Supervisor

Sam Weiss

Programme

MSc in Data Analytics

Subject

Computer Science

Abstract

Rice, a staple food for nearly half of the global population, requires accurate classification of its varieties to ensure food quality, support agricultural trade, and enhance yield optimisation. Traditional manual classification methods are time-intensive and error-prone, prompting this study's exploration of unsupervised learning for feature extraction from rice grain images. The research tested classifiers on 75,000 rice samples across five classes, with 15,000 samples per class.

The study's DCGAN-CNN model achieved the highest classification accuracy of 99.67%. However, the PCA-CNN model underperformed, with only 20% accuracy, due to implementation errors. Recommendations for improvement include optimising model parameters such as learning rates, batch sizes, network architecture, and optimisers to enhance performance and reliability.

This research underscores the potential of advanced machine learning techniques for automated and efficient classification of rice varieties, addressing limitations of traditional methods and supporting agricultural advancements.

Date of Award

2024

Full Publication Date

2024

Access Rights

open access

Document Type

Capstone Project

Resource Type

thesis

Share

COinS