基于SIFT和HSI模型的彩色图像复制-粘贴盲鉴别算法  

Coloured image copy-move forgery detection based on SIFT and HSI

作　　者：申铉京[1,2] 朱叶[1,2] 吕颖达[1,2] 陈海鹏[1,2] 

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]吉林大学符号计算与知识工程教育部重点实验室,长春130012

出　　处：《吉林大学学报（工学版）》2014年第1期171-176,共6页Journal of Jilin University:Engineering and Technology Edition

基　　金：吉林省自然科学基金项目(201115025);符号计算与知识工程教育部重点实验室开放基金项目(450060445325)

摘　　要：针对彩色图像复制-粘贴篡改中误匹配的问题,提出一种基于SIFT和HSI模型的彩色图像复制-粘贴盲鉴别算法。首先确定彩色图像的SIFT特征点和特征向量;然后对每个SIFT特征点提取HSI彩色特征;最后对两两不同特征点的SIFT特征向量和HSI特征向量进行匹配,确定图像的复制-粘贴篡改区域。实验结果表明:本文算法与SIFT算法、SURF算法和改进SIFT算法相比,能有效地降低误匹配率,并对高斯模糊、白噪声和JPEG重压缩有较强的鲁棒性。In order to solve the problem of the false matching in detecting copy-move forgeries, an improved method based on Scale Invariant Feature Transform （SIFT） and HSI was proposed in this study. First, the SIFT key points and SIFT feature vector are extracted. Secondly, for each SIFT point the HSI feature is extract. Finally, the SIFT feature vector and the HSI feature vector between every two different key points are matched to determine the copy-move regions. The experimental results show that the proposed algorithm based on SIFT and HSI can reduce false matching rate in comparison with the SIFT algorithm, the SURF algorithm and the improved SIFT algorithm. The proposed algorithm has higher robustness even when an image is distorted by Gaussian blur, white noise and JPEG recompression.

关 键 词：计算机应用 盲鉴别 图像复制一粘贴篡改 SIFT特征向量 HSI彩色空间 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]