| Presentation | 2006-06-16 Facial image classification by feature of generation using self-organization Koichi Ikuta, Hiroshi Kage, Ken-ichi Tanaka, Kazuo Kyuma, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | As management of personal information becomes strict in recent years, it becomes difficult to acquire a large amount of facial image data with personal information like gender, generation, etc. For this reason, we consider applying self-organization map algorithm to the problem of generation classification. The algorithm is capable of learning the some feature topology from the feature space. The feature construction of generation has continuousness in the feature space of facial image. However, it is difficult to control formations of proper MAP in general. Therefore we combine supervised learning to the self-organization of generation feature so that supervised signals works as leads of construction of generation topology. We tested the algorithm by computer simulation. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Self-organization MAP / facial image / generation classification / personal information |
| Paper # | NC2006-31 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2006/6/9(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) | Facial image classification by feature of generation using self-organization |
| Sub Title (in English) | |
| Keyword(1) | Self-organization MAP |
| Keyword(2) | facial image |
| Keyword(3) | generation classification |
| Keyword(4) | personal information |
| 1st Author's Name | Koichi Ikuta |
| 1st Author's Affiliation | Advanced Technology R&D Center Mitsubishi Electric Corporation() |
| 2nd Author's Name | Hiroshi Kage |
| 2nd Author's Affiliation | Advanced Technology R&D Center Mitsubishi Electric Corporation |
| 3rd Author's Name | Ken-ichi Tanaka |
| 3rd Author's Affiliation | Advanced Technology R&D Center Mitsubishi Electric Corporation |
| 4th Author's Name | Kazuo Kyuma |
| 4th Author's Affiliation | Advanced Technology R&D Center Mitsubishi Electric Corporation |
| Date | 2006-06-16 |
| Paper # | NC2006-31 |
| Volume (vol) | vol.106 |
| Number (no) | 102 |
| Page | pp.pp.- |
| #Pages | 4 |
| Date of Issue | |