结合Harris角点检测和不变质心的稳健图像Hash算法  

Robust image Hash algorithm based on Harris corners and invariant centroid

作　　者：崔得龙[1] 左敬龙[1] 彭志平[1] 

机构地区：[1]茂名学院计算机与电子信息学院,广东茂名525000

出　　处：《传感器与微系统》2011年第5期30-33,共4页Transducer and Microsystem Technologies

基　　金：广东省自然科学基金资助项目(8152500002000003);茂名市重点科技计划资助项目(203624)

摘　　要：提出了应用Harris角点检测和不变质心的图像Hash算法。算法从仿射变换的数学模型出发,利用仿射前后图像质心位置的不变特性,计算Harris角点与不变质心的欧氏距离作为特征向量,最后经编码量化产生图像Hash。实验结果表明:本算法对视觉可接受的JPEG压缩、滤波等具有良好的鲁棒性,而恶意扰动或篡改则会改变Hash值。密钥的使用保证了Hash的安全性。A novel image Hash algorithm using Harris corners and invariant centroid is proposed.Originating from the mathematical model of affine transform,the distances between Harris corners and invariant centroid are calculated as feature vector,which based on the invariance of centroid of images in the affine transform,finally the feature vectors are compressed to generate the image Hash.Experimental results show that the proposed scheme is robust against perceptually acceptable modifications to the image such as JPEG compression,filtering,while sensitive to excessive changes and malicious tampering.Security of the Hash is guaranteed by using secret keys.

关 键 词：图像HASH HARRIS角点 不变质心 归一化Hamming距离 密钥 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]