跳到主要內容

臺灣博碩士論文加值系統

(3.238.135.174) 您好!臺灣時間:2021/08/05 07:00
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:陳意翔
研究生(外文):Yi-Hsiang Chen
論文名稱:運用基因演算法與支撐向量機於數位影像來源相機鑑識之研究
論文名稱(外文):Source Camera of Digital Image Identification based on Support Vector Machine and Genetic Algorithms
指導教授:賴政良賴政良引用關係
指導教授(外文):Cheng-Liang Lai
學位類別:碩士
校院名稱:佛光大學
系所名稱:資訊學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:62
中文關鍵詞:數位鑑識基因演算法支撐向量機
外文關鍵詞:Digital ForensicsGenetic AlgorithmSupport Vector Machine
相關次數:
  • 被引用被引用:1
  • 點閱點閱:427
  • 評分評分:
  • 下載下載:48
  • 收藏至我的研究室書目清單書目收藏:0
現今數位影像擷取設備的普及化,且數位相片存在易於編輯及竄改等問題,使得數位鑑識的技術成為影像處理中一個重要的領域。本研究利用基因演算法搜尋出影像最佳特徵值,並利用支撐向量機進行分類,以減少數位影像來源相機辨識的時間,並同時可達到高辨識率。
本研究是利用數位相機與其所拍攝出的影像之關係,針對不同相機所拍攝出的影像,利用影像處理技術計算出影像的特徵值,並使用基因演算法的複製、交配、突變自動搜尋出最佳特徵值,再將這些由基因演算法所搜尋出之最佳特徵值利用支撐向量機進行訓練及分類,用以鑑別該影像之來源相機。在實驗設計部分,本研究實驗環境在不同廠牌、型號及相似或不相似的影像內容的情況下利用基因演算法搜尋出最佳特徵值,並利用支撐向量機做分類並驗證其辨識率。本研究也針對影像經過後製軟體做不同情形的修改包括:改變大小(resize)、模糊、增加額外的圖案的情況下鑑別該影像之來源相機。實驗結果顯示,本研究利用基因演算法自動搜尋出之最佳特徵值,不但可利用比相關文獻更少的特徵值得到較佳的辨識率,而且可以減少擷取影像特徵值的時間與數位影像來源辨識的執行時間。影像經過影像編輯軟體做修改後也可達到高辨識率。
In recent years, Digital image captures devices have become very common. Digital images also have the problem of being easy to edit and to tamper. As a result, digital forensics is now an important field in image processing. This research utilizes the Genetic Algorithm (GA) select optimal features, then the Support Vector Machine (SVM) used for classification, Reduce time of operation and achieved high accuracy for the source camera of the digital images.
This study is to analyze the relationship between digital cameras and images produced by them. Digital image processing technology is applied in the identification procedures in order to get images’ features. The features are then selected, crossed and mutated using the GA as a screening process to search the optimal features. Those features are trained and classified to identify the source camera of the images by SVM techniques. In experimental design, the different brands, models and the similar or dissimilar image content using GA search for the optimal features and then using SVM to classification and validation. This study also used image editing software for the post-processing of images, include resize, blurry and tamper then to identify the source camera of the images. The experimental results showed that the features selected using the GA could not only use less features, but also achieved better accuracy for the source camera of the digital images, and reduce images to extract the time of features and time of operation. We were also able to achieve high accuracy after the images were tampered.
中文摘要 I
英文摘要 II
致謝 III
目錄 IV
圖目錄 VI
表目錄 VII
第一章 緒論 1
1.1研究動機 1
1.2研究目的 3
第二章 文獻探討 5
2.1 鏡片像差 5
2.2 感測器雜訊 6
2.3 CFA內插法 7
2.4影像特徵值 9
2.4.1 影像色彩特徵 9
2.4.2 影像品質特徵 9
2.4.3 影像之頻率域特徵 10
第三章 研究方法 11
3.1支撐向量機(Support Vector Machine) 11
3.1.1 SVM概述 11
3.1.2 線性SVM 11
3.1.3 非線性SVM 13
3.1.4核心函數(Kernel Function) 14
3.2 基因演算法(Genetic Algorithm) 15
3.2.1基因演算法概述 15
3.2.2 初始族群(Initial Population) 16
3.2.3 適應函數(Fitness Function) 16
3.2.4 複製(Reproduction) 17
3.2.5 交配(Crossover) 18
3.2.6 突變(Mutation) 21
3.2.7 終止條件(Termination) 22
3.3利用基因演算法搜尋最佳特徵值 22
第四章 實驗結果 26
4.1 實驗流程 26
4.2 實驗個案 26
第五章 結論與未來研究方向 46
參考文獻 48
附錄:影像特徵值計算公式 50
[1] 電腦鑑識,台灣網路危機處理暨協調中心,http://www.cert.org.tw/document/column/show.php?key=67,2003-09。

