隨著日常生活周遭的監視攝影機數量不斷地攀增，其拍攝內容經常為法庭上或警方辦案時重要的證據之一。因此該如何確認其攝影內容的完整性與真實性是一件越來越重要的議題。本論文提出一個被動式數位影片鑑識系統，此系統不需要依賴任何預先嵌入的資訊來驗證數位影片之真實性，亦不需要由使用者手動選取檢測區域。將受測影片的每張影格取出對於拼接竄改操作較為敏感之特徵向量，該特徵向量是由四個部分所組成，其包含畫面品質特徵、矩特徵、局部頻率特徵，以及馬可夫特徵。分別從多個面向以及不同層面之統計特徵，凸顯出影格畫面經過拼接竄改後所造成之影響。將所取出之特徵向量經由支援向量機歸類，可以得到包含每張影格所屬類別之類別向量。將類別向量加以修正後，取出被歸類為拼接竄改類別之影格並建立其索引表，接著再利用被歸類為真實類別之影格來取出參考樣板雜訊。最後將這些竄改影格使用樣板雜訊之區塊相關性來定位出影格中被竄改的區域。由實驗結果可以顯示出本系統對於一般拍攝環境下之拼接竄改影片具有不錯的檢測效果。

In this research, a passive spliced forgery detection system for digital videos is proposed. The proposed system consists of four parts. The first one is feature vector extraction which generates the features of the frame. The feature vector contains the frame quality features, the moment features, the local frequency features, and the Markov features. The second one is to determine if the processed frame belongs to a suspected frame. After finish the second part, each frame is classified as a normal or suspected frame. The third part is firstly to take an advanced evaluation for these detected suspected frames to determine if the suspicion is not necessary. It is based on the concept that for a tampered video it is not usual to modify one frame only during a sequence of frames. Then the sensor noise pattern is evaluated by averaging the noise of these normal frames. The sensor noise pattern is used to determine the tampered region for these tampered frames. The proposed method was firstly evaluated using the Columbia Image Splicing Detection Evaluation Dataset created by Columbia DVMM Research Lab. It is shown that the detection rate is 92.18%. For video application, seven videos were captured via SONY HANDYCAM HDR-SR5E under four different lighting conditions. Two types of tampered method which include cut-paste and hiding the objects are applied. Experimental results show that the detection rates are above 85%, which results for type of cut-paste are even greater than 90%.

[1] Photo Tampering Throughout History, http://www.cs.dartmouth.edu/farid/research/ digitaltampering
[2] Wei-Che Chen, and Ming-Shi Wang, “A fuzzy c-means clustering-based fragile watermarking scheme for image authentication,” Expert System with Application, vol.36, pp.1300-1307, 2009.
[3] Ming-Shi Wang, and Wei-Che Chen, “A majority-voting based watermarking scheme for color image tamper detection and recovery,” Computer Standards and Interfaces, vol.29, pp.561-570, 2007.
[4] Eugene T. Lin, Christine I. Podilchuk, and Edward J. Delp, "Detection of image alterations using semi-fragile watermarks," Proceedings of SPIE, security and watermarking of multimedia contents II, San Jose, CA, USA, vol.3971, pp.152-163, 23-28 Jan. 2000.
[5] Ibrahim Nasir, Ying Weng, and Jianmin Jiang, "A New Robust Watermarking Scheme for Color Image in Spatial Domain," Proceedings of the 2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System, Jiangong Jinjiang, Shanghai, China, pp.942- 947, 16-19 Dec. 2007.
[6] Marc Schneider, and Shi-Fu Chang, “A robust content based digital signature for image authentication,” Proceedings of the IEEE International Conference on Image Processing, Lausanne, Switzerland, vol.3, pp.227-230, 01 Sep. 1996.
[7] Chun-Shien Lu, and Hong-Yong Mark Liao, “Structural digital signature for image authentication: an incidental distortion resistant scheme,” IEEE Transactions on Multimedia, vol.5, pp.161-173, 2000.
[8] Tian-Tsong Ng, Shih-Fu Chang, Ching-Yung Lin, and Qibin Sun, “Passive-Blind Image Forensics,” Multimedia Security Technologies for Digital Rights, Elsvier, 2006.
[9] Hany Farid, “A Survey of Image Forgery Detection,” IEEE Signal Processing Magazine, vol.26 no.2, pp.16-25, 2009.
[10] Jessica Fridrich, David Soukal, and Jan Lukáš, “Detection of copy-move forgery in digital images,” in Proc. Digital Forensic Research Workshop, Cleveland, OH, USA, 5-8 Aug. 2003.
[11] Alin Constantin Popescu, and Hany Farid, “Exposing digital forgeries by detecting duplicated image regions,” Technical Report, TR2004-515, Dartmouth College, Computer Science, 2004.
