Theme: Food Calorie Estimation
Team Members: Okan ALAN Gökberk Şahin Emre Yazıcı
This is our first blog post. In this blog post, we will explain our project’s outlines.
Introduction
What is a calorie? A calorie is the amount of heat needed to raise the temperature of one gram of water by one degree Celsius. Calories in food provide energy in the form of heat so that our bodies can function.
We all need this energy to live and stay healthy. Everything we do relies on the energy that comes in the form of calories. We should pay attention to how many calories we took. If we take more than we burn, we gain weight. When people’s Body Mass Index (BMI) is over 30 (kg/m2), they are generally considered to be obese. High BMI can increase the risk of illnesses like heart disease [1].
What did we do this week? We examined related works and our dataset that we found. We determined to get reference one project that is first related work in below.
Calorie Estimation Method Based On Deep Learning
The process of estimating calories requires two images from top and side, and each image should include the calibration object. This process is shown in Figure 1.
Dataset
We are going to use ECUSTFD (ECUST Food Dataset) that contains 19 kinds of food. There are almost 3000 images. There are almost 1500 pair images. Each pair of images contains a top view and a side view. A 1 CNY coin is used as the calibration object. In the ECUSTFD has volume and mass of food records. If we need more data for our project, we can increase it easily.
Related Works:
References:
[1] W. Zheng, D. F. Mclerran, B. Rolland, X. Zhang, M. Inoue, K. Matsuo, J. He, P. C. Gupta, K. Ramadas, S. Tsugane, Association between body- mass index and risk of death in more than 1 million Asians, New England Journal of Medicine 364 (8) (2011) 719–29.
