多様体学習法と事例ベース法を融合した超解像技術とその高速化

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: 2012/11/01

タイトル(英語): Fast Example-Based Super-Resolution Using Manifold Learning

著者名: 谷口　和輝（立命館大学情報理工学部メディア情報学科），韓　先花（立命館大学情報理工学部メディア情報学科），大橋　基範（立命館大学情報理工学部メディア情報学科），岩本　祐太郎（立命館大学情報理工学部メディア情報学科），笹谷　聡（立命館大学情報理工学部メディア情報学科），陳　延偉（立命館大学情報理工学部メディア情報学科）

著者名(英語): Kazuki Taniguchi (Intellinent Image Processing Lab., Ritsumeikan University), Xian-Hua Han (Intellinent Image Processing Lab., Ritsumeikan University), Motonori Ohashi (Intellinent Image Processing Lab., Ritsumeikan University), Yutaro Iwamoto (Intellinent Image Processing Lab., Ritsumeikan University), So Sasatani (Intellinent Image Processing Lab., Ritsumeikan University), Yen-Wei Chen (Intellinent Image Processing Lab., Ritsumeikan University)

キーワード: 画質改善，超解像技術，多様体学習　　Image Restoration，Image Super-Resolution，Manifold Learning

要約(英語): This paper presents a new method for single-frame Super-Resolution (SR), by combining Example-based SR and neighbor embedding based SR (NE-based SR). Example-based SR attempts to generate High-Resolution (HR) image through estimating the High-Frequency (HF) components that are lost in the input Low-Resolution (LR) image. This method usually can achieve acceptable HR images if enough amounts of similar training samples are prepared. However, the HF component is approximated by only one training sample, which easily produces noise and artifacts. On the other hand, NE-based SR recovers HR image using manifold learning - Locally Linear Embedding, which represents any LR input and its corresponding HR one by a weighted linear combination of several training patches. The NE-based SR need to prepare large-scale training database with both intensity and structure variation, which will lead to high computation. This study combines these two methods to only estimate the HF components using several training samples. Moreover, we extend the proposed method to a fast version by processing only the patches with large variance. Experimental results show that the reconstructed HR images by our proposed approach are much better than those by conventional methods and interpolation techniques, and at the same time the computation is much faster.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.132 No.11 （2012） 特集：電気関係学会関西連合大会

本誌掲載ページ: 1768-1773 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/132/11/132_1768/_article/-char/ja/