CalorieCamV2
CalorieCamV2 copied to clipboard
negi111111
Food Calorie Estimation using Deep Learning and AR
CalorieCamV2
This application measures real area of food using AR technology mounted on iphone and applied it to estimate calorie content.
Demo
Youtube link is here
Dependencies
- Swift >= 4.0
- iOS >= 11.0
- Xcode >= 9.0
Install
git clone https://github.com/negi111111/CalorieCamV2.gitpod install- Compile project with Xcode
Citation
If you use this app in a publication, a link to or citation of this repository would be appreciated.
@misc{
author = {Ryosuke Tanno},
title = {CalorieCamV2},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/negi111111/CalorieCamV2}},
}
Recognition Performance
Top–1 and Top–5 performance on the UECFood100 dataset. First 4 rows show the results achieved by using methods adopting hand-crafted features. Next 11 rows show the performance obtained by deep learningbased approaches on the ground-truth cropped images. Last 2 rows depict the results obtained considering images having more than a single food class (i.e., no ground truth is exploited). Best results is highlighted in boldface font.
| Method | Top-1 | Top-5 | Publication |
|---|---|---|---|
| DeepFoodCam | 72.26 | 92.00 | UBICOMP2014[1] |
| AlexNet | 75.62 | 92.43 | ACMMM2016[2] |
| DeepFood | 76.3 | 94.6 | COST2016 [3] |
| FV+DeepFoodCam | 77.35 | 94.85 | UBICOMP2014[1] |
| DCNN-FOOD | 78.77 | 95.15 | ICME2015[4] |
| VGG | 81.31 | 96.72 | ACMMM2016[5] |
| Inception V3 | 81.45 | 97.27 | ECCVW2016[6] |
| Arch-D | 82.12 | 97.29 | ACMMM2016[7] |
| ResNet-200 | 86.25 | 98.91 | CVPR2016[8] |
| WRN | 86.71 | 98.92 | BMVC2016[9] |
| WISeR | 89.58 | 99.23 | arXiv[10] |
| Inception-V4 | ??? | ??? | arXiv[11] |
| NASNet-A | ??? | ??? | arXiv[12] |
Publications
[1]Y. Kawano and K. Yanai. Food Image Recognition with Deep Convolutional Features. In ACM International Joint Conference on Pervasive and Ubiquitous Computing, 2014.[2] J. Chen and C.-W. Ngo. Deep-based Ingredient Recognition for Cooking Recipe Retrieval. In ACM Multimedia, 2016.
[3]C. Liu, Y. Cao, Y. Luo, G. Chen, V. Vokkarane, and Y. Ma. Deepfood: Deep learning-based food image recognition for computer-aided dietary assessment. In IEEE International Conference on Smart Homes and Health Telematics, volume 9677, pages 37–48, 2016.
[4]K. Yanai and Y. Kawano. Food image recognition using deep convolutional network with pre-training and fine-tuning. In International Conference on Multimedia & Expo Workshops, 2015.
[5]J. Chen and C.-W. Ngo. Deep-based Ingredient Recognition for Cooking Recipe Retrieval. In ACM Multimedia, 2016.
[6]H. Hassannejad, G. Matrella, P. Ciampolini, I. De Munari, M. Mordonini, and S. Cagnoni. Food Image Recognition Using Very Deep Convolutional Networks. In European Conference Computer Vision Workshops and Demonstrations, 2016.
[7] J. Chen and C.-W. Ngo. Deep-based Ingredient Recognition for Cooking Recipe Retrieval. In ACM Multimedia, 2016.
[8]K. He, X. Zhang, S. Ren, and J. Sun. Deep Residual Learning for Image Recognition. In International Conference on Computer Vision and Pattern Recognition, 2016.
[9]S. Zagoruyko and N. Komodakis. Wide Residual Networks. In British Machine Vision Conference, 2016.
[10]Ma. Niki, G. L. Foresti, and C. Micheloni. Wide-Slice Residual Networks for Food Recognition, arXiv preprint arXiv:1612.06543, 2016.
[11]C. Szegedy, S. Ioffe, V. Vanhoucke and A Alemi. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, arXiv preprint arXiv:1602.07261, 2016.
[12]B. Zoph, V. Vasudevan, J. Shlens, Q. V. Le. Learning Transferable Architectures for Scalable Image Recognition, arXiv preprint arXiv:1707.07012, 2017.
Thanks
License
MIT. Copyright (c) 2018 Ryosuke Tanno
Metadata
Owner
negi111111
Metadata
Food Calorie Estimation using Deep Learning and AR