摘要
针对单一基于相关性的图像篡改检测算法难以同时解决虚警和漏检的缺陷,提出一种具有双重检测机制的图像篡改检测算法——第一重检测利用待测图像各区域的相机指纹是否与参考相机的指纹具有相关性来确定疑似篡改图像块;第二重检测从疑似篡改图像块中抽取特征,送到训练好的支持向量机(SVM),由基于图像特征的SVM对其分类,把误判块和真实篡改块区分开来.实验结果表明,该算法优于经典的单一基于相机指纹相关性的篡改检测算法.
As the classical correlation-based image tampering detection algorithms cannot avoid false alarm and mis- detection, a novel algorithm based on double detection mechanisms is proposed. In this algorithm, first, tampered image blocks under suspicion are picked out according to the correlation between the camera fingerprint in each re- gion of the detected image and that for reference. Then, image features are extracted from each suspicious image block and are sent to a trained SVM （Support Vector Machine） to construct an image features-based SVM classifier for distinguishing the mis-deteeted blocks from the real tampered ones. Experimental results demonstrate that the proposed method outperforms the classical one only based on the correlation of camera fingerprints.
出处
《华南理工大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2012年第4期16-22,共7页
Journal of South China University of Technology(Natural Science Edition)
基金
华南理工大学中央高校基本科研业务费专项资金资助项目(2012ZM0027)
关键词
相机指纹
相关性检测
模式分类
篡改检测
双重检测机制
camera fingerprint
correlation detection
pattern classification
tampering detection
double detection mechanism
