Im2Calories: Towards an Automated Mobile Vision Food Diary

Resource | v1 | created by janarez |
Type Paper
Created 2015-12
Identifier ISBN: 9781467383912


We present a system which can recognize the contents of your meal from a single image, and then predict its nutritional contents, such as calories. The simplest version assumes that the user is eating at a restaurant for which we know the menu. In this case, we can collect images offline to train a multi-label classifier. At run time, we apply the classifier (running on your phone) to predict which foods are present in your meal, and we lookup the corresponding nutritional facts. We apply this method to a new dataset of images from 23 different restaurants, using a CNN-based classifier, significantly outperforming previous work. The more challenging setting works outside of restaurants. In this case, we need to estimate the size of the foods, as well as their labels. This requires solving segmentation and depth / volume estimation from a single image. We present CNN-based approaches to these problems, with promising preliminary results.


relates to Computer vision

Computer vision is an interdisciplinary scientific field that deals with how computers can gain high-...

about Automatic food clasiffication

Many people are interested in tracking what they eat to help them achieve weight loss goals or manag...

created by Google

The IT Support Professional Certificate program is part of Grow with Google, an initiative that draws...

referenced in Application of Deep Learning in Food: A Review

Deep learning has been proved to be an advanced technology for big data analysis with a large number...

Edit details Edit relations Attach new author Attach new topic Attach new resource
5.0 /10
useless alright awesome
from 1 review
Write comment Rate resource Tip: Rating is anonymous unless you also write a comment.
Resource level 7.0 /10
beginner intermediate advanced
Resource clarity 7.0 /10
hardly clear sometimes unclear perfectly clear
Reviewer's background 5.0 /10
none basics intermediate advanced expert
Comments 1
0 0

5 rating 7 level 7 clarity 5 user's background

Datasets are available. Quite easy to follow.
As with all papers no source codes. No cool approach that would blow your mind.
One of the first attempts to predict calorie intake of meals from images. Uses CNNs to tackle that and more advanced approaches such as segmentation and volume / size predictions.