| Presentation | 2009-08-04 Sigma-Delta CNN Considering Local Structure of Image Hisashi AOMORI, Tsuyoshi OTAKE, Nobuaki TAKAHASHI, Ichiro MATSUDA, Susumu ITOH, Mamoru TANAKA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The sigma-delta cellular neural network (SD-CNN) is a complete framework of a spatial domain sigma-delta modulator, and has a very high image reconstruction (AD-to-DA) performance. In this architecture, the cell that is the basic processing unit of CNN are locally connected in the spatial regular grid. Though the CNN is very powerful and effective framework for image processing, The prediction performance of interpolation type CNN depends on the interpolation ability of spatial filter used for the A-template. Since the DAC in SD-CNN is designed by a prediction type CNN, its accuracy depends on performance of the A-template. In this paper, spatial frequency changes in local region of image are analyzed, and two templates are selected according to the spatial frequency changes for high precision prediction. The effectiveness of the proposed method is confirmed by the experimental results. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Σ-Δ Modulator / Local Structure of Image / Cellular Neural Network / Image Reconstruction |
| Paper # | NLP2009-52 |
| Date of Issue |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2009/7/27(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 | Nonlinear Problems (NLP) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Sigma-Delta CNN Considering Local Structure of Image |
| Sub Title (in English) | |
| Keyword(1) | Σ-Δ Modulator |
| Keyword(2) | Local Structure of Image |
| Keyword(3) | Cellular Neural Network |
| Keyword(4) | Image Reconstruction |
| 1st Author's Name | Hisashi AOMORI |
| 1st Author's Affiliation | Department of Electrical Engineering, Tokyo University of Science() |
| 2nd Author's Name | Tsuyoshi OTAKE |
| 2nd Author's Affiliation | Department of Software Science, Tamagawa University |
| 3rd Author's Name | Nobuaki TAKAHASHI |
| 3rd Author's Affiliation | IBM Systems & Technology Group, IBM Japan, Ltd. |
| 4th Author's Name | Ichiro MATSUDA |
| 4th Author's Affiliation | Department of Electrical Engineering, Tokyo University of Science |
| 5th Author's Name | Susumu ITOH |
| 5th Author's Affiliation | Department of Electrical Engineering, Tokyo University of Science |
| 6th Author's Name | Mamoru TANAKA |
| 6th Author's Affiliation | Department of Electrical and Electronics Engineering, Sophia University |
| Date | 2009-08-04 |
| Paper # | NLP2009-52 |
| Volume (vol) | vol.109 |
| Number (no) | 167 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |