Presentation 2012-11-07
Bayesian image super-resolution of large image with a compound MRF and estimating registration parameters
Toshiki KINOSHITA, Seiji MIYOSHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Super-resolution is a technique to estimate a higher resolution image from low-resolution images. In this manuscript, we first conduct processing large images in Bayesian super-resolution using latent variables of the line process by Kanemura et al. It is shown that we can obtain good results for a large image. Second, we propose a method of estimating registration parameters from any area of images. Previously, we estimated registration parameters from center area of images. This change allowed good estimation of registration parameters by using area which has a large change of pixel values.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) super-resolution / compound Markov random field prior / Bayesian inference / variational EM algorithm
Paper # IBISML2012-35
Date of Issue

Conference Information
Committee IBISML
Conference Date 2012/10/31(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 Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Bayesian image super-resolution of large image with a compound MRF and estimating registration parameters
Sub Title (in English)
Keyword(1) super-resolution
Keyword(2) compound Markov random field prior
Keyword(3) Bayesian inference
Keyword(4) variational EM algorithm
1st Author's Name Toshiki KINOSHITA
1st Author's Affiliation Graduate School of Science and Engineering, Kansai University()
2nd Author's Name Seiji MIYOSHI
2nd Author's Affiliation Faculty of Engineering Science, Kansai University
Date 2012-11-07
Paper # IBISML2012-35
Volume (vol) vol.112
Number (no) 279
Page pp.pp.-
#Pages 8
Date of Issue