ホサカ　タダアキ   HOSAKA TADAAKI   保坂　忠明    所属   明治大学  理工学部    職種   専任准教授
言語種別	英語
発行・発表の年月	2007/03
形態種別	学術雑誌
査読	査読あり
標題	Image Segmentation Using MAP-MRF Estimation and Support Vector Machine
執筆形態	共著(筆頭者)
掲載誌名	Interdisciplinary Information Sciences
掲載区分	国外
出版社・発行元	Tohoku University
巻・号・頁	13(1),pp.33-42
著者・共著者	Tadaaki Hosaka,Takumi Kobayashi,Nobuyuki Otsu
概要	Image segmentation has recently been studied in a framework of maximum a posteriori estimation for the Markov random field, where the cost function representing pixel-wise likelihood and inter-pixel smoothness should be minimized. The common drawback of these studies is the decrease in performance when a foreground object and the background have similar colors. We propose the likelihood formulation in the cost function considering not only a single pixel but also its neighboring pixels, and utilizing the support vector machine to enhance the discrimination between foreground and background. The global optimal solution for our cost function can be realized by the graph cut algorithm. Experimental results show an excellent segmentation performance in many cases.
DOI	10.4036/iis.2007.33
ISSN	1340-9050
NAID	110006274935
PermalinkURL	http://hdl.handle.net/10097/17445
researchmap用URL	https://jlc.jst.go.jp/DN/JALC/00291771207?from=CiNii