摘要
提出了一种小波域图像水印方法,该方法利用神经网络实现水印的盲提取。水印序列被嵌入到YUV彩色空间中Y分量的低频系数中,其中包括一段模板信息,这段模板信息定义了对低频部分进行3×3分块后块内低频系数之间的一种关系,然后利用模板信息训练神经网络,实现水印的盲提取。
A watermarking method for images in wavelet domain is proposed in this paper, which realizes the watermarking blind extraction by using neural network technology. Watermark sequence is imbedded in the low-sequence of Y component in YUV color space, including a section of template information. The template information defines a kind of relation among the low-frequency coefficients in the block after divided into 3 × 3 in the low-frequency portion. The neural network is trained to realize the watermarking blind extraction through utilizing template information.
出处
《西华大学学报(自然科学版)》
CAS
2010年第2期131-134,186,共5页
Journal of Xihua University:Natural Science Edition
基金
四川省学术和技术带头人培养基金资助(08209057)
关键词
神经网络
图像水印
离散小波变换
彩色图像
neural network
image watermarking
discrete wavelet transform
color image