Self-synchronization Blind Audio Watermarking Based on Feature Extraction and Subsampling

Authors:
Xiaohong Ma;Bo Zhang;Xiaoyan Ding
Affiliations:
School of Electronic and Information Engineering, Dalian University of Technology, Dalian 116023, China;School of Electronic and Information Engineering, Dalian University of Technology, Dalian 116023, China;School of Electronic and Information Engineering, Dalian University of Technology, Dalian 116023, China
Venue:
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
Year:
2007

Citing 4
Cited 4

A fast fixed-point algorithm for independent component analysis

Neural Computation
Blind Audio Watermark Decoding Using Independent Component Analysis

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
DCT-based image watermarking using subsampling

IEEE Transactions on Multimedia
Localized audio watermarking technique robust against time-scale modification

IEEE Transactions on Multimedia

Watermark Image Restoration Method Based on Block Hopfield Network

ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part III
A robust digital audio watermarking scheme using wavelet moment invariance

Journal of Systems and Software
A pseudo-Zernike moment based audio watermarking scheme robust against desynchronization attacks

Computers and Electrical Engineering
Digital audio watermarking technique using pseudo-zernike moments

ICICS'09 Proceedings of the 11th international conference on Information and Communications Security

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel embedding watermark signal generation scheme based on feature extraction is proposed in this paper. The original binary watermark image is divided into two blocks with the same size and each block is changed into one dimension sequences. After that, Independent Component Analysis (ICA) is used to extract the independent features of them, which are regarded as two embedding watermark signals. In the embedding procedure, the embedding watermark signals are embedded in some selected wavelet coefficients of the subaudios obtained by subsampling. And Self-synchronization is implemented by applying special peak point extraction scheme. The blind extraction procedure is basically the converse procedure of the embedding one. And the original watermark image can be recovered with the help of the mixing matrix of the ICA. Experimental results show the validity of this scheme.