Food Recognition Tool for Dietary Management

Bhatia, Gautam (2024) Food Recognition Tool for Dietary Management. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (4MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

International students usually face challenges with food when they move abroad, especially if they have specific dietary restrictions or allergies. This research aims to help these students by developing a tool that uses advanced deep learning models such as CLIP (Contrastive Language-Image Pretraining) and MobileNetV2 to recognise food ingredients and allergens. The goal is to assist students in identifying what’s in their food and finding recipes that suit their dietary needs. We compared the performance of both models to the recognition of food. our results show that CLIP performs better than MobileNetV2 and CLIP recognize various food categories. This study contributes to the food computing field by showing the best tool that can address real-life dietary issues faced by international students. This tool was developed to improve food safety and diet management for users. Future work will focus on improving the models and adding more features to make the tool even more useful. This research highlights the use of deep learning models to create solutions for everyday problems.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haque, Rejwanul UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Food Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	07 Aug 2025 14:03
Last Modified:	07 Aug 2025 14:03
URI:	https://norma.ncirl.ie/id/eprint/8467

Actions (login required)

View Item