| Presentation | 2017-07-21 The classification of natural scenes by color statistics Masatoshi Kitaguchi, Masahiro Wakabayashi, Hiromichi Sato, Tomoyuki Naito, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Little is known about the spatial and temporal color information structures in the scenes, which distinguish a scene from others. In this study, we had performed fixed-point imaging of 103 different locations at three distinctive times of day (morning, noon, and evening) during a year, and analyzed the involved color information in them. Using color statistics of the images, we conducted image classifications by support vector machine (SVM). Our results showed that with the most effective color statistics of the scene, SVM correctly classified the places, seasons and times of day of images ranging ~ 85-100%, suggesting that the color statistics may play roles for the scene identification. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Natural scene / Fixed-point imaging / landscape / Color Statistic / machine-learning |
| Paper # | IMQ2017-12,HIP2017-54 |
| Date of Issue | 2017-07-14 (IMQ, HIP) |
| Conference Information | |
| Committee | IMQ / HIP |
|---|---|
| Conference Date | 2017/7/21(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Satellite Campus, Sapporo City University |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Human Information Processing and Image Media Quality |
| Chair | Kenji Sugiyama(Seikei Univ.) / Masahiro Ishii(Sapporo City Univ.) |
| Vice Chair | Toshiya Nakaguchi(Chiba Univ.) / Mitsuru Maeda(Canon) / Miyuki Kamachi(Kogakuin Univ.) / Shuichi Sakamoto(Tohoku Univ.) |
| Secretary | Toshiya Nakaguchi(Nagoya Univ.) / Mitsuru Maeda(Sony) / Miyuki Kamachi(Univ. of Tsukuba) / Shuichi Sakamoto(Nagoya Univ.) |
| Assistant | Masaru Tsuchida(NTT) / Gosuke Ohashi(Shizuoka Univ.) / Atsushi Wada(NICT) / Kanaya Hidetoshi(Aichi Syukutoku Univ.) / Rika Mochizuki(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Image Media Quality / Technical Committee on Human Information Processing |
|---|---|
| Language | ENG-JTITLE |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | The classification of natural scenes by color statistics |
| Sub Title (in English) | |
| Keyword(1) | Natural scene |
| Keyword(2) | Fixed-point imaging |
| Keyword(3) | landscape |
| Keyword(4) | Color Statistic |
| Keyword(5) | machine-learning |
| 1st Author's Name | Masatoshi Kitaguchi |
| 1st Author's Affiliation | Osaka University(Osaka Univ.) |
| 2nd Author's Name | Masahiro Wakabayashi |
| 2nd Author's Affiliation | Osaka University(Osaka Univ.) |
| 3rd Author's Name | Hiromichi Sato |
| 3rd Author's Affiliation | Osaka University(Osaka Univ.) |
| 4th Author's Name | Tomoyuki Naito |
| 4th Author's Affiliation | Osaka University(Osaka Univ.) |
| Date | 2017-07-21 |
| Paper # | IMQ2017-12,HIP2017-54 |
| Volume (vol) | vol.117 |
| Number (no) | IMQ-144,HIP-145 |
| Page | pp.pp.33-37(IMQ), pp.33-37(HIP), |
| #Pages | 5 |
| Date of Issue | 2017-07-14 (IMQ, HIP) |