NORMA eResearch @NCI Library

Food Image Recognition and Calorie Estimation Using Object Detection Algorithms

Yuganathan, Manoj Kumar (2022) Food Image Recognition and Calorie Estimation Using Object Detection Algorithms. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Obesity has caused a significant increase in the number of people suffering from various health problems in recent years. Excessive calorie consumption is one of the most important factors contributing to obesity. This project proposes a solution for recognizing and identifying different food items, as well as tracking the estimated number of calories consumed for the various food items based on their corresponding food proportions. This study uses the convolutional neural networks and transfer learning algorithms such as VGG, InceptionNet, and ResNet to extract features to estimate calorie consumption. The novelty of this study stems from the fact that this implementation is done by combining data augmentation techniques with applying rapidly decreasing threshold learning rate schedulers to achieve high detection rates of multiple food items on a single food plate. This ensemble technique of performing feature selection, one-hot encoding, data augmentation, and applying the tuned dataset to the InceptionNet V3 model helped to achieve an increased accuracy of almost 87%. In future research, identifying the estimated calorie count using the bounding and applying calibration technique to accurately predict the number of calories consumed by an individual for their daily meal would be implemented.

Item Type: Thesis (Masters)
Uncontrolled Keywords: food recognition; deep learning; calorie consumption; InceptionNet v3; data augmentation; image classification
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Q Science > QP Physiology > Nutrition
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 14 Mar 2023 16:16
Last Modified: 14 Mar 2023 16:16

Actions (login required)

View Item View Item