イトイ　キヨアキ   Kiyoaki Itoi   糸井　清晃    所属   千葉工業大学  工学部 情報通信システム工学科    千葉工業大学  工学研究科 情報通信システム工学専攻    職種   助教
言語種別	英語
発行・発表の年月	2017/11
形態種別	学術雑誌
査読	査読あり
標題	Convex Filter Networks Based on Morphological Filters and their Application to Image Noise and Mask Removal
執筆形態	共著
掲載誌名	IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
掲載区分	国内
出版社・発行元	The Institute of Electronics, Information and Communication Engineers
巻・号・頁	Vol.E100-A(No.11),pp.2238-2247
著者・共著者	Makoto NAKASHIZUKA, Kei-ichiro KOBAYASHI, Toru ISHIKAWA, Kiyoaki ITOI
概要	This paper presents convex filter networks that are obtained from extensions of morphological filters. The proposed filter network consists of a convex and concave filter that are extensions of the dilation and erosion of mathematical morphology with the maxout activation function. Maxout can approximate arbitrary convex functions as piecewise linear functions, including the max function. The class of the convex function hence includes the morphological dilation and can be trained for specific image processing tasks. In this paper, the closing filter is extended to a convex-concave filter network with maxout. The convex-concave filter is trained by the stochastic gradient method for noise and mask removal. The examples of noise and mask removal show that the convex-concave filter can obtain a recovered image, whose quality is comparable to inpainting by using the total variation minimization with reduced computational cost without mask information of the corrupted pixels.