基于DWT和PNN的数字图像水印算法

Digital Image Watermarking Algorithm Based on DWT and PNN

针对数字信息在存储或传输过程中可能受到复制、攻击或修改的问题,提出一种基于DWT和PNN的数字图像水印算法.该算法在基于块的小波系数中选择最佳位置嵌入水印图像,采用PNN记录水印与对应图像之间的关系,在不需要原始图像和水印图像的情况下,从嵌入水印的图像中恢复水印.使用PSNR和NCC对算法进行不可见性和鲁棒性测试.实验结果表明,本文算法提取的水印图像具有优秀的不可见性和鲁棒性,能够有效应对不同类型的攻击.

For the problems of the digital information in the process of storage or transmission may be copied,attacked or modified,a digital image watermarking algorithm based on Discrete Wavelet Transform（DWT）and Probabilistic Neural Network（PNN）is proposed.This algorithm screens the best position to embed the watermark image based on blocks of Wavelet Coefficients,and records the relationship between the watermark and the corresponding image by PNN so as to recover the watermark from the embedded watermark without the need of original image and watermark image.PSNR and NCC are used to verify the imperceptibility and robustness of the algorithm.Experimental results show that the proposed algorithm has excellent invisibility and robustness,and can effectively deal with the existing different kinds of attacks.