Robust watermarking technique using back propagation neural network: a security protection mechanism for social applications

摘要

In this paper, an algorithm for digital watermarking based on discrete wavelet transforms (DWTs) and singular value decomposition (SVD) has been proposed. In the embedding process, the host colour image is decomposed into third-level DWT. Low frequency band (LL3) is transformed by SVD. The watermark image is also transformed by SVD. The S vector of watermark information is embedded in the S component of the host image. Watermarked image is generated by inverse SVD on modified S vector and original U, V vectors followed by inverse DWT. Watermark is extracted using an extraction algorithm. In order to enhance the robustness performance of the image watermark, back propagation neural network (BPNN) is applied to the extracted watermark to reduce the effects of different noise applied on the watermarked image. Results are obtained by varying the gain factor and size of the cover and watermark image, experimental results are provided to illustrate that the proposed method is able to withstand a variety of signal processing attacks and has been found to be giving superior performance for robustness and imperceptibility compared to existing methods suggested by other authors.