基于DCT域的增益不变量化的数字图像水印算法

Novel gain invariant quantization-based watermarking algorithm based on DCT domain

提出一种新的基于离散余弦变换(discrete cosine transform,DCT)域的增益不变量化索引调制的数字图像水印算法。该算法根据DCT域中DC分量的稳健性,将水印信息采用增益不变的量化嵌入DC分量中,并通过最小距离公式进行水印提取。水印被量化嵌入,提取水印信息无需原载体图像,算法能对水印信息盲提取。实验结果表明,与其他数字水印算法相比,算法有较好的透明性,并对JPEG图像压缩、高斯噪声、中值滤波、泊松噪声、椒盐噪声、缩放等常见图像攻击有很强的鲁棒性。

This paper presents a novel quantization - based watermarking algorithm based on DCT domain, which is invari- ant to gain attack. According to the robustness of DC component in DCT domain, watermark information is embedded in DC component by using gain invariant watermarking scheme based on quantization. The watermark code is extracted by using the minimum Euclidean distance. Because of quantization embedding strategies, watermarking extraction does not need the original host image, which is a blind watermarking algorithm. Experimental results verify the superiority of the proposed technique against common attacks in comparison with other algorithms, and it has a strong robustness to effectively resist the JPEG compression, Gaussian noise, median filter, Poisson noise, salt and pepper noise, image scaling attack.