Exploring Food Detection using CNNs

TL;DR

This paper reviews recent advances in food detection using CNNs and introduces an optimized model combining GoogLeNet, PCA, and SVM that surpasses current state-of-the-art results on public datasets.

Contribution

It presents a novel food detection model integrating GoogLeNet, PCA, and SVM, achieving superior performance over existing methods.

Findings

Outperforms state-of-the-art on two datasets

Effective combination of CNN, PCA, and SVM

Provides an overview of recent food detection advances

Abstract

One of the most common critical factors directly related to the cause of a chronic disease is unhealthy diet consumption. In this sense, building an automatic system for food analysis could allow a better understanding of the nutritional information with respect to the food eaten and thus it could help in taking corrective actions in order to consume a better diet. The Computer Vision community has focused its efforts on several areas involved in the visual food analysis such as: food detection, food recognition, food localization, portion estimation, among others. For food detection, the best results evidenced in the state of the art were obtained using Convolutional Neural Network. However, the results of all these different approaches were gotten on different datasets and therefore are not directly comparable. This article proposes an overview of the last advances on food detection and an optimal model based on GoogLeNet Convolutional Neural Network method, principal component analysis, and a support vector machine that outperforms the state of the art on two public food/non-food datasets.