摘要
基于数字全息和独立分量分析,提出一种新的数字盲水印算法。首先,原始水印图像经过傅里叶变换转化为数字全息图,再将宿主图像进行离散小波变换,然后将低频子带分解成互不交叠的8×8的子块,并对各子块进行离散余弦变换,选取低频系数用于全息水印的嵌入。独立分量分析用于水印的提取,该算法在不需要宿主图像、水印和攻击信息的条件下,能够正确地提取水印信号。实验结果表明,该算法能抵抗多种攻击,特别对JPEG压缩、尺度缩放等攻击具有较好的鲁棒性。
A new digital watermark technique based on digital holography and independent component analysis is presented. In this paper, the secret image is transformed into a digital hologram by the Fourier transform. When embedding, the cover image is transformed into wavelet domain. The low frequency band is divided into non-overlapping blocks. Each block is transformed into discrete cosine domain. Then the low frequency coefficients are chosen to embed watermarking. When embedding, by the means of independent component analysis, the watermark is successfully extracted without requiring any information about the original image, watermark or attack. Experimental results show that algorithm is robust against many attacks, especially in JPEG compression and resizing scale attacks.
出处
《廊坊师范学院学报（自然科学版）》
2014年第5期32-36,共5页
Journal of Langfang Normal University(Natural Science Edition)
关键词
数字全息
独立分量分析
数字水印
傅里叶变换
digital holography
independent component analysis
digital watermark
Fourier transform
