Presentation 2012-11-17
Design of probabilistic image inpainting filters using Gaussian graphial models
Tomotaka KITAGAWA, Muneki YASUDA, Kazuyuki TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A probabilistic image inpainting filter is an image processing filter that reconstructs lost or deteriorated pixels of images by using information of other pixels in the images. Pixel-based probabilistic image inpainting filters on the basis of a Gaussian graphical models (Gaussian Markov random fields), which can fast reconstruct damaged parts of images, have been proposed by some authors. In this paper, to reconstruct larger damaged regions in images, we propose a new texture-based probabilistic image inpainting filter by extending the pixel-based probabilistic image inpainting filters.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image inpainting / Bayes statistics / probabilistic information processing / Gaussian graphical model / maximum likelihood estimation
Paper # NC2012-71
Date of Issue

Conference Information
Committee NC
Conference Date 2012/11/9(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Design of probabilistic image inpainting filters using Gaussian graphial models
Sub Title (in English)
Keyword(1) image inpainting
Keyword(2) Bayes statistics
Keyword(3) probabilistic information processing
Keyword(4) Gaussian graphical model
Keyword(5) maximum likelihood estimation
1st Author's Name Tomotaka KITAGAWA
1st Author's Affiliation Department of Applied Information Sciences, Graduate School of Information Sciences, Tohoku University()
2nd Author's Name Muneki YASUDA
2nd Author's Affiliation Department of Applied Information Sciences, Graduate School of Information Sciences, Tohoku University
3rd Author's Name Kazuyuki TANAKA
3rd Author's Affiliation Department of Applied Information Sciences, Graduate School of Information Sciences, Tohoku University
Date 2012-11-17
Paper # NC2012-71
Volume (vol) vol.112
Number (no) 298
Page pp.pp.-
#Pages 6
Date of Issue