A perceptual hashing method based on luminance features

摘要

With the rapid development of multimedia technology, content based searching and image authentication has become strong requirements. Image hashing technique has been proposed to meet them. In this paper, an RST (Rotation, Scaling, and Translation) resistant image hash algorithm is presented. In this method, the geometric distortions are extracted and adjusted by normalization. The features of the image are generated from the high-rank moments of luminance distribution. With the help of the efficient image representation capability of high-rank moments, the robustness and discrimination of proposed method are improved. The experimental results show that the proposed method is better than some existing methods in robustness under rotation attack.