臺灣博碩士論文加值系統

在數位化時代來臨的今天，許多的媒體都以數位化的形式記錄、呈現，數位設備大行其道，相對也面臨許多新興的數位需求，數位鑑識即是其中之一。
本文是研究數位相機與其拍攝出之影像之關係，針對不同相機所拍攝出的影像，結合影像處理技術與資料探勘方法，計算出影像的特徵值，並將這些特徵進行訓練及分類，用以鑑別該影像之來源相機；同時，針對此方法進行分析，依據分析結果提出改進方法以提高影像來源鑑識率，並提出實驗結果以說明其有效性。
此外，本辨識方法係利用各家廠商間相機的內部成像演算法不同，運算出隱藏在影像中的特徵，除了在不同廠牌的相機間具有優異辨識率外，本研究也探討在同廠牌且型號接近情況下，該方法是否仍具有辨識能力，並針對結果提出本方法之可能限制。
最後，根據實驗結果，提出結論說明之，並提出未來研究可能的方向與方法之建議。

In this digital era, all kinds of media data are recorded and presented digitally. The popularity of digital devices also brings up the needs for new digital data applications, and digital forensics is one of them.
This research is to analyze the relationship between digital cameras and images produced by them. First, digital image processing technology is applied with data mining method to get images’ features. Later, these features were trained and classified to identify the images’ original camera sources. Second, the identification features were further analyzed and improvements, based on the analyses, were proposed to enhance the identification precision rate.
In addition, camera manufacturers have various designs of image formation process for digital camera. By analyzing the distinctive feature of the process, the original camera source of digital image will be identified. This research focused on comparing and contrasting not only cameras of different manufacturers, but also those of the same manufacturer and similar models. By doing so, the potential limits of this identification method will be defined by the research results.
Finally, a conclusion based on the research findings is presented, and suggestions for future and further research are provided as well.

[1] 資策會資訊試場情報中心，http://mic.iii.org.tw/intelligence/，2005-01-26.
[2] 錢世傑、錢世豐、劉嘉明、張紹斌，電腦鑑識與企業安全，文魁資訊，民94
[3] 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
[4] 林一德，國立台灣大學法律研究所，電子數位資料於證據法上之研究，民國89年
[5] Timothy Wright，The Field guide for investigation Computer Crime: search and seizure basic part three, security focus, 2000。
[6] J. Adams, K. Parulski, and K. Spaulding, Color processing in digital cameras,. Micro, IEEE, vol. 18, pp.20.30, Nov.-Dec 1998.
[7] I. Avcibas, N. Memon, and B. sankur, .Steganalysis using image quality metrics.. IEEE transactions on Image Processing, January 2003.
[8] 陳同孝、張真誠、黃國峰，數位影像處理技術，松岡圖書資料股份有限公司，2001
[9] SRI International (2001)，”tsm API Library”, homepage of Digital Earth, 2001, http://www.tsmapi.com/geovrml.shtml。
[10] Kharrazi, M., Sencar, H. T., and Memon, N.: ”Blind Source Camera Identification”, Proc. ICIP’ 04, Singapore, October 24-27,2004.
[11] 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 Vol. 4232, p. 505-512, Enabling Technologies for Law Enforcement and Security, 2001.
[12] 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.
[13] DCView數位視野—數位相機、攝影專業網站，http://www.dcview.com.tw/