基于SURF算法的JPEG地质资料复制-移动篡改检测

刘助龙^{1, 2}，方先知³，廖 苗²，李香花⁴，赵于前²，戴塔根^{1, 2}，贾亮亮^{1, 2}，陈 瑜²

(1. 中南大学 有色金属成矿预测教育部重点实验室，长沙 410083；
2. 中南大学 地球科学与信息物理学院, 长沙 410083;
3. 湖南省国土资源厅，长沙，410007；4. 中南大学 土木工程学院，长沙 410083)

摘 要：针对JPEG地质资料的复制-移动篡改，提出一种结合SURF特征匹配与JPEG块伪影特征矩阵因子的篡改区域检测方法。首先运用SURF算法提取图像特征点并进行特征点匹配，根据剔除伪匹配点后的匹配对计算仿射变换参数，定位复制-移动区域，然后通过引入JPEG块伪影特征矩阵因子实现篡改区域的定位。结果表明：相比其他算法，本方法能够更有效地探测JPEG地质资料的复制-移动篡改，并精确定位篡改区域。

关键词：篡改探测；复制-移动；JPEG；地质资料

Copy-move forgery detection for JPEG geological images based on SURF algorithm

LIU Zhu-long^{1, 2}, FANG Xian-zhi³, LIAO Miao², LI Xiang-hua⁴, ZHAO Yu-qian², DAI Ta-gen^{1, 2}, JIA Liang-liang^{1, 2}, CHEN Yu²

(1. Key Laboratory of Metallogenic Prediction of Nonferrous Metals, Ministry of Education,
Central South University, Changsha 410083, China;
2. School of Geosciences and Info-Physics, Central South University, Changsha 410083, China;
3. Department of Land and Resources of Hunan Province, Changsha 410007, China;
4. School of Civil Engineering, Central South University, Changsha 410083, China)

Abstract:Aiming at copy-move forgery in the JPEG geological images, a new tampered region detecting method was presented based on the speeded up robust features (SURF) matching and JPEG blocking artifact characteristics matrix (BACM) factor. Firstly, the SURF algorithm was applied to extract and match the feature points of the image, the affine transformation parameters are obtained by the matched feature points, and were used to detect the copy-move tampered regions. Then, the tampered region was located according to the JPEG BACM factor. The results show that the proposed method can detect the copy-move tampered region in JPEG geologic images more effectively, and can also locate the tampered region more precisely than the other methods, which can therefore ensure the security and accuracy of the digital geological data.

Key words:tampering detection; copy-move; JPEG; geological data