期刊名称：International Journal of Security and Its Applications
印刷版ISSN：1738-9976
出版年度：2016
卷号：10
期号：6
页码：171-180
DOI：10.14257/ijsia.2016.10.6.17
出版社：SERSC
摘要：How to improve the effect of digital watermark has been the main direction of research. This paper first proposes a network adaptive sparse transformation method based on dictionary learning. In this method, the adaptive optimal sparse transform is constructed, and the sparse matrix of the network data is introduced into the dictionary learning problem to satisfy the requirement of the data processing of the watermark image and the high real time requirement of the sparse transform. Through the improvement of the watermark embedding and extraction, the compression perception algorithm has achieved good results in robustness and concealment. The simulation results show that the algorithm has good feasibility.
关键词：compression perception; digital watermark; dictionary learning
