Publication: Tomato ripeness prediction learning based regression models
Loading...
Date
2024-07-01
Authors
Lee Jun Wei
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Accurate assessment of tomato ripeness is crucial for various stakeholders in the tomato value chain. Traditional methods, primarily manual inspection, are often subjective and inconsistent. This study proposes a machine learning regression model to predict tomato ripeness as a continuous percentage. The model utilizes color, texture, and shape features extracted from tomato images. Three regression models—Support Vector Regression (SVR), Random Forest Regression, and XGBoost—were trained and evaluated. The Random Forest model demonstrated the best performance, achieving the lowest mean squared error and highest R-squared value on both validation and test sets. These findings highlight the potential of machine learning in accurate tomato ripeness assessment, offering benefits to the agricultural industry.