Supervisor

David Gonzalez

Programme

MSc in Data Analytics

Subject

Computer Science

Abstract

This research explores the use of Convolutional Neural Networks (CNNs) for the automated classification and profiling of food products based on publicly sourced data. With the vast array of food products available worldwide and the complexity of labelling regulations, food business operators face challenges in ensuring compliance, while regulators struggle to verify adherence. This study addresses the need for efficient and accurate methods for food classification and eco/nutritional profiling. It begins with a comprehensive literature review on the application of CNNs in food product classification, followed by the collection of a large-scale dataset from Open Food Facts. A CNN architecture tailored for food product classification was developed, focusing on optimising the model's architecture and hyperparameters. Additionally, a user-friendly tool was created using Streamlit, in line with trends in the literature. The research investigates the effectiveness of this integrated approach compared to traditional manual methods. The study highlights the importance of high-quality, extensive datasets and the challenges of recognising visually complex food images. The results indicate that while the CNN models performed well during training, validation accuracy was lower, suggesting potential overfitting. Hyperparameter tuning, focusing on learning rate, optimizer type, and dropout rate, was used to mitigate this. The findings underscore the need for a balance between model complexity and efficiency, with various techniques explored to improve performance. A front-end user interface was developed and is publicly available.

Date of Award

2024

Full Publication Date

2024

Access Rights

open access

Document Type

Capstone Project

Resource Type

thesis

Download

Share

COinS