臺灣博碩士論文加值系統

數位化時代的來臨造就多采多姿的數位生活，但由於數位影像易於修改，因此數位影像的真實性成為重要的議題。區域複製篡改(Region Duplication Forgery)為一種簡單又常見的影像篡改方式，近年來提出的影像區域複製篡改偵測方法，大多使用稀疏性影像不變特徵，如SIFT、SURF等作為偵測之依據，雖然這些方法能有效偵測帶有幾何與亮度改變等篡改操作，但在影像不變特徵數量過於稀少或影像具有相似重複物件(Intrinsic Repeated Elements)時，容易造成無法偵測或錯誤判斷的結果。
本論文藉由修改SIFT演算法及提出影像不變特徵分群分析(Cluster Analysis)與區域離群值檢測(Local Outlier Detection)，以改善現有文獻無法解決之問題。此外，我們基於影像區域相關性與影像紋理特徵設計一適應性的篡改區域定位方法，用以獲得最佳的篡改區域定位圖作為偵測之結果。在實驗測試中，我們設計帶有幾何轉換與亮度變化的自動篡改程式進行實驗評估，從實驗結果顯示，我們提出利用影像不變特徵與區域相關性之偵測方式較現有文獻方法更加強健與準確。

With the coming of age of the digital era, it brings us a colorful digital life. However, the authenticity of digital image has become an important issue as the digital image is easily modified. Region duplication is a common and simple way to modify or tamper the digital image. The recent methods proposed in literature are based on spare image invariant feature (such as SIFT, SURF), and can effectively detect the geometric and brightness tampering. However, they fail to detect the tampering when the image invariant feature is inadequate, and often misclassify the original contents as the duplication tampering when the image contains the intrinsic repeated elements.
Our method proposes a modified SIFT algorithm, an image invariant feature clustering analysis, and local outlier detection to improve the above problem. In order to locate the tampering region, we design an adaptive tampering locating method based on image local region correlation and image texture feature. We evaluate our proposed approach on tampered images with and without intrinsic repeated elements, and the geometry and brightness of the tampered duplicated region is further altered by an automatic forgery program. The experimental results and analyses demonstrate that our proposed method is robust and effective in region duplication detection.

摘　要 i
ABSTRACT ii
誌　謝 iii
目　錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 研究動機與目的 1
1.2 研究方法 2
1.3 研究貢獻 3
1.4 論文組織架構 3
第二章 相關背景知識 4
2.1 SIFT特徵提取演算法 4
2.1.1 尺度空間極值檢測(Scale-Space Extrema Detection) 5
2.1.2 特徵點定位(Keypoint Localization) 7
2.1.3 主要方向性(Orientation Assignment) 8
2.1.4 特徵點描述(Keypoint Descriptor) 9
2.2 區域離群值演算法 10
2.3 GLCM紋理特徵演算法 12
第三章 相關文獻回顧與分析 14
3.1 稀疏特徵點提取分析 16
3.2 分群機制分析 17
3.3 區域相關性評估分析 17
第四章 本論文相關工作 18
4.1 平滑區域之特徵提取 18
4.2 相似物件區域排除 21
4.3 適應性之區域相關性評估 22
第五章 本論文提出之偵測方法 24
5.1 方法架構流程 24
5.2 特徵提取與匹配管理 25
5.3 匹配特徵對分群分析 26
5.3.1 空間位置的分群機制 26
5.3.2 密度基底的分群機制 27
5.4 仿射轉換估計 29
5.5 區域離群值檢測 32
5.6 篡改區域定位 34
5.6.1 區域相關性評估 34
5.6.2 重複區域定位 36
第六章 實驗結果與討論 38
6.1 實驗環境 38
6.2 自動篡改程式 38
6.3 評估標準 40
6.4 準確度評估實驗 42
6.5 JPEG壓縮與Blur處理測試 50
6.6 實際篡改影像之偵測實驗 51
6.7 時間複雜度分析 60
第七章 結論 61
參考文獻 62
附錄A 相似物件影像之準確度評估實驗 64
附錄B UCID影像資料庫之準確度評估實驗 70

