MCNNとSOMを用いた動画像の記銘と動的想起

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: 2015/04/01

タイトル(英語): Dynamical Recollection and Storage of Video Images via MCNN and SOM

著者名: 渡邊　駿（山口大学大学院理工学研究科），呉本　尭（山口大学大学院理工学研究科），小林　邦和（愛知県立大学情報科学部情報科学科），間普　真吾（山口大学大学院理工学研究科），大林　正直（山口大学大学院理工学研究科）

著者名(英語): Shun Watanabe (Graduate School of Science and Engineering, Yamaguchi University), Takashi Kuremoto (Graduate School of Science and Engineering, Yamaguchi University), Kunikazu Kobayashi (School of Information Science and Techonology, Aichi Prefectural University), Shingo Mabu (Graduate School of Science and Engineering, Yamaguchi University), Masanao Obayashi (Graduate School of Science and Engineering, Yamaguchi University)

キーワード: 連想記憶，多層カオスニューラルネットワーク，自己組織化マップ，動画像　　association memory，multi-layer chaotic neural network，self-organizing map，video images

要約(英語): Various association memory models have been proposed with artificial neural networks. For example, an interconnected network model proposed by Hopfield is able to recall stored patterns stably, a chaotic neural network (CNN) proposed by Adachi et al. is able to recall stored patterns dynamically. Kuremoto et al. proposed a multi-layer chaotic neural network (MCNN) with CNNs, which is able to recall multiple time series patterns orderly and dynamically. However, conventional association memory models used to be examined their association ability by experiments with simple binary patterns. In this paper, a novel association system is proposed to realize chaotic recollection of time series for video images using MCNN. In the proposed system, features of video images are extracted and clustered by Kohonen's self-organizing map (SOM), and those clustered feature maps are transformed to be binary images which are stored by MCNN with Hebbian Learning rule. In the recalling process, MCNN outputs time series patterns of different video images in the sense different features, and typical frame of images is able to be reproduced by the median feature vector. Dynamical and temporal association of the proposed system for the video images was confirmed by the experiment results.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.135 No.4 （2015） 特集：知覚情報技術の最前線

本誌掲載ページ: 414-422 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/135/4/135_414/_article/-char/ja/