Presentation | 2014-03-07 Food Image Recognition Using Convolutional Neural Networks for Helping Food Record Hokuto Kagaya, Kiyoharu AIZAWA, Makoto OGAWA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we discuss application of Convolutional Neural Networks (CNN), one of deep learning method, to image recognition to assist food record. In the small dataset, the best accuracy was 73.70%, which 10-15% higher than existing techniques. We also apply CNN to personal log, and then we found that re-training by the personal images the model trained by general images was better. We also use CNN for food detection. The accuracy of classification between food and non-food images was 93.75%. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Image Recognition / Foodlog / Food Recognition / Deep Learning / Convolutional Neural Networks |
Paper # | LOIS2013-66 |
Date of Issue |
Conference Information | |
Committee | LOIS |
---|---|
Conference Date | 2014/2/28(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 | Life Intelligence and Office Information Systems (LOIS) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Food Image Recognition Using Convolutional Neural Networks for Helping Food Record |
Sub Title (in English) | |
Keyword(1) | Image Recognition |
Keyword(2) | Foodlog |
Keyword(3) | Food Recognition |
Keyword(4) | Deep Learning |
Keyword(5) | Convolutional Neural Networks |
1st Author's Name | Hokuto Kagaya |
1st Author's Affiliation | Dept. of Information and Communication Eng. The University of Tokyo() |
2nd Author's Name | Kiyoharu AIZAWA |
2nd Author's Affiliation | Dept. of Information and Communication Eng. The University of Tokyo |
3rd Author's Name | Makoto OGAWA |
3rd Author's Affiliation | foo.log inc. |
Date | 2014-03-07 |
Paper # | LOIS2013-66 |
Volume (vol) | vol.113 |
Number (no) | 479 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |