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: 2013/12/02タイトル(英語): A Novel Method for Exploring Patch-level Context to Improve Image Categorization Performance著者名: Shuang Bai (Beijing Jiaotong University), Tetsuya Matsumoto (Nagoya University), Yoshinori Takeuchi (Daido University), Hiroaki Kudo (Nagoya University), Noboru Ohnishi (Nagoya University)著者名(英語): Shuang Bai (Beijing Jiaotong University), Tetsuya Matsumoto (Nagoya University), Yoshinori Takeuchi (Daido University), Hiroaki Kudo (Nagoya University), Noboru Ohnishi (Nagoya University)キーワード: Image categorization，Bag-of-visual words，Patch-level context，Representation fusion要約(英語): Patch-level context can be used to relieve ambiguity of patch encoding in the bag of visual words method. However, in previous research patches of interest are often combined to their context in a fixed way. In this paper, we propose a novel approach in which the variation of the closeness of the relationship between a patch of interest and its context is taken into consideration, so that the context can be utilized more effectively. Specifically, we associate each patch of interest with other patches and take them as its context. In patch encoding, the patch of interest is first encoded by its N nearest visual words. Then, the encoding is adjusted based on its context by investigating whether its assignments to the visual words get support from the context patches. Furthermore, to explore the image content extensively, given an input image, we create three representations using different context strategies and fuse them in a probabilistic manner. Finally, we evaluated the proposed method on the datasets scene categories 8, scene categories 13 and scene categories 15, respectively. Experimental results demonstrated the effectiveness of the proposed method.本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.133 No.12 （2013） 特集：電気関係学会東海支部連合大会本誌掲載ページ: 2264-2274 p原稿種別: 論文／英語電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/133/12/133_2264/_article/-char/ja/
Related
Related
Related
Related