No abstract

Calculating the amount of calories in a given food item is now a common task. We propose a machine-learning-based approach to predict the amount of calories from food images. Our system does not require any input from the user, except from an image of the food item. We take a pragmatic approach to accurately predict the amount of calories in a food item and solve the problem in three phases. First, we identify the type of the food item in the image. Second, we estimate the size of the food item in grams. Finally, by taking into consideration the output of the first two phases, we predict the amount of calories in the photographed food item. All these three phases are based purely on supervised machinelearning. We show that this pipelined approach is very effective in predicting the amount of calories in a food item as compared to baseline approaches which directly predicts the amount of calories from the image.