| Presentation | 2016-11-17 Gaussian Markov random field model without periodic boundary conditions Shun Katakami, Hirotaka Sakamoto, Shin Murata, Masato Okada, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this study, we discuss Gaussian Markov random field model without periodic boundary conditions. First, we formulate a generative model and an estimation model of images without periodic boundary conditions by Markov random field model. Second, by applying Bayes’ theorem to the the estimation model, we explain image restorations, the estimation of hyperparameters, and the expectation of free energy. Third, we conduct numerical simulations to compare the method with a method which assume periodic boundary conditions. Finally, we verify the effectiveness of this method focusing on the difference between the generative and estimation models. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Markov random field model / Bayesian inference / hyperparameter estimation / image restoration / boundary condition |
| Paper # | IBISML2016-83 |
| Date of Issue | 2016-11-09 (IBISML) |
| Conference Information | |
| Committee | IBISML |
|---|---|
| Conference Date | 2016/11/16(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Kyoto Univ. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Information-Based Induction Science Workshop (IBIS2016) |
| Chair | Kenji Fukumizu(ISM) |
| Vice Chair | Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Kyoto Univ.) |
| Secretary | Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Nagoya Inst. of Tech.) |
| Assistant | Toshihiro Kamishima(AIST) / Tomoharu Iwata(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Gaussian Markov random field model without periodic boundary conditions |
| Sub Title (in English) | |
| Keyword(1) | Markov random field model |
| Keyword(2) | Bayesian inference |
| Keyword(3) | hyperparameter estimation |
| Keyword(4) | image restoration |
| Keyword(5) | boundary condition |
| 1st Author's Name | Shun Katakami |
| 1st Author's Affiliation | The University of Tokyo(UTokyo) |
| 2nd Author's Name | Hirotaka Sakamoto |
| 2nd Author's Affiliation | The University of Tokyo(UTokyo) |
| 3rd Author's Name | Shin Murata |
| 3rd Author's Affiliation | The University of Tokyo(UTokyo) |
| 4th Author's Name | Masato Okada |
| 4th Author's Affiliation | The University of Tokyo(UTokyo) |
| Date | 2016-11-17 |
| Paper # | IBISML2016-83 |
| Volume (vol) | vol.116 |
| Number (no) | IBISML-300 |
| Page | pp.pp.267-274(IBISML), |
| #Pages | 8 |
| Date of Issue | 2016-11-09 (IBISML) |