[1]A. Haouzia and R. Noumeir, “Methods for Image Authentication: A Survey,” Springer Netherlands, Multimedia Tools and Applications, Vol. 39. No. 1, pp. 1-46, Aug. 2008.
[2]H. Farid, “Digital Image Forensics,” Scientific American Magazine, pp. 66-71, Jun. 2008.
[3]H. T. Sencar and N. Memon, “Overview of State-of-the-Art in Digital Image Forensics,” Statistical Science and Interdisciplinary Research. World Scientific Press, Singapore, 2008.
[4]B. Mahdian and S. Saic, “Blind Methods for Detecting Image Fakery,” IEEE International Carnahan Conference on Security Technology, pp. 280-286, Oct. 2008.
[5]T. V. Lanh, K. S. Chong, S. Emmanuel and M. S. Kankanhalli, “A Survey on Digital Camera Image Forensic Methods,” IEEE International Conference on Multimedia and Expo, pp. 16-19, Jul. 2007.
[6]W. Luo, Z. H. Qu, F. Pan and J. Huang, “A Survey of Passive Technology for Digital Image Forensics,” Frontiers of Computer Science in China, Vol. 1, pp. 166-179, May 2007.
[7]W. Luo, et al., ”Robust Detection of Region-Duplication Forgery in Digital Image,” International Conference on ICPR, Vol. 4 pp. 746-749, Sep. 2006.
[8]G. Li, et al., ”A Sorted Neighborhood Approach for Detecting Duplicated Regions in Image Forgeries Based on DWT and SVD,” IEEE International Conference on Multimedia and Expo, pp. 1750-1753, Aug. 2007.
[9]G. Liu, et al., “Detection of Image Region Duplication Forgery Using Model with Circle Block,” IEEE Conferences on MINES, Vol. 1, pp. 25-29, Jan. 2009.
[10]A.N. Myrna, et al., ”Detection of Region Duplication Forgery in Digital Images Using Wavelets and Log-Polar Mapping,” International Conference on Computational Intelligence and Multimedia Applications, Vol. 3, pp. 371-377, Dec. 2007.
[11]S. Bayram, H.T. Sencar, N. Memon; ”An efficient and robust method for detecting copy-move forgery,” ICASSP, pp. 1053-1056, May 2009.
[12]Q. Wu, S. Wang and X. Zhang, “Detection of Image Region-Duplication with Rotation and Scaling Tolerance”, Computational Collective Intelligence. Technologies and Applications, Vol. 6421, pp.100-108, 2010.
[13]B.S. Sergio, K.N. Asoke, "Automated detection and localisation of duplicated regions affected by refection, rotation and scaling in image forensics," EURASIP, Feb. 2011.
[14]S.J Ryu, M.J. Lee, H.K. Lee, “Detection of Copy-Rotate-Move Forgery Using Zernike Moments,” Workshop on Information Hiding (Lecture Notes in Computer Sciences).Berlin, Germany: Springer-Heidelberg, Vol.6387, pp.51-65, 2010.
[15]V. Christlein, C. Riess, E. Angelopoulou, “On rotation invariance in copy-move forgery detection”, IEEE International Workshop on Information Forensics and Security (WIFS), pp.1-6, 2010.
[16]H. Huang, W. Guo, Y. Zhang, ”Detection of Copy-Move Forgery in Digital Images Using SIFT Algorithm,” PACIIA, Vol.2, pp. 272-276, Jan. 2008.
[17]X. Bo, et al., ”Image Copy-Move Forgery Detection Based on SURF” IEEE Conferences on MINES, pp. 889-892, Nov. 2010.
[18]X. Pan and S. Lyu, ”Region Duplication Detection Using Image Feature Matching,” IEEE Transactions on Information Forensics and Security, Vol. 5, Issue 4, pp. 857-866, Nov. 2010. [In top 10 accessed articles of IEEE TIFS March 2011]
[19]E. Ardizzone, et al., ”Detecting multiple copies in tampered images,” ICIP, pp. 2117-2120, Sept. 2010.
[20]I. Amerini, et al., ”A SIFT-based forensic method for copy-move attack detection and transformation recovery,” IEEE Transactions on Information Forensics and Security, Vol. pp, pp. 1, Mar. 2011.
[21]P. Kakar, N. Sudha, “Exposing Postprocessed Copy-Paste Forgeries Though Transform-Invariant Features,” IEEE Transactions on Information Forensics and Security, Vol. 7, pp. 1018-1028, 2012.
[22]郭天穎、黃偲能，基於影像不變特徵及區域離群值檢測之重複區域篡改偵測，國立臺北科技大學電機工程系碩士論文，中華民國一百年七月
[23]D. Lowe, “Distinctive image features from scale-invariant keypoints,” Int.’l Journal of Computer Vision, Vol. 60, No.2, pp. 91-110, 2004.
[24]H. Bay, et al., "SURF: Speeded Up Robust Features", Computer Vision and Image Understanding, Vol. 110, pp. 346-359, 2008.
[25]M. Breunig, H.P. Kriegel, R.T. Ng, J. Sander, "LOF: Identifying Density-Based Local Outliers," ACM SIGMOD Int. Conf. on Management of Data, Vol. 29, No. 2, pp.93-104,Jun. 2000.
[26]R. M. Haralick, K Shanmugam, “Textural Features for Image Classification", IEEE Transactions on Systems, Man, and Cybernetics SMC-3 (6): 610–621.
[27]Wikipedia contributors, Cluster analysis,
[online] http://en.wikipedia.org/wiki/Cluster_analysis (Accessed: 10 July 2012).
[28]R. Hess, ”An Open Source SIFT Library ,” ACM MM, 2010.
[29]G. Schaefer and M. Stich, “UCID—an uncompressed colour image database ” School Comput. Math., Nottingham Trent University, Nottingham,U.K., Tech. Rep., 2003 Available: http://www-staff.lboro.ac.uk/~cogs/datasets/UCID/ucid.html
[30]R. Franzen, “Kodak Lossless True Color Image Suite”
Available: http://r0k.us/grapics/kodak/