一种新的自适应盲数字水印算法

A Novel Adaptive Blind Digital Watermarking Algorithm

本文提出了一种新颖的基于DCT域的自适应育数字水印算法,该算法由三个阶段组成。首先,根据人眼视觉系统(HVS)和图像的局部特性来选择水印嵌入区域;然后充分利用 JPEG压缩量化阶段的舍入误差;第三个阶段是采用一组公式来嵌入多个版本的水印,水印是经位扩展和二值随机序列调制得到的。水印的检测不需要原始图像。实验结果表明,该算法在保证水印不可见性的同时,对常见的几种图像处理如缩放、椒盐噪声、滤波特别是JPEG压缩和剪切有很高的鲁棒性。

In this paper, an adaptive blind digital watermarking scheme is proposed. The algorithm consists of three phases. First, the embedding region of watermark is selected via the human visual system model and local characteristics of image, then the round-off errors is analysed during the quantization step of JPEG compression; at the third phase, several simple formulas are assumed to embed several watermarks that are generated by bit-spreading and binary random sequences modulation. The watermark is detected without any reference to the original image. Experimental results show that the embedded watermark is invisible; while at the same time the algorithm is robust to some typical kinds of image processing such as scaling, salt ＆ pepper noise, filtering, especially, JPEG compression and cropping attacks.