Color image watermarking algorithm using BPN neural networks

Authors:
Cheng-Ri Piao;Sehyeong Cho;Seung-Soo Han
Affiliations:
Department of Information Engineering & NPT Center, Myongji University, Yongin, Kyunggi, South Korea;Department of Computer Software Engineering, Myongji University, Yongin, Kyunggi, South Korea;Department of Information Engineering & NPT Center, Myongji University, Yongin, Kyunggi, South Korea
Venue:
ICONIP'06 Proceedings of the 13th international conference on Neural information processing - Volume Part III
Year:
2006

Citing 4
Cited 0

Blind Watermarking Algorithm Using Complex Block Selection Method

PCM '01 Proceedings of the Second IEEE Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Quantization index modulation: a class of provably good methods for digital watermarking and information embedding

IEEE Transactions on Information Theory
A new, fast, and efficient image codec based on set partitioning in hierarchical trees

IEEE Transactions on Circuits and Systems for Video Technology
Multichannel watermarking of color images

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new watermarking scheme in which a logo watermark is embedded into the discrete wavelet transform (DWT) domain of the color image using Back-Propagation Neural networks (BPN). In order to strengthen the imperceptibility and robustness, the original image is transformed from RGB color space to brightness and chroma space (YCrCb). After transformation, the watermark is embedded into DWT coefficient of chroma component, CrCb. A secret key determines the locations in the image where the watermark is embedded. This process prevents possible pirates from removing the watermark easily. BPN will learn the characteristics of the color image, and then watermark is embedded and extracted by using the trained neural network. Experimental results show that the proposed method has good imperceptibility and high robustness to common image processing attacks.