基于图像尺度空间的几何不变特征点提取算法

图像特征点的提取是实现抗几何攻击数字水印算法的重要步骤，所提取的特征点是否鲁棒，将直接影响抗几何攻击水印的鲁棒性．Harris—Laplace角点检测方法是一种多尺度抗几何攻击角点提取方法，但计算比较复杂．将Harris．Laplace角点检测方法进行改进，把直接分析图像局部灰度值的角点提取方法与图象尺度空间的思想相结合，并兼顾多尺度的不同权值，则既可以保证角点抵抗一般几何攻击的鲁棒性，又减少计算复杂度的，根据此思路提出了加权平均Harris-Laplace角点检测方法来提取特征点．实验结果表明，该算法提取的图像特征点不仅具有很好的抵抗图像裁剪、几何缩放能力，而且计算复杂度明显低于相同重复检测率的Harris—Laplace角点检测算法．

Geometrically Invariant Feature Points Detection Based on Scale Space Theory

Feature extraction is a vital part of watermarking technology that resists geometrically attacks. The points extracted from the image will directly influence the robustness of the watermak exists in the image. This paper improves Harris-Laplace comer detector by presenting a novel method to extract geometrically invariant feature points based on the scale space theory. According to the experiments, the proposed method can select those feature points that resist several geometrically attacks such as scaling and cropping, but at the cost of lower computation.