Classification of Food Objects using Deep Convolutional Neural Network using Transfer learning

Abstract

With the advancements of Deep Learning technologies, its application has broadened into the fields of food classification from image recognition using Convolutional Neural Network, since food ingredient classification is a very important aspect for eating habit recognition and also reducing food waste. This research is an addition to the previous research with a clear illustration for deep learning approaches and how to maximize the classification accuracy to get a more profound framework for food ingredient classification. A fine-tuned model based on the Xception Convolutional Neural Network model trained with transfer learning has been proposed with a promising accuracy of 95.20% which indicates a greater scope of accurately classifying food objects with Xception deep learning model. Higher rate of accuracy opens the door of further research of identifying various new types of food objects through a robust approach. The main contribution in the research is better fine-tuning features of food classification. The dataset used in this research is the Food-101 Dataset containing 101 classes of food object images in the dataset.