Thefirst series of algorithms are aiming at finding some physical values on the discretewavelet transformation domain acting as “invariant watermark”, which should berather stable under common audio signal processing and synchronization attacks.
第一系列算法基于恒定水印的思想,在离散小波域寻找在各种音频信号处理和同步攻击下都能保持基本稳定的物理量用于水印的嵌入和检测。
参考来源 - 鲁棒性数字音频水印算法研究·2,447,543篇论文数据，部分数据来源于NoteExpress
The image watermark scheme based on Scale Invariant feature Transform (SIFT) feature is proposed for resisting geometric attacks.
提出一种利用尺度不变特征变换(SIFT)特征点实现对抗几何攻击的水印方案。
A video object watermark algorithm using Scale-Invariant feature Transform (SIFT) features and video segmentation based on spatiotemporal information is proposed.
提出一种结合尺度不变特征变换(SIFT)特征点校正和时空域视频对象分割的视频对象水印算法。
The main methods adopted include:1) watermark synchronization is achieved by invariant local circular regions which can be generated using image locally most stable feature points;
采取的主要方法有：1）利用图像中的局部最稳定特征点生成具有几何不变性的圆形特征区域，用于水印的同步；
应用推荐