Image inpainting based on sparse representations with a perceptual metric

Ogawa, Takahiro; Haseyama, Miki

EURASIP Journal on Advances in Signal Processing, 2013, 2013, 179

Permalink : https://hdl.handle.net/2115/70669

このアイテムのアクセス数:486件（2026-08-19 01:00 集計）

ファイル	フォーマット	サイズ	閲覧回数	説明
Image inpainting based on sparse representations with a perceptual metric	pdf	1.85 MB	562

アクセス権	open access
URI	https://hdl.handle.net/2115/70669
タイトル	Image inpainting based on sparse representations with a perceptual metric
著者	e-Rad_Researcher 20524028 著者名 Ogawa, Takahiro
著者	e-Rad_Researcher 00218463 著者名 Haseyama, Miki
言語	英語
発行日	2013-12-05
出版者	Springer
収録物名	EURASIP Journal on Advances in Signal Processing
巻(号)	2013
ページ	179
抄録	This paper presents an image inpainting method based on sparse representations optimized with respect to a perceptual metric. In the proposed method, the structural similarity (SSIM) index is utilized as a criterion to optimize the representation performance of image data. Specifically, the proposed method enables the formulation of two important procedures in the sparse representation problem, ‘estimation of sparse representation coefficients’ and ‘update of the dictionary’, based on the SSIM index. Then, using the generated dictionary, approximation of target patches including missing areas via the SSIM-based sparse representation becomes feasible. Consequently, image inpainting for which procedures are totally derived from the SSIM index is realized. Experimental results show that the proposed method enables successful inpainting of missing areas.
資源タイプ	学術雑誌論文
出版タイプ	Version of Record
権利情報	Creative Commons Attribution 2.0 Generic
EISSN	1687-6180
関連情報 (isIdenticalTo)	出版社版DOI https://doi.org/10.1186/1687-6180-2013-179