Calorie Estimation from Fast Food Images Using Support Vector Machine

Abstract

Calorie estimation is one of the interesting area of research nowadays. The proposed model focuses on estimation of number of calories in the food item by just taking its image as input. Some image processing operations are performed on the image of food item followed by machine learning technique known as support vector machine(SVM). We took data from different resources [20] [21] [22], compile them to create our own dataset. Augmented dataset is used to train the SVM model and results show an accuracy of 90.66%. The experiments we performed conforms the feasibility of the proposed model.