摘要
文章提出了一种基于DCT系数量化的自适应数字图像水印算法。该算法选取彩色图像作为载体图像,首先将彩色图像从RGB颜色空间转换到YIQ颜色空间,并提取其Y分量作为水印嵌入的载体,对Y分量用自组织映射(SOM)的方法进行块分类和离散余弦变换,然后将Arnold置乱后的二值水印图像量化嵌入到载体图像的DCT系数中,量化因子随块类别不同而不同,水印检测过程不需要原始图像的参与。实验证明,该算法对于常见的图像处理、JPEG压缩等具有较高的鲁棒性。
This paper represents a self-adaptive digital image watermarking algorithm based on quantizing DCT coefficients.The color image is selected as the original image.This algorithm firstly transforms the original image from RGB color space to YIQ color space and extracts component Y as the watermark carrier,then makes block classification and discrete cosine transform(DCT) of component Y by self-organizing mapping(SOM) method,at last embeds the watermarked binary image after Arnold transform into the carrier through quantizing and modifying its DCT coefficients,and the quantizing factor varies with the sorts of blocks.The watermark can be extracted without resorting the original image.Experiment results show that high robustness can be obtained under the attack of normal image processing and JPEG compression,etc.
出处
《合肥工业大学学报(自然科学版)》
CAS
CSCD
北大核心
2010年第8期1198-1201,共4页
Journal of Hefei University of Technology:Natural Science
关键词
数字水印
自组织映射
离散余弦变换
digital watermarking
self-organizing mapping
discrete cosine transform