[12] Babak Mahdian and Stanislav Saic, "Detection of copy–move forgery using a method based on blur moment invariants," Forensic Science International, vol.171, issues 2-3, pp.180-189, 13 Sep. 2007.
[13] Weihong Wang, and Hany Farid, "Exposing digital forgeries in video by detecting duplication," International Multimedia Conference Proceedings of the 9th workshop on Multimedia & security, Dallas, Texas, pp.35-42, 2007.
[14] Alin Constantin Popescu, and Hany Farid, “Exposing digital forgeries by detecting traces of resampling,” IEEE Transactions on Signal Processing, vol.53, no.2, pp.758-767, 2005.
[15] Tian-Tsong Ng, and Shih-Fu Chang, “A model for image splicing,” IEEE International Conference on Image Processing, Singapore, vol.2, pp.1169-1172, 24-27 Oct. 2004.
[16] Tian-Tsong Ng, and Shih-Fu Chang, “Blind Detection of Digital Photomontage Using Higher Order Statistics,” ADVENT Technical Report #201-2004-1, Columbia University, 8 Jun. 2004.
[17] İsmail Avcıbaş, Sevinç Bayram, Nasir Memon, Bülent Sankur, and Mahalingam Ramkumar, “A classifier design for detecting image manipulation,” IEEE International Conference on Image Processing, Singapore, pp.2645-2648, 24-27 Oct. 2004.
[18] Sevinç Bayram, Ismail Avcibas, Bülent Sankur, and Nasir Memon, “Image manipulation detection,” Journal of Electronic Imaging, vol.15, issue4, 41102, Oct-Dec. 2006.
[19] Wen Chen, Yun-Qing. Shi, and Wei Su, “Image Splicing Detection using 2-D Phase Congruency and Statistical Moments of Characteristic Function,” In: SPIE Electronic Imaging: Security, Steganography, and Watermarking of Multimedia Contents, San Jose, CA, USA , 29 Jan. 2007.
[20] Yun-Qing. Shi, Chunhua Chen, and Wen Chen, “A Natural Image Model Approach to Splicing Detection,” International Multimedia Conference Proceedings of the 9th workshop on Multimedia & security, Dallas, Texas, USA, pp.20-21, 20-21 Sep. 2007.
[21] Dongdong Fu, Yun-Qing. Shi, and Wei Su, “A generalized Benford’s law for JPEG coefficients and its applications in image forensics”, In: Proc. SPIE, Security, Steganography and Watermarking of Multimedia Contents IX, San Jose, CA, USA, 29 Jan. 2007.
[22] Frank Benford, "The law of anomalous numbers," Proceedings of the American Philosophical Society, vol.78, no.4, pp.551-572, 31 Mar. 1938.
[23] Alin Constantin Popescu and Hany Farid, “Statistical tools for digital forensics,” in Proc. 6th International Workshop on Information Hiding, Toronto, Canada, pp.128-147, 23-25 May. 2004.
[24] Zhouchen Lin, Junfeng He, Xiaoou Tang, and Chi-Keung Tang, "Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis," Pattern Recognition, vol.42, issue 11, pp.2492-2501, Nov. 2009.
[25] Weihong Wang, and Hany Farid, “Exposing digital forgeries in video by detecting double MPEG compression,” International Multimedia Conference Proceedings of the 8th workshop on Multimedia and security, Geneva, Switzerland, pp.37-47, 26-27 Sep. 2006.
[26] Weihong Wang, and Hany Farid, "Exposing Digital Forgeries in Video by Detecting Double Quantization," ACM Multimedia and Security Workshop, Princeton, NJ, 7 May. 2009.
[27] Micah Kimo Johnson, and Hany Farid, “Exposing digital forgeries through chromatic aberration,” In: Proceedings of the 8th workshop on Multimedia and security, Geneva, Switzerland, pp.48-55, 26-27 Sep. 2006.
[28] Alin Constantin Popescu and Hany Farid, “Exposing digital forgeries in color filter array interpolated images,” IEEE Transactions on Signal Processing, vol.53, no.10, pp.3948-3959. 2005.
[29] Yangjing Long, and Yizhen Huang, “Image based source camera identification using demosaicking,” in IEEE International Workshop on Multimedia Signal Processing, vol.3, pp.419-424, 01 Dec. 2006.
[30] Y.-F. Hsu and S.-F. Chang, “Detecting Image Splicing Using Geometry Invariants and Camera Characteristics Consistency,” in IEEE International Conference on Multimedia and Expo, Toronto, Ontario, Canada, pp.549-552, 9-12 Jul. 2006.
