| Presentation | 2003/11/13 Method of Gender and Age-Group Estimation by Integrating Multiple Information Satoshi IMAIZU, Kazuya UEKI, Kenichi KANEKO, Nobuhiro SEKINE, Jiro KATTO, Tetsunori KOBAYASHI, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We propose a technique for the estimation of gender and age-group from a low-resolution face image. In the proposed method, we adopt Principal-Component-Analysis-based feature extraction and Gaussian-Mixture-Mode-based likelihood calculation. As for the gender estimation, we compared three types of methods: first one is to use the likelihood calculated from the whole face image, second one is to combine the likelihood from the partial face image and that from the hair image, and third one is to combine them using the Dempster-Shafer theory. Experimental results show the slight superiority of the Dempster-Shafer-based combination method. As for the age-group estimation, we tried classification of three age-groups and got about 70% identification rate. We also applied our algorithms to the movies captured in a convenience store. Experimental results show that our algorithm works well also in the real environment. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Gender and Age-Group Estimation / PC A / GMM / Dempster-Shafer Theory |
| Paper # | PRMU2003-142,HIP2003-48 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2003/11/13(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 | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Method of Gender and Age-Group Estimation by Integrating Multiple Information |
| Sub Title (in English) | |
| Keyword(1) | Gender and Age-Group Estimation |
| Keyword(2) | PC A |
| Keyword(3) | GMM |
| Keyword(4) | Dempster-Shafer Theory |
| 1st Author's Name | Satoshi IMAIZU |
| 1st Author's Affiliation | Science and Engineering, Waseda University() |
| 2nd Author's Name | Kazuya UEKI |
| 2nd Author's Affiliation | Science and Engineering, Waseda University:NEC Soft, Ltd. |
| 3rd Author's Name | Kenichi KANEKO |
| 3rd Author's Affiliation | Science and Engineering, Waseda University:NEC Soft, Ltd. |
| 4th Author's Name | Nobuhiro SEKINE |
| 4th Author's Affiliation | NEC Soft, Ltd. |
| 5th Author's Name | Jiro KATTO |
| 5th Author's Affiliation | Science and Engineering, Waseda University |
| 6th Author's Name | Tetsunori KOBAYASHI |
| 6th Author's Affiliation | Science and Engineering, Waseda University |
| Date | 2003/11/13 |
| Paper # | PRMU2003-142,HIP2003-48 |
| Volume (vol) | vol.103 |
| Number (no) | 452 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |