基于小波域和块分类的鲁棒自适应水印算法

A robust image-adaptive public watermarking algorithm based on DWT and blocks classification

一种基于小波域和图像块分类的鲁棒的自适应水印算法,能更加有效地利用人眼的视觉掩蔽特性,增强水印的安全性和鲁棒性。算法首先将8×8分块后的图像块根据亮度区别和纹理特征进行分类,计算出各块的JND阈值。把分块后的原图像按Hilbert扫描顺序排列,在序列中选取两相邻块,然后结合各分块JND阈值,通过不同强度的调整两相邻块各对应中高频子带均值之间的大小关系自适应的嵌入水印。同时,根据水印信号改变低频系数的值以嵌入水印信号。实验结果证明:该算法可以存储较大量的水印信息,而且对常见图像处理操作、有损压缩、裁剪、挤压、像素移位等几何变换有较高的鲁棒性,且有较高的透明性。

In making the most of the hiding features of human visual system （HVS） and increasing the security and robust of watermarking, a robust image-adaptive public watermarking algorithm based on discrete wavelet domain （DWT） and blocks of image is proposed. First, blocks of the original image are classified according to their luminance and texture features and the JND value of each block is calculated according to its feature. At the same time, the 8 × 8 blocks of the original image are rearranged into a 1-D Hilbert scanning order. Then, two neighboring blocks are selected from the Hilbert sequence of the host image blocks in turn. According to the JND value of the blocks, a binary watermark with visually recognizable patterns is embedded into the host image by modifying the polarity of the average value of the two corresponding sub-bands. Finally, a corresponding detail sub-band is chosen from three detail sub-bands of the two neighboring blocks at a time respectively. The lowest coefficiency is changed by the use of the watermark. The embedded watermark is invisible. The experimental results show that the proposed algorithm is effective and robust to common image processing operations and some geometric distortions such as cropping, pinching, pixel-shift, and so on.