摘 要
近幾年來，由於行動裝置的快速發展與普及，數位攝影變得越來越方便，再加上數位影像處理相關技術越趨成熟，使得數位影像編輯軟體使用上也越來越容易。由於數位影像的資訊容易被修改，衍生數位影像鑑識的議題，因此該如何確認其影像內容的真實性變得越來越重要。本研究的目的在於快速偵測經過鈍化遮罩處理後的影像，也就是將銳化後的影像偵測出來，以垂直邊緣二進位編碼演算法為基礎加以改良，利用格雷碼對稱的特性，降低特徵的運算量，加快執行時間；再加上使用Otsu門檻化結合Canny邊緣偵測，可以保留對比明顯的邊緣，增加辨識的成功率。由實驗結果顯示，本研究之改良式鈍化遮罩偵測系統，對於一般拍攝環境下，經過鈍化遮罩處理過的影像具有快速且不錯的檢測效果。
關鍵詞：影像拼接辨識、鈍化遮罩偵測、Otsu門檻化、格雷碼
Abstract
Nowadays, with the advance of wireless technology, people generally have many mobile devices such as smart phones or tablet PCs. Therefore, photographing becomes very common in our daily lives. Owing to the fact that the software of digital image processing is becoming easier and easier to use, the issue of digital image authentication becomes more and more urgent. In this study, we focus on Unsharp Masking (USM) detection. The proposed detecting system is based on Edge Perpendicular Binary Coding (EPBC). We use Otsu thresholding to enhance the performance of Canny edge detection, so that the accuracy of USM detection can be increased. Moreover, the symmetric property of Gray encoding is used to reduce the number of feature points. This improves the execution time of the detecting system. Experimental results show that our proposed method has faster execution and better accuracy of USM detection for the normal shooting environment.
Keywords: Image Tampering Recognition, Unsharp Masking Detection, Otsu Thresholding, Gray Code