English  |  正體中文  |  简体中文  |  Items with full text/Total items : 60861/93527 (65%)
Visitors : 1498754      Online Users : 9
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/74550

    Title: Image forgery detection algorithms
    Other Titles: 影像造假偵測之演算法
    Authors: 王駿瑋;Wang, Chun-Wei
    Contributors: 淡江大學資訊工程學系博士班
    林慧珍;Lin, Hwei-Jen
    Keywords: 複製-移動;重新取樣;位移向量;零化濾鏡;字彚排序;基數排序;連通元件分析;中間值濾波;重新取樣倍率;線性內插;copy-move;resampling;shift vector;zeroing mask;lexicographical sort;radix sort;Connected Component Analysis;medium filtering;resampling rate;Linear interpolation
    Date: 2011
    Issue Date: 2011-12-28 18:50:46 (UTC+8)
    Abstract: 在本論文中,我們提出了影像複製-移動偵測演算法與影像重新取樣偵測演算法。為了偵測影像複製-移動之造假,給定的影像將會分成重疊的區塊,再對每一個區塊抽取出一組特徵,以一向量表示之。接著對所有的特徵向量利用基數排序法進行排序,接著計算每一對相鄰的向量其相對區塊位置的差,稱之為位移向量。相同的位移向量累積量達一門檻值時,很可能就會存在著重複的區域。而這些向量所對應到的區塊就會被標示,而後再對這些標示的區塊進行中間值濾波及連通元件分析的處理,就能求出複製-移動的區域。在影像重新取樣之偵測的部分,我們提出了兩個偵測的方法:精確偵測法與近似偵測法。精確偵測法分為三個部分:對於一個重新取樣倍率,提出了一個建構重新取樣矩陣的演算法(RMC);提出了一個對於一個重新取樣倍率,推導出其一零化濾鏡之演算法;提出了一個演算法(RD),使用一組零化濾鏡來進行影像重新取樣偵測。此精確偵測法只能偵測出系統提供的零化濾鏡之相對取樣倍率,使用上較缺乏彈性,因而提出近似偵測法,來改善這樣的缺點。近似偵測法裡,當影像重新取樣倍率與使用的零化濾鏡的倍率很接近時,其倍率可以被近似估測出。此方法藉由檢查影像與零化濾鏡的旋積值之週期性,來推論出這張影像的重新取樣倍率。實驗結果可看出我們提出的兩種影像造假之偵測方法均具有極高偵測率與效率。
    In this thesis, we propose a method to detect copy-move forgery of images and two methods to detect resampling of images. To detect copy-move forgery of an image, the given image is divided into overlapping blocks of equal size, features for each block are then extracted and represented as a vector, all the extracted feature vectors are then sorted using a radix sort. The difference of the positions of every pair of adjacent feature vectors, called shift vector, in the sorting list is computed. The accumulated number for each of the shift vectors is evaluated. A large accumulated number is considered as possible presence of a duplicated region, and thus all the feature vectors corresponding to the shift vectors with large accumulated numbers are detected, whose corresponding blocks are then marked to form a tentative detected result. Finally the medium filtering and connected component analysis are performed on the tentative detected result to obtain the final result. For resampling detection, two detection methods are proposed. The former method was exact detection which includes three steps: first, we present an algorithm Resampling Matrix Construction (RMC) that automatically derives the resampling matrix for any given factor. Second, we show an algorithm that constructs a zeroing mask for the resampling by a factor with the support of the corresponding resampling matrix produced by the proposed algorithm Zeroing Mask Derivation (ZMD). Lastly, we propose an algorithm RD that detects resampling on images using the zeroing masks in a specific order. The latter is an improved version of exact detection to detect a much wider range of resampling factors by checking some periodic repetition with an approximation detection mechanism. The experimental results have demonstrated that the proposed methods are indeed effective and efficient.
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Thesis

    Files in This Item:

    File SizeFormat

    All items in 機構典藏 are protected by copyright, with all rights reserved.

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback