Machine Learning-Based Classification of Fruit Quality: Fresh and Rotten Fruit

Narayanaswamy, Pradeep (2023) Machine Learning-Based Classification of Fruit Quality: Fresh and Rotten Fruit. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Fruits play a crucial role in many industries and are good sources of vitamins and minerals, identification of fresh and rotten fruit in the early stage is important to prevent contamination of other fruits and maintain economic stability during export. Industries depending on manual detection of fruit quality require an advanced classification model to reduce human effort and production time. The recent advancement in the field of deep learning has gained popularity for image-processing applications within the realm of computer vision, the classification of fresh and rotten fruits using deep learning is crucial for commercial and agricultural uses within computer vision. However, there are some challenges such as limitations of the dataset, the diversity of fruit types, and environmental factors. This study addresses challenges faced by earlier researchers by developing a methodology for Fresh and rotten fruit classification. In this research, a total of 18,492 fruit images are used, comprising three types apples, bananas, and oranges which are based on six classes. The machine learning models used for the project are Support Vector Machine (SVM), VGG16 Transfer learning, VGG16 with Edge Detection, and Multi-class classification using VGG16 with Edge Detection. VGG16 with Edge Detection performed better with a high accuracy of 97.96% compared to other models.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Shubnil, Shubham UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Agriculture Industry H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Food Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	18 May 2025 14:26
Last Modified:	18 May 2025 14:26
URI:	https://norma.ncirl.ie/id/eprint/7575

Actions (login required)

View Item