A New Watermarking Algorithm based on Slowly Feature Analysis
Qi Xia, Jianbin Gao, Chunxiang Xu · 2008
Recently, Blind Source Separate (BSS) technique has been extended to digital watermarking field. Slowly Feature Analysis (SFA)-a kind of BSS technique-is a new unsupervised learning algorithm to learn nonlinear functions that extract slowly varying signals out of the input data. It expediently can be used to extract image feature and separate the mixed signals. Making use of the advantages of SFA, in this paper, we propose a watermarking scheme based on SFA. In the experiments, we compare our scheme with other watermarking algorithm which has been used to digital watermarking field especially wavelets. Results indicate that our scheme has not only better invisibility and good robustness to different kinds of attacks but also ease the conflicts between them.