[2] 蘇木春、張孝德,「機器學習類神經網路、模糊系統以及基因演算法」,全華科技圖書股份有限公司,民國88年1月。

[3] 周鵬程,「遺傳演算法原理與應用-活用Matlab」,全華科技圖書股份有限公司,民國91年10月。

[4] 蔡銘箴、吳冠輝、劉蓉、賴政良,「鑑定相機來源之數位鑑識研究」,資訊管理學報第14卷第2期。

[5] K. S. Choi, E. Y. Lam, and K. K. Y. Wong, “Source camera identification using footprints from lens aberration”, Proc. SPIE , Digital Photography II, vol. 6069 , pp. 155-162, 2006.

[6] Min-Jen Tsai, Cheng-Liang Lai and Jung Liu “Camera/mobile phone source identification for digital forensics” IEEE International Conference on Acoustic, Speech and Signal Processing, pp. 221-224, 2007.

[7] I. Avcibas, N. Memon, and B. sankur, “Steganalysis using image quality metrics”, IEEE Transactions on Image Processing, pp. 221-229, January 2003.

[8] C.- C. Chang and C.- J. Lin, “LIBSVM: a library for support vector machines”, 2001, software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm

[9] J. Lukas, J. Fridrich, and M. Goljan, “Digital camera identification from sensor pattern noise”, IEEE Transactions on Information Forensics and Security, vol. 1, pp. 205-214, June 2006.

[10] Z. J. Geradts, J. Bijhold, M. Kieft, K. Kurosawa, K. Kuroki, and N. Saitoh, “Methods for identification of images acquired with digital cameras”, Proc. SPIE, Enabling Technologies for Law Enforcement and Security, vol. 4232, pp.505-512, February 2001.

[11] A. Emir Dirik, Husrev T. Sencar and Nasir Memon “Source camera identification based on sensor dust characteristics”, IEEE, Signal Processing Applications for Public Security and Forensics, 11-13 April 2007 .

[12] S. Bayram, H. T. Sencar, N. Memon, and I. Avcibas, “Source camera identification based on CFA interpolation”, IEEE International Conference on Image Processing, vol. 3, pp. 69-72, 2005.

[13] M. Kharrazi, H.T. Sencar, and N. Memon, “Blind source camera identification”, IEEE International Conference on Image Processing, vol. 1, pp. 709-712, 2004.

[14] C.- W. Hsu, C.- C. Chang, and C.- J. Lin, “A Practical Guide to Support Vector Classification,” available at http://www.csie.ntu.edu.tw/~cjlin/paper/guide/guide.pdf

[15] M.- J. Tsai and C.- S. Wang, “Adaptive feature selection for digital camera source identification”, IEEE International Symposium on Circuits and Systems, pp. 412-415, 2008.

[16] J. Lukas, J. Fridrich, and M. Goljan, “Determining digital image origin using sensor imperfections” Proc. SPIE, Image and Video Communication and Processing, vol.5685, pp. 249-260, 2005.

[17] Tran Van Lanh, Kai-Sen Chong, Sabu Emmanuel, Mohan S Kankanhalli, “A survey on digital camera image forensic methods”, IEEE International Conference on Multimedia and Expo, pp. 16-19, 2007.

[18] K. S. Choi, E. Y. Lam, and K. K. Y. Wong, “Automatic source camera identification using the intrinsic lens radial distortion”, Optics Express, vol. 14, pp. 11551-11565, 2006.

[19] C. Cortes and V. Vapnik, “Support-vector networks”, Machine Learning, vol. 20, pp. 273-297, 1995.

[20] Nitin Khanna, Aravind K. Mikkilineni, Anthony F. Martone, Gazi N. Ali, George T. - C. Chiu, Jan P. Allebach, Edward J. Delp, “A survey of forensic characterization methods for physical devices”, Digital Investigation, vol. 3, pp. 17-28, 2006.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top