Food Image Recognition by Using Convolutional Neural Networks (CNNs)

TL;DR

This paper compares traditional and CNN-based methods for food image recognition, demonstrating CNN's superior accuracy and the benefits of data augmentation in improving model performance.

Contribution

It introduces a small-scale food image dataset and shows that CNNs outperform traditional models, with data augmentation significantly enhancing accuracy.

Findings

CNN achieved 74% accuracy, outperforming BoF+SVM.

Data augmentation increased accuracy to over 90%.

Overfitting was mitigated through data augmentation techniques.

Abstract

Food image recognition is one of the promising applications of visual object recognition in computer vision. In this study, a small-scale dataset consisting of 5822 images of ten categories and a five-layer CNN was constructed to recognize these images. The bag-of-features (BoF) model coupled with support vector machine (SVM) was first evaluated for image classification, resulting in an overall accuracy of 56%; while the CNN model performed much better with an overall accuracy of 74%. Data augmentation techniques based on geometric transformation were applied to increase the size of training images, which achieved a significantly improved accuracy of more than 90% while preventing the overfitting issue that occurred to the CNN based on raw training data. Further improvements can be expected by collecting more images and optimizing the network architecture and hyper-parameters.