| Presentation | 2017-03-20 Fully Convolutional Networks based plant foreground segmentation Syunsuke Sakurai, Hideaki Uchiyama, Rin-ichiro Taniguchi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Analyzing plant phenotyping is a fundamental technology for many agricultural fields. Leaf segmentation is useful for automatic analysis of plant phenotyping. In this work, we investigate the tendency of neural networks through leaf semantic segmentation to construct leaf instance segmentation method based on deep learning. First, we examine leaf semantic segmentation using RGB images. Second, we examine transfer learning of different plants with a few inputs. Third, we examine leaf semantic segmentation using grayscale images. Finally, we examine robustness of networks to view-invariance applying affine transformation to input images. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep learning / FCN / Leaf segmentation / Transfer learning |
| Paper # | BioX2016-43,PRMU2016-206 |
| Date of Issue | 2017-03-13 (BioX, PRMU) |
| Conference Information | |
| Committee | PRMU / BioX |
|---|---|
| Conference Date | 2017/3/20(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Eisaku Maeda(NTT) / Masakatsu Nishigaki(Shizuoka Univ.) |
| Vice Chair | Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / Akira Otsuka(AIST) / Hiroshi Takano(Toyama Pref. Univ.) |
| Secretary | Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / Akira Otsuka(NEC) / Hiroshi Takano(AIST) |
| Assistant | Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / Masatsugu Ichino(Univ. of Electro-Comm.) / Naoyuki Takada(Secom) / Takahiro Aoki(Fujitsu Labs.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Biometrics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Fully Convolutional Networks based plant foreground segmentation |
| Sub Title (in English) | |
| Keyword(1) | Deep learning |
| Keyword(2) | FCN |
| Keyword(3) | Leaf segmentation |
| Keyword(4) | Transfer learning |
| 1st Author's Name | Syunsuke Sakurai |
| 1st Author's Affiliation | Kyushu University(Kyushu Univ.) |
| 2nd Author's Name | Hideaki Uchiyama |
| 2nd Author's Affiliation | Kyushu University(Kyushu Univ.) |
| 3rd Author's Name | Rin-ichiro Taniguchi |
| 3rd Author's Affiliation | Kyushu University(Kyushu Univ.) |
| Date | 2017-03-20 |
| Paper # | BioX2016-43,PRMU2016-206 |
| Volume (vol) | vol.116 |
| Number (no) | BioX-527,PRMU-528 |
| Page | pp.pp.57-62(BioX), pp.57-62(PRMU), |
| #Pages | 6 |
| Date of Issue | 2017-03-13 (BioX, PRMU) |