ミヤタ　タカミチ   Takamichi Miyata   宮田　高道    所属   千葉工業大学  先進工学部 知能メディア工学科    千葉工業大学  工学研究科 工学専攻    千葉工業大学  先進工学研究科 知能メディア工学専攻    職種   教授
言語種別	英語
発行・発表の年月	2012
形態種別	学術雑誌
査読	査読あり
標題	Image Recovery by Decomposition with Component-wise Regularization
執筆形態	共著
掲載誌名	IEICE Transactions on Fundamentals
掲載区分	国内
巻・号・頁	vol. 95-A(no. 12),pp.pp. 2470-2478
著者・共著者	Shunsuke Ono,Takamichi Miyata,Isao Yamada,Katsunori Yamaoka
概要	Solving image recovery problems requires the use of some efficient regularizations based on a priori information with respect to the unknown original image. Naturally, we can assume that an image is modeled as the sum of smooth, edge, and texture components. To obtain a high quality recovered image, appropriate regularizations for each individual component are required. In this paper, we propose a novel image recovery technique which performs decomposition and recovery. We formulate image recovery as a convex optimization problem and design an iterative scheme based on the alternating direction method of multipliers for approximating its global minimizer efficiently. Experimental results reveal that the proposed image recovery technique outperforms a state-of-the-art method.