| Presentation | 2017-10-20 Estimating the attractiveness of a food photo using a Convolutional Neural Network Akinori Sato, Keisuke Doman, Takatsugu Hirayama, Ichiro Ide, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We have previously proposed a method for estimating the attractiveness of a food photo in order to assist a user to shoot attractive food photos. In this method, image features were extracted from food photos with attractiveness scores, and the attractiveness score of an input food photo was estimated in a regression framework. In this report, we describe the result of constructing an attractiveness estimator using a convolutional neural network (CNN) as a new approach to this method. Specifically, CNNs which transfer-learned each of the pre-trained models of VGG16, ResNet50 and Inception-v3 is constructed and used as an attractiveness estimator. From the results compared with the previous method, we confirmed that the attractiveness estimator based on the VGG16 pre-trained model was effective. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Food photo / shooting support / attractiveness / convolutional neural networks |
| Paper # | MVE2017-32 |
| Date of Issue | 2017-10-12 (MVE) |
| Conference Information | |
| Committee | MVE |
|---|---|
| Conference Date | 2017/10/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | KitamiInstitute of Technology |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Yoshinari Kameda(Univ. of Tsukuba) |
| Vice Chair | Kenji Mase(Nagoya Univ.) |
| Secretary | Kenji Mase(Kyoto Univ.) |
| Assistant | Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Media Experience and Virtual Environment |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Estimating the attractiveness of a food photo using a Convolutional Neural Network |
| Sub Title (in English) | |
| Keyword(1) | Food photo |
| Keyword(2) | shooting support |
| Keyword(3) | attractiveness |
| Keyword(4) | convolutional neural networks |
| 1st Author's Name | Akinori Sato |
| 1st Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 2nd Author's Name | Keisuke Doman |
| 2nd Author's Affiliation | Chukyo University(Chukyo Univ.) |
| 3rd Author's Name | Takatsugu Hirayama |
| 3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 4th Author's Name | Ichiro Ide |
| 4th Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 5th Author's Name | Yasutomo Kawanishi |
| 5th Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 6th Author's Name | Daisuke Deguchi |
| 6th Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 7th Author's Name | Hiroshi Murase |
| 7th Author's Affiliation | Nagoya University(Nagoya Univ.) |
| Date | 2017-10-20 |
| Paper # | MVE2017-32 |
| Volume (vol) | vol.117 |
| Number (no) | MVE-252 |
| Page | pp.pp.107-111(MVE), |
| #Pages | 5 |
| Date of Issue | 2017-10-12 (MVE) |