Fit2Calorie

The presented system recognizes the meal from a single image, and then predicts its calories. The
User who wants to use this system clicks or uploads a picture of the meal and the system gets back
to him with its calorific value. In this case, we use the 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 look up the corresponding nutritional facts. We apply this method to a new
dataset of images, using an MLP-based classifier. The challenging facts to be considered in this is
the estimation of the size of the foods, and their labels. This requires solving segmentation and
depth/volume estimation from a single image where we use a neural network-based approach.