進化型ニューラルネットワークのセル結合モデルによる画像変換
進化型ニューラルネットワークのセル結合モデルによる画像変換
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: 2012/03/01
タイトル(英語): Image Transformation with Cellularly Connected Evolutionary Neural Networks
著者名: 大塚 純二(横浜国立大学大学院環境情報学府),矢田 紀子(千葉大学大学院融合科学研究科),長尾 智晴(横浜国立大学大学院環境情報学府)
著者名(英語): Junji Otsuka (Graduate School of Environment and Information Sciences, Yokohama National University), Noriko Yata (Graduate School of Advanced Integration Science, Chiba University), Tomoharu Nagao (Graduate School of Environment and Information Sciences, Yokohama National University)
キーワード: ニューラルネットワーク,遺伝的アルゴリズム,画像処理 neural network,genetic algorithm,image processing
要約(英語): Constructing processes of image transformation manually requires a lot of effort, so several methods to automate it with machine learning, such as neural networks or genetic programming, have been proposed. Most of them are just constructed image filters that calculate an output value from values in local area in each pixel independently. However in several tasks, like area detections, the information of more distant area is helpful to processing. In this paper, we introduce a new neural network model for automatic construction of image transformation. The proposed model is composed of a regular array of the identical evolutionary neural networks, represented Real Valued Flexibly Connected Neural Network (RFCN) we previously proposed, and each RFCN connects with neighbor RFCNs. The proposed model is represented Cellular RFCN (CRFCN). Because of the local connections, each RFCN can consider information of distant area indirectly. We apply CRFCN to three kinds of image transformation tasks comparing with other methods and examine the effectiveness.
本誌: 電気学会論文誌C(電子・情報・システム部門誌) Vol.132 No.3 (2012) 特集:エネルギーハーベスティングと無線電力伝送
本誌掲載ページ: 430-438 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/132/3/132_3_430/_article/-char/ja/
受取状況を読み込めませんでした
