Tobacco leaf grade classification using machine learning

Author

Muzemi, Jotham.

Title

Tobacco leaf grade classification using machine learning

Abstract

This research contributes to enhancing the accuracy and reliability of tobacco leaf classification. The developed model provides valuable insights for tobacco farmers and industry stakeholders, facilitating improved grading and quality assessment of tobacco leaves. The findings underscore the potential of machine learning in optimizing tobacco leaf classification, leading to more efficient and standardized practices in the tobacco industry. The implementation of this project using a computer-based application will streamline the grading process, enabling farmers to classify tobacco leaves quickly and accurately. This work builds upon previous research conducted by other scholars, such as the article "Automated Tobacco Leaf Classification Using Machine Learning" (Smith et al., 2020) and the article "Deep Learning Approaches for Tobacco Leaf Grade Classification" (Johnson et al., 2018). By leveraging machine learning techniques, this research advances the field of tobacco leaf classification and contributes to the overall improvement of tobacco grading practices.

Date

June 2024

Publisher

BUSE

Keywords

Tobacco leaf classification,

Grading and quality assessment of tobacco leaves,

Potential of machine learning in optimizing,

Supervisor

Mr. O. Muzurura,