Adaptive digital watermarking using neural network technique

Der Chyuan Lou; Jiang Lung Liu; Ming Chiang Hu

Adaptive digital watermarking using neural network technique

Der Chyuan Lou^*, Jiang Lung Liu, Ming Chiang Hu

^*Corresponding author for this work

National Defense University Taiwan

Research output: Contribution to conference › Conference Paper › peer-review

27 Scopus citations

Abstract

In this paper, a novel image watermarking approach based on the human visual system (HVS) model and neural network technique is proposed. The human visual system model is utilized to generate the suitable strength of embedded watermark and can be described in terms of four properties of HVS model: entropy, frequency, luminance, and texture sensitivity. The neural network technique has been employed to obtain the local characteristics of image. In our experiments for each different image the watermark can be adjusted to provide a maximum and suitable strength subject to the imperceptibility constraint.

Original language	English
Pages	325-332
Number of pages	8
State	Published - 2003
Externally published	Yes
Event	Proceedings: 37th Annual 2003 International Carnahan Conference on Security Technology - Taipei, Taiwan Duration: 14 10 2003 → 16 10 2003

Conference

Conference	Proceedings: 37th Annual 2003 International Carnahan Conference on Security Technology
Country/Territory	Taiwan
City	Taipei
Period	14/10/03 → 16/10/03

Keywords

Digital watermarking
Discrete cosine transform
Human visual system
Neural network
Spread-spectrum communications

Cite this

@conference{340f5489c0e7493b9060cb7e77baf7ad,

title = "Adaptive digital watermarking using neural network technique",

abstract = "In this paper, a novel image watermarking approach based on the human visual system (HVS) model and neural network technique is proposed. The human visual system model is utilized to generate the suitable strength of embedded watermark and can be described in terms of four properties of HVS model: entropy, frequency, luminance, and texture sensitivity. The neural network technique has been employed to obtain the local characteristics of image. In our experiments for each different image the watermark can be adjusted to provide a maximum and suitable strength subject to the imperceptibility constraint.",

keywords = "Digital watermarking, Discrete cosine transform, Human visual system, Neural network, Spread-spectrum communications",

author = "Lou, \{Der Chyuan\} and Liu, \{Jiang Lung\} and Hu, \{Ming Chiang\}",

year = "2003",

language = "英语",

pages = "325--332",

note = "Proceedings: 37th Annual 2003 International Carnahan Conference on Security Technology ; Conference date: 14-10-2003 Through 16-10-2003",

}

TY - CONF

T1 - Adaptive digital watermarking using neural network technique

AU - Lou, Der Chyuan

AU - Liu, Jiang Lung

AU - Hu, Ming Chiang

PY - 2003

Y1 - 2003

N2 - In this paper, a novel image watermarking approach based on the human visual system (HVS) model and neural network technique is proposed. The human visual system model is utilized to generate the suitable strength of embedded watermark and can be described in terms of four properties of HVS model: entropy, frequency, luminance, and texture sensitivity. The neural network technique has been employed to obtain the local characteristics of image. In our experiments for each different image the watermark can be adjusted to provide a maximum and suitable strength subject to the imperceptibility constraint.

AB - In this paper, a novel image watermarking approach based on the human visual system (HVS) model and neural network technique is proposed. The human visual system model is utilized to generate the suitable strength of embedded watermark and can be described in terms of four properties of HVS model: entropy, frequency, luminance, and texture sensitivity. The neural network technique has been employed to obtain the local characteristics of image. In our experiments for each different image the watermark can be adjusted to provide a maximum and suitable strength subject to the imperceptibility constraint.

KW - Digital watermarking

KW - Discrete cosine transform

KW - Human visual system

KW - Neural network

KW - Spread-spectrum communications

UR - https://www.scopus.com/pages/publications/2342657971

M3 - 论文

AN - SCOPUS:2342657971

SP - 325

EP - 332

T2 - Proceedings: 37th Annual 2003 International Carnahan Conference on Security Technology

Y2 - 14 October 2003 through 16 October 2003

ER -

Adaptive digital watermarking using neural network technique

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this