基于离散曲波变换的图像Hash算法  

Image Hash based on discrete curvelet transform

作　　者：徐文娟[1] 易波[1] 

机构地区：[1]湖南大学计算机与通信学院,长沙410082

出　　处：《中国图象图形学报》2011年第8期1374-1378,共5页Journal of Image and Graphics

摘　　要：为了提高图像Hash算法的鲁棒性,提出一种新的基于离散曲波变换的图像Hash算法。该算法首先对图像预处理,再进行基于"打包"的快速离散曲波变换,提取出包含图像主要特征的曲波低频系数和边缘信息较丰富的细节2层系数作为特征向量;然后用Logistic方程对特征向量加密;最后进行量化压缩得到图像Hash序列。实验结果表明,该算法与已有传统算法相比,具有更高的鲁棒性;能有效区分不同图像,具有易碎性;混沌系统的引入使算法具有安全性。In order to improve the robustness of image Hash algorithm a new image Hash algorithm based on discrete curvelet transform is proposed. The image is firstly preprocessed, and then decomposed with discrete curvelet transform via wrapping. The curvelet coefficients of low frequency contained the main features of image and the coefficient of details of two layer contained rich edge information are as the feature vectors. And Logistic equation is used to encrypt the eigenvector. Finally, the image Hash sequence is obtained by quantization and compression. Experimental results show that the algorithm has better robustness compared to some other Hash method. It is fragility to different images. The chaos system enhances the security.

关 键 词：图像HASH 曲波变换 图像认证 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]