現今，我們處在一個數位影像的時代裡。數位影像在人類的生活中，扮演著極重要的角色，因為，每一位人士都可在每天看到大量的數位影像；然而，過去我們曾經所看過的那些數位影像，完全都是真實無誤的嗎？
隨著眾多數位影像編輯軟體的信手可得，例如：Adobe Photoshop，數位影像是很容易地遭受到惡意人士的竄改，以進行非法的用途。假設此種情況發生於我們的生活中，將會導致數位影像的內容不切實際，並且誤導人們去相信從未發生的事物；因此，如何開發出一套數位影像驗證系統，是一項非常重要的研究。
在本篇論文中，我們提出兩套影像驗證系統。第一套是竄改影像偵測系統，第二套是竄改影像定位系統。基於倒傳遞神經網路的竄改影像偵測系統，能夠偵測輸入的數位影像，是否有遭受到竄改；如果此張數位影像被偵測為竄改，基於壓縮像差的竄改影像定位系統，可以定位出影像中的竄改區域。
在實驗測試中，我們使用CASIA v1.0竄改影像偵測的資料庫來評估本方法所提出的性能。於CASIA v1.0竄改影像的資料庫中，具有兩種類型的竄改影像，分別是影像拼貼(Image splicing)與複製移動(Copy-move forgery)。最後，我們列出當前最先進的方法，並且取之實驗結果與我們進行比較，結果顯示，本方法所提出的性能具有最高的分類準確度，同時也可定位出影像當中的竄改區域。

Nowadays, we are living in the era of digital image. Digital image plays an important role in our human life because everyone may see a lot of digital images every day. However, are those images that we have seen completely real? With many kinds of photo-editing software (e.g. Adobe Photoshop), digital image can easily be tampered by malicious user. In this case, the content of digital image is not real and mislead the people to trust something that never happen in real life. Therefore, how to develop an image authentication system is a very important research.
In this thesis, we propose two image authentication systems. One is tampered image detection, and the other is tampered image location. The system of tampered image detection can detect whether an image is authentic or tampered, which is based on back-propagation neural network (BPNN). If an image in the system of tampered image detection is detected as tampered, the system of tampered image location can locate the tampered region from this image, which is based on compression ghost approaches.
In our experiments, we apply CASIA Tampered Image Detection Evaluation Database (CASIA TIDE v1.0) to evaluate our image authentication systems. There have two types of image tampering in this benchmark dataset. One is image splicing, and the other is copy-move forgery. Finally, we list some state-of-the-art methods to compare their functionalities with our proposed method. The outcome shows that our proposed method has higher classification accuracy than previous literatures, and also has the ability to locate the tampered region in tampered image.

[1] T. Qazi, K. Hayat, S. U. Khan, S. A. Madani, I. A. Khan, Ko, x, J. odziej, H. Li, W. Lin, K. C. Yow, and C. Z. Xu, “Survey on blind image forgery detection,” Image Processing, IET, vol. 7, no. 7, pp. 660-670, 2013.
[2] H. Shah, P. Shinde, and J. Kukreja, “Retouching Detection and Steganalysis,” International Journal of Engineering Innovations and Research, vol. 2, no. 6, pp. 487-490, 2013.
[3] H. Farid, "Exposing Digital Forgeries From JPEG Ghosts," IEEE Transactions on Information Forensics and Security, vol. 4, no. 1, pp. 154-160, 2009.
[4] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," Systems, Man and Cybernetics, IEEE Transactions on, vol. 9, no. 1, pp. 62-66, 1979.
[5] M. Moniruzzaman, M. A. K. Hawlader, and M. F. Hossain, "An image fragile watermarking scheme based on chaotic system for image tamper detection," in Informatics, Electronics & Vision (ICIEV), 2014 International Conference on, pp. 1-6, 2014.
[6] G. Muhammad, M. H. Al-Hammadi, M. Hussain, and G. Bebis, “Image forgery detection using steerable pyramid transform and local binary pattern,” Machine Vision and Applications, vol. 25, no. 4, pp. 985-995, May, 2014.
[7] W. Junwen, L. Guangjie, X. Bo, L. Hongyuan, D. Yuewei, and W. Zhiquan, "Image Forgery Forensics Based on Manual Blurred Edge Detection," in Multimedia Information Networking and Security (MINES), 2010 International Conference on, pp. 907-911, 2010.
