An adaptive digital image watermarking based on image features in discrete wavelet transform domain and general regression neural network

الملخص EN

In this paper, a new intelligent, robust and adaptive digital watermarking technique for gray image based on combination of discrete wavelet transform (DWT), human visual system (HVS) model and general regression neural network (GRNN) is proposed.

Wavelet coefficients are analyzed by a HVS model to select suitable coefficients for embedding the watermark.

The watermark bits are extracted from the watermarked image by training a GRNN.

Some statistical characteristics of wavelet coefficients are used in extracting process for better performance and accuracy of watermarking algorithm.

The implementation results show that the watermarking algorithm has very good robustness to all kind of attacks.