Wavelet Digital Watermarking with Unsupervised Learning  

作　　者：SHEKun HUANGJuncai ZHOUMingtian 

机构地区：[1]CollegeofScienceandTechnology,ElectronicScienceandTechnologyUniversityofChina,Chengdu610054,China

出　　处：《Chinese Journal of Electronics》2005年第1期10-14,共5页电子学报（英文版）

摘　　要：In this paper a novel technique for the digital watermarking of still color images based on the concept of color space transform, wavelet fusion and image denoising is presented. Our algorithm transforms R, G, B colorspace to R′, G′, B′ color space firstly, which constructs three grey images, then computes the 2nd-level discretewavelet decomposition of the three grey images. Embedding watermark fuses a grey image (watermark) with each of the three images' wavelet coefficients, then transforms R′, G′, B′ color space to R, G, B color space to obtain thewatermarked color image. When extracting watermark, at first two grey images X1, X2 from the two of three wavelet coefficients is distilled, then Independent component analyses (ICA) is used to denoise and get grey image (watermark) W. The results of our test show the superior performance of the technique and the great potential of the watermarking of photographic imagery.

关 键 词：数字水印 色隙变换 ICA 图像噪声 小波变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]