Convolutional neural networks for food calorie estimation

Leona Ramy (2022) Convolutional neural networks for food calorie estimation. Universiti Malaysia Sabah. (Unpublished)

	Text Convolutional Neural Networks For Food Calorie Estimation.24PAGES.pdf Download (745kB)
	Text Convolutional Neural Networks For Food Calorie Estimation.pdf Restricted to Registered users only Download (2MB)

Abstract

Understanding calorie intake is important as it influences an individual’s health, and the amount of calories in food tells people how much potential energy they contain. In recent years, the food calorie estimation system has become popular due to calorie intake rose in most of the world because there has been a decrease in the quality of diet. However, a problem statement has been highlighted where existing researches did not include mass estimation procedures for their calorie estimation system. The number of calories estimated for each food item was constant. The purpose of this paper is to implement a food calorie system that utilized a mass estimation procedure, to test and evaluate the food calorie estimation to validate its effectiveness and to develop a GUI of the proposed system. The application of Deep Learning has been increasing dramatically in various fields, including food calorie estimation. In this paper, we proposed to build a system that can estimate the calorie content of food using the DL algorithm. Future works of this project is to fulfil all the objectives targeted.

Item Type:	Academic Exercise
Keyword:	Leona Ramy , Leona Ramy
Subjects:	T Technology > TX Home economics > TX1-1110 Home economics > TX341-641 Nutrition. Foods and food supply
Department:	FACULTY > Faculty of Computing and Informatics
Depositing User:	DG MASNIAH AHMAD -
Date Deposited:	18 Jul 2022 11:50
Last Modified:	18 Jul 2022 11:50
URI:	https://eprints.ums.edu.my/id/eprint/33212

Actions (login required)

View Item