[31] Mo Chen, Jessica Fridrich, and Jan Lukáš, “Determining image origin and integrity using sensor pattern noise,” IEEE Transactions. Information Forensics Security, vol.3, no.1, pp.74-90. 2008.
[32] Jessica Fridrich, “Digital Image Forensics Using Sensor Noise,” Signal Processing Magazine, Special Issue on Digital Forensics, vol. 26, no.2, pp.26-37, Mar. 2009.
[33] Chih-Chung Hsu, Tzu-Yi Hung, Chia-Wen Lin, and Chiou-Ting Hsu, “Video forgery detection using correlation of noise residue,” In IEEE International Workshop on Multimedia Signal Processing, Cairns, Australia, pp.170-174, 8-10 Oct. 2008.
[34] Michihiro Kobayashi, Takahiro Okabe, and Yoichi Sato, “Detecting video forgeries based on noise characteristics,” In Proceedings of the 3rd Pacific-Rim Symposium on Image and Video Technology, Tokyo, Japan, vol.5414, 13-16 Jan. 2009.
[35] Micah Kimo Johnson, and Hany Farid, “Exposing digital forgeries by detecting inconsistencies in lighting,” In: Proceedings of the 7th Workshop on Multimedia and Security, New York, NY, USA, pp.1-10, 1-2 Aug. 2005.
[36] Micah Kimo Johnson, and Hany Farid, “Exposing digital forgeries through specular highlights on the eye,” In: Proceedings of the 9th International Workshop on Information Hiding, Saint Malo, France, pp.311-325, 11-13 Jan. 2007.
[37] Haralick, R.M., “Statistical and structural Approaches to Texture,” Proceedings of the IEEE, vol. 67, no.5, pp.786-804, 1979.
[38] M. Concetta Morrone, John Ross, David C. Burr, and Robyn Owens, “Mach bands are phase dependent,” Nature, vol.324, issue.6094, pp.250-253, Nov. 1986.
[39] Svetha Venkatesh and R.A. Owens, "An energy feature detection scheme," In The IEEE International Conference on Image Processing, Singapore, pp.553-557, 18-20 Jul. 1989.
[40] Peter Kovesi, “Image features from phase congruency”, Journal of Computer Vision Research, vol.1, no.3, pp.1-26, 1999.
[41] Jean B. Lasserre, “Average Optimal Stationary Policies and linear Programming in countable Space Markov Decision Process,” IEEE Conference on Decision and Control, Tucson, Artzous, pp.3325-3327, 16-18 Dec. 1992.
[42] Martin L. Puterman, "Markov decision processes: discrete stochastic dynamic programming," John Wiley and Sons, Inc, New York, NY, USA, 1994.
[43] Vladimir N. Vapnik, "The Nature of Statistical Learning Theory," Springer, 1995.
[44] Dan Klein, "Lagrange Multipliers without Permanent," Berkeley, 2004.
[45] R.Fletcher, "Practical methods of optimization," 2nd edition, Wiley, 1987.
[46] Corinna Cortes and Vladimir Vapnik, "Support-vector networks," Machine Learning, vol.20, pp.273-297, 1995.
[47] Bernhard E. Boser , Isabelle M. Guyon , and Vladimir N. Vapnik, "A training algorithm for optimal margin classifiers," in Proceedings of the Fifth Annual Workshop on Computational Learning Theory, Pittsburgh, Pennsylvania, United States, pp.144-152, 27-29 Jul. 1992.
[48] Marcelo J. Weinberger, Gadiel Seroussi, and Guillermo Sapiro, “LOCO-I: A low complexity, context-based, lossless image compression algorithm,” in Procedings of IEEE Data Compression Conference, pp.140-149, 31 Mar.-03 Apr. 1996.
[49] M. K. Mihcak, I. Kozintsev, and K. Ramchandran, “Spatially adaptive statistical modeling of wavelet image coefficients and its application to denoising,” in Proc. IEEE International Conference, Acoustics, Speech, and Signal Processing, vol.6, pp.3253-3256, 15-19 Mar. 1999.
[50] Chih-Chung Chang, and Chih-Jen Lin, LIBSVM: a library for support vector machines, 2001. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
[51] Columbia DVMM Research Lab. Columbia Image Splicing Detection Evaluation Dataset, http://www.ctr.columbia.edu/dvmm/downloads/AuthSplicedDataSet/AuthSp licedDataSet.htm
[52] Columbia DVMM Research Lab. Columbia Uncompressed Image Splicing Detection Evaluation Dataset,http://www.ee.columbia.edu/ln/dvmm/downloads/authsplcuncmp/
[53] G. Schaefer and M. Stich, "UCID - An Uncompressed Colour Image Database," Processing of SPIE, Storage and Retrieval Methods and Applications for Multimedia, San Jose, USA, pp.472-480, 16 Jan.2004.