| Presentation | 2017-07-13 A Study of Image Inpainting Methods by using SD-CNN Ryohei Mizutani, Hideharu Toda, Hisashi Aomori, Sathit Prasomphan, Mamoru Tanaka, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, the practical use of digital images have been progressed because of the popularization and advance of information terminals such as personal computers, smartphones and tablets. The image deteriorations are caused by image sensor failure, noise mixing in communication path, digitization of already defected photographs and mixing of unwilling objects. In our previous work, to cope with above problems, the basic restoration technique of damaged image using the sigma-delta cellular neural network (SD-CNN) was proposed. In this paper, to improve restoration performance, we propose a novel image inpainting method using the SD-CNN having the defective-pixel-oriented B-template. In the proposed method, in order to perform optimal pixel reconstruction, the B-template is adaptively switched according missing pixel information. We performed image reconstruction experiments on 6 images with 10% - 50% loss rate and clarified that the proposed method has better image restoration performance than that of our previous method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Sigma-Delta Modulation / Cellular Neural Network / Image Inpainting |
| Paper # | NLP2017-37 |
| Date of Issue | 2017-07-06 (NLP) |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2017/7/13(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Miyako Island Marine Terminal |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | etc. |
| Chair | Masaharu Adachi(Tokyo Denki Univ.) |
| Vice Chair | Norikazu Takahashi(Okayama Univ.) |
| Secretary | Norikazu Takahashi(Nagaoka Univ. of Tech.) |
| Assistant | Toshihiro Tachibana(Shonan Inst. of Tech.) / Masayuki Kimura(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Nonlinear Problems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Study of Image Inpainting Methods by using SD-CNN |
| Sub Title (in English) | |
| Keyword(1) | Sigma-Delta Modulation |
| Keyword(2) | Cellular Neural Network |
| Keyword(3) | Image Inpainting |
| 1st Author's Name | Ryohei Mizutani |
| 1st Author's Affiliation | Chukyo University(Chukyo Univ.) |
| 2nd Author's Name | Hideharu Toda |
| 2nd Author's Affiliation | Chukyo University(Chukyo Univ.) |
| 3rd Author's Name | Hisashi Aomori |
| 3rd Author's Affiliation | Chukyo University(Chukyo Univ.) |
| 4th Author's Name | Sathit Prasomphan |
| 4th Author's Affiliation | King Mongkut University of Technology North Bangkok(King Mongkut Univ. of Tech. North Bangkok) |
| 5th Author's Name | Mamoru Tanaka |
| 5th Author's Affiliation | Sophia University(Sophia Univ.) |
| Date | 2017-07-13 |
| Paper # | NLP2017-37 |
| Volume (vol) | vol.117 |
| Number (no) | NLP-121 |
| Page | pp.pp.53-57(NLP), |
| #Pages | 5 |
| Date of Issue | 2017-07-06 (NLP) |