[1]段宇平,Gouenou Coatrieux,舒华忠.基于原始传感器模式噪声的CT图像来源检测算法[J].东南大学学报(自然科学版),2016,46(6):1122-1125.[doi:10.3969/j.issn.1001-0505.2016.06.002]
 Duan Yuping,Gouenou Coatrieux,Shu Huazhong.CT image origin identification algorithm based on original sensor pattern noise[J].Journal of Southeast University (Natural Science Edition),2016,46(6):1122-1125.[doi:10.3969/j.issn.1001-0505.2016.06.002]
点击复制

基于原始传感器模式噪声的CT图像来源检测算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
46
期数:
2016年第6期
页码:
1122-1125
栏目:
计算机科学与工程
出版日期:
2016-11-20

文章信息/Info

Title:
CT image origin identification algorithm based on original sensor pattern noise
作者:
段宇平12Gouenou Coatrieux2舒华忠1
1东南大学影像科学与技术实验室, 南京 210096; 2布列塔尼国立高等电信学校, 法国布雷斯特 29238
Author(s):
Duan Yuping12 Gouenou Coatrieux2 Shu Huazhong1
1Laboratory of Image Science and Technology, Southeast University, Nanjing 210096, China
2TELECOM Bretagne, Brest 29238, France
关键词:
图像来源检测 计算机断层扫描 原始传感器模式噪声 支持向量机
Keywords:
image origin identification computed tomography original sensor pattern noise support vector machine
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2016.06.002
摘要:
为了实现无先验信息情况下的CT图像来源检测,提出了一种基于CT扫描仪原始传感器模式噪声的来源检测算法.首先,采用由5种不同滤波器构建出的滤波器组,从CT图像中获取5种不同类型的传感器模式噪声;然后,对每一种噪声分别进行CT三维重建反变换,得到原始传感器模式噪声;最后,根据原始传感器模式噪声的统计特征向量,并结合支持向量机分类器进行分类,从而实现来源检测.实验结果表明,针对4个厂家的15种不同型号CT扫描仪,采用所提算法获得了较基于模式噪声的来源检测算法更高的识别精度,其平均分类精度可达94.12%.
Abstract:
To detect the origin of a computed tomography(CT)image without prior knowledge, an origin identification algorithm based on the original sensor pattern noise of the CT scanner is proposed. First, 5 different sensor pattern noises are extracted from CT images by a filterbank constituted of 5 distinct filters. Then, the original sensor pattern noises are obtained by the inverse transform of three dimensional CT reconstruction for each type of noise. Finally, the statistic feature vectors of the original sensor pattern noises and the support vector machine(SVM)based classifier are combined to tackle origin identification. The experimental results show that as for 15 different CT scanners from 4 manufacturers, the proposed origin identification algorithm obtains higher identification precision compared with other existing origin identification algorithms based on pattern noises, and the average classification accuracy can reach 94.12%.

参考文献/References:

[1] Coatrieux G, Huang H, Shu H, et al. A watermarking-based medical image integrity control system and an image moment signature for tampering characterization [J]. IEEE Journal of Biomedical and Health Informatics, 2013, 17(6): 1057-1067. DOI:10.1109/JBHI.2013.2263533.
[2] Bidgood W D, Horii S C, Prior F W, et al. Understanding and using DICOM, the data interchange standard for biomedical imaging[J]. Journal of the American Medical Informatics Association, 1997, 4(3): 199-212. DOI: 10.1136/jamia. 1997. 0040199.
[3] Ouyang J, Coatrieux G, Shu H. Robust hashing for image authentication using quaternion discrete Fourier transform and log-polar transform[J]. Digital Signal Processing, 2015, 41: 98-109. DOI:10.1016/j.dsp.2015.03.006.
[4] Warbhe A D, Dharaskar R V, Thakare V M. Computationally efficient digital image forensic method for image authentication[J]. Procedia Computer Science, 2016, 78: 464-470. DOI:10.1016/j.procs.2016.02.089.
[5] Zhou Z P, Hu C Y, Zhou C J. Mobile camera source identification based on CFA Interpolation and large components of sensor pattern noise[C]//Proceedings of the International Conference on Control, Mechatronics and Automation Technology(ICCMAT 2014). Beijing, 2015: 236-239.
[6] Swaminathan A, Wu M, Liu K J R. Nonintrusive component forensics of visual sensors using output images [J]. IEEE Transactions on Information Forensics and Security, 2007, 2(1): 91-106.
[7] Deng Z, Gijsenij A, Zhang J. Source camera identification using auto-white balance approximation [C]//IEEE International Conference on Computer Vision. Barcelona,Spain,2011: 57-64.
[8] Gerules G, Bhatia S K, Jackson D E. A survey of image processing techniques and statistics for ballistic specimens in forensic science [J]. Science & Justice, 2013, 53(2): 236-250. DOI:10.1016/j.scijus.2012.07.002.
[9] Choi K S, Lam E Y, Wong K K. Automatic source camera identification using the intrinsic lens radial distortion[J]. Opt Express, 2006, 14(24): 11551-11565. DOI:10.1364/oe.14.011551.
[10] Lukas J, Fridrich J, Goljan M. Digital Camera identification from sensor pattern noise[J]. IEEE Transactions on Information Forensics and Security, 2006, 1(2): 205-214. DOI:10.1109/tifs.2006.873602.
[11] Kharboutly A, Puech W, Subsol G, et al. CT-scanner identification based on sensor noise analysis [C]//2014 IEEE European Workshop on Visual Information Processing(EUVIP). Paris,France,2014: 1-5. DOI:10.1109/euvip.2014.7018385.
[12] Duan Y, Coatrieux G, Shu H. Identification of digital radiography image source based on digital radiography pattern noise recognition [C]//2014 IEEE International Conference on Image Processing(ICIP). Paris,France,2014: 5372-5376. DOI:10.1109/icip.2014.7026087.
[13] Seeram E. Computed tomography: Physical principles, clinical applications, and quality control [M]. New York: Elsevier Health Sciences, 2015: 232-272.
[14] Hsieh J, Nett B, Yu Z, et al. Recent advances in CT image reconstruction [J]. Current Radiology Reports, 2013, 1(1): 39-51.DOI:10.1007/s40134-012-0003-7.

备注/Memo

备注/Memo:
收稿日期: 2016-05-26.
作者简介: 段宇平(1985—),女,博士生; 舒华忠(联系人),男,博士,教授,博士生导师,shu.list@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(61073138,61201344, 61271312, 61401085, 81101104).
引用本文: 段宇平, Gouenou Coatrieux, 舒华忠.基于原始传感器模式噪声的CT图像来源检测算法[J].东南大学学报(自然科学版),2016,46(6):1122-1125. DOI:10.3969/j.issn.1001-0505.2016.06.002.
更新日期/Last Update: 2016-11-20