| Presentation | 2018-03-18 Simultaneous Learning Model of Food Image Recognition and Ingrediensts Estimation Koyo Ito, Takao Yamanaka, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, many health-care applications such as food diary have been developed for smart devices. It is important for the applications to recognize the food category and the ingredients from a food image. In the generic object recognition, the accuracy has been dramatically improved by the deep convolutional neural networks(CNN). Using CNN, the food recognition has been successfully developed by learning both the food image recognition task and the ingredients estimation task, simultaneously. However, only the simple models have been studied in the previous works. In this paper, novel models using CNN have been proposed for the simultaneous learning of the food image recognition and the ingredients estimation. As results of the evaluation experiments, the accuracy was improved in the most of the proposed methods from the existing models. In the proposed models, the food recognition was improved by 1.4%, while the accuracy of the ingredients estimation was increased by 1.82% for Micro-F1 and 6.52% for Macro-F1. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | food image recognition / ingredients estimation / convolutional neural network / multi-task CNN |
| Paper # | BioX2017-38,PRMU2017-174 |
| Date of Issue | 2018-03-11 (BioX, PRMU) |
| Conference Information | |
| Committee | PRMU / BioX |
|---|---|
| Conference Date | 2018/3/18(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Kazuhiko Sumi(AGU) |
| Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Hiroshi Takano(Toyama Pref. Univ.) / Hitoshi Imaoka(NEC) |
| Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Hiroshi Takano(Shizuoka Univ.) / Hitoshi Imaoka(Fujitsu Labs.) |
| Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Masatsugu Ichino(Univ. of Electro-Comm.) / Naoyuki Takada(Secom) / Norihiro Okui(KDDI Research) |
| 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) | Simultaneous Learning Model of Food Image Recognition and Ingrediensts Estimation |
| Sub Title (in English) | |
| Keyword(1) | food image recognition |
| Keyword(2) | ingredients estimation |
| Keyword(3) | convolutional neural network |
| Keyword(4) | multi-task CNN |
| 1st Author's Name | Koyo Ito |
| 1st Author's Affiliation | Sophia University(Sophia Univ.) |
| 2nd Author's Name | Takao Yamanaka |
| 2nd Author's Affiliation | Sophia University(Sophia Univ.) |
| Date | 2018-03-18 |
| Paper # | BioX2017-38,PRMU2017-174 |
| Volume (vol) | vol.117 |
| Number (no) | BioX-513,PRMU-514 |
| Page | pp.pp.13-18(BioX), pp.13-18(PRMU), |
| #Pages | 6 |
| Date of Issue | 2018-03-11 (BioX, PRMU) |