[8] K. Bahrami, A. C. Kot, L. Leida, and L. Haoliang, “Blurred Image Splicing Localization by Exposing Blur Type Inconsistency,” Information Forensics and Security, IEEE Transactions on, vol. 10, no. 5, pp. 999-1009, 2015.
[9] W. Wang, J. Dong, and T. Tan, "Tampered region localization of digital color images based on JPEG compression noise," in 9th International Workshop on Digital Watermarking, IWDW 2010, October 1, 2010 - October 3, 2010, Seoul, Korea, Republic of, pp. 120-133, 2011.
[10] Credits for the use of the CASIA Image Tempering Detection Evaluation Database (CAISA TIDE) V1.0 are given to the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Corel Image Database and the photographers. http://forensics.idealtest.org
[11] A. A. Alahmadi, M. Hussain, H. Aboalsamh, G. Muhammad, and G. Bebis, "Splicing image forgery detection based on DCT and Local Binary Pattern," in 2013 1st IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013, Austin, TX, pp. 253-256, 2013.
[12] W. Wang, J. Dong, and T. Tan, "Image tampering detection based on stationary distribution of Markov chain," in 2010 17th IEEE International Conference on Image Processing, ICIP 2010, September 26, 2010 - September 29, 2010, Hong Kong, pp. 2101-2104, 2010.
[13] G. Muhammad, M. H. Al-Hammadi, M. Hussain, A. M. Mirza, and G. Bebis, "Copy move image forgery detection method using steerable pyramid transform and texture descriptor," in EUROCON, 2013 IEEE, pp. 1586-1592, 2013.
[14] S. Q. Saleh, M. Hussain, G. Muhammad, and G. Bebis, "Evaluation of image forgery detection using multi-scale weber local descriptors," in 9th International Symposium on Advances in Visual Computing, ISVC 2013, July 29, 2013 - July 31, 2013, Rethymnon, Crete, Greece, pp. 416-424, 2013.
[15] W. Wei, D. Jing, and T. Tieniu, "Effective image splicing detection based on image chroma," in Image Processing (ICIP), 2009 16th IEEE International Conference on, pp. 1257-1260, 2009.
[16] Y. Zhang, C. Zhao, Y. Pi, and S. Li, "Revealing image splicing forgery using local binary patterns of DCT coefficients," 2012 International Conference on Communications, Signal Processing, and Systems, CSPS 2012, pp. 181-189, 2012.
[17] T. Ahonen, A. Hadid, and M. Pietikainen, “Face Description with Local Binary Patterns: Application to Face Recognition,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 28, no. 12, pp. 2037-2041, 2006.
[18] T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 24, no. 7, pp. 971-987, 2002.
[19] “Center for Machine Vision Research (CMV),” [Online] Available http://www.cse.oulu.fi/CMV (accessed on June 26, 2015)
[20] D. R. G. H. R. Williams and G. Hinton, "Learning representations by back-propagating errors," Nature, vol. 323, pp. 533-536, 1986.
[21] M. Negnevitsky, Artificial intelligence: a guide to intelligent systems: 2nd Ed. Pearson Education, 2005.
[22] D. Garcia-Ordas, L. Fernandez-Robles, E. Alegre, M. T. Garcia-Ordas, and O. Garcia-Olalla, "Automatic Tampering Detection in Spliced Images with Different Compression Levels," Pattern Recognition and Image Analysis, Ibpria 2013, vol. 7887, pp. 416-423, 2013.
[23] “Weka Data Mining Software”, [Online] Available http://www.cs.waikato.ac.nz/ml/weka/ (accessed on June 26, 2015)
[24] D. Jing, W. Wei, and T. Tieniu, "CASIA Image Tampering Detection Evaluation Database," in Signal and Information Processing (ChinaSIP), 2013 IEEE China Summit & International Conference on, pp. 422-426, 2013.
[25] X. Zhao, J. Li, S. Li, and S. Wang, "Detecting digital image splicing in chroma spaces," in 9th International Workshop on Digital Watermarking, IWDW 2010, October 1, 2010 - October 3, 2010, Seoul, Korea, Republic of, pp. 12-22, 2011.
[26] M. H. Al-Hammadi, G. Muhammad, M. Hussain, and G. Bebis, "Curvelet transform and local texture based image forgery detection," in 9th International Symposium on Advances in Visual Computing, ISVC 2013, July 29, 2013 - July 31, 2013, Rethymnon, Crete, Greece, pp. 503-512, 2013.