カテゴリ: 論文誌(論文単位)グループ名: 【C】電子・情報・システム部門発行日: 2017/05/01タイトル(英語): Detecting Doctored JPEG Image Based on Block Noise Analysis and Double JPEG Analysis著者名: 多谷 邦彦（京都府警察科学捜査研究所），竹田 直人（（株）扶桑プレシジョン），小林 正（京都府警察科学捜査研究所），尾崎 吉明（京都府警察科学捜査研究所），黒木 修隆（神戸大学大学院工学研究科）著者名(英語): Kunihiko Taya (Forensic Science Lab., Kyoto Prefectural Police H. Q.), Naoto Takeda (FUSO PRECISION Co.,Ltd.), Tadashi Kobayashi (Forensic Science Lab., Kyoto Prefectural Police H. Q.), Yoshiaki Ozaki (Forensic Science Lab., Kyoto Prefectural Police H. Q.), Nobutaka Kuroki (Graduate School of Engineering, Kobe University)キーワード: 画像改ざん，JPEG，ブロックノイズ，Double JPEG Doctored image，JPEG，Block Noise，Double JPEG要約(英語): Today we can take many pictures with smart phones or digital cameras, and can edit them easily by ourselves. These pictures are very useful not only for hobby, but for investigation. It is very important to check whether they are doctored or not. This paper proposes an automatic detection method of doctored JPEG images based on two different analyisis: the block noise analysis and the Double-JPEG analysis. Former can find unnatural boundaries of 8×8 DCT blocks while latter can find double saved images by other editing software. Finally SVM classifies images into doctored and undoctored groups based on the above analysis. Experimental results have shown that the detection accuracy of our method achieves 0.90 in terms of F-measure while J. He's method achieves 0.82.本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.137 No.5 （2017）本誌掲載ページ: 742-749 p原稿種別: 論文／日本語電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/137/5/137_742/_article/-char/ja/
