

month = may,

doi = "10.1109/IWBF.2019.8739245",

language = "Ingl{\'e}s",

series = "2019 7th International Workshop on Biometrics and Forensics, IWBF 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 7th International Workshop on Biometrics and Forensics, IWBF 2019",

address = "Estados Unidos",

}

Fierro-Radilla, A, Nakano-Miyatake, M , Cedillo-Hernandez, M, Cleofas-Sanchez, L & Perez-Meana, H 2019, A robust image zero-watermarking using convolutional neural networks. in 2019 7th International Workshop on Biometrics and Forensics, IWBF 2019., 8739245, 2019 7th International Workshop on Biometrics and Forensics, IWBF 2019, Institute of Electrical and Electronics Engineers Inc., 7th International Workshop on Biometrics and Forensics, IWBF 2019, Cancun, Mexico, 2/05/19. https://doi.org/10.1109/IWBF.2019.8739245

A robust image zero-watermarking using convolutional neural networks. / Fierro-Radilla, Atoany; Nakano-Miyatake, Mariko ; Cedillo-Hernandez, Manuel et al.
2019 7th International Workshop on Biometrics and Forensics, IWBF 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8739245 (2019 7th International Workshop on Biometrics and Forensics, IWBF 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A robust image zero-watermarking using convolutional neural networks

AU - Fierro-Radilla, Atoany

AU - Nakano-Miyatake, Mariko

AU - Cedillo-Hernandez, Manuel

AU - Cleofas-Sanchez, Laura

AU - Perez-Meana, Hector

PY - 2019/5

Y1 - 2019/5

N2 - In the image zero-watermarking techniques, a watermark sequence is not physically embedded into the host image but has a logical linkage with the host image. This property of zero-watermarking is desirable for some kinds of images in which a minimum distortion may cause serious detection or diagnostic errors, such as medical images and remote sensing images. In this paper, we propose a robust zero-watermarking algorithm based on the Convolutional Neural Networks (CNN) and deep learning algorithm, in which robust inherent features of image is generated by the CNN, and it is combined with the owner's watermark sequence using XOR operation. The experimental results show the watermark robustness against several attacks and common image processing.

AB - In the image zero-watermarking techniques, a watermark sequence is not physically embedded into the host image but has a logical linkage with the host image. This property of zero-watermarking is desirable for some kinds of images in which a minimum distortion may cause serious detection or diagnostic errors, such as medical images and remote sensing images. In this paper, we propose a robust zero-watermarking algorithm based on the Convolutional Neural Networks (CNN) and deep learning algorithm, in which robust inherent features of image is generated by the CNN, and it is combined with the owner's watermark sequence using XOR operation. The experimental results show the watermark robustness against several attacks and common image processing.

KW - Convolutional Neural Networks

KW - Deep Learning

KW - Robust Features

KW - Zero-watermarking

UR - http://www.scopus.com/inward/record.url?scp=85068443113&partnerID=8YFLogxK

U2 - 10.1109/IWBF.2019.8739245

DO - 10.1109/IWBF.2019.8739245

M3 - Contribución a la conferencia

AN - SCOPUS:85068443113

T3 - 2019 7th International Workshop on Biometrics and Forensics, IWBF 2019

BT - 2019 7th International Workshop on Biometrics and Forensics, IWBF 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th International Workshop on Biometrics and Forensics, IWBF 2019

Y2 - 2 May 2019 through 3 May 2019

ER -

Fierro-Radilla A, Nakano-Miyatake M , Cedillo-Hernandez M, Cleofas-Sanchez L, Perez-Meana H. A robust image zero-watermarking using convolutional neural networks. In 2019 7th International Workshop on Biometrics and Forensics, IWBF 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8739245. (2019 7th International Workshop on Biometrics and Forensics, IWBF 2019). doi: 10.1109/IWBF.2019.8739245

A robust image zero-watermarking using convolutional neural networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this