A Novel Damage Inspection Method Using Fluorescence Imaging Combined with Machine Learning Algorithms Applied to Green Bell Pepper

Abstract

Fluorescence imaging has emerged as a powerful tool for detecting surface damage in fruits, yet its application to vegetables such as green bell peppers remains underexplored. This study investigates the fluorescent characteristics of minor mechanical damage, specifically 5 × 5 mm cuts in the exocarp of green bell peppers, which conventional digital imaging techniques fail to classify accurately. Chlorophyll fluorescence imaging was combined with machine learning algorithms—including logistic regression (LR), artificial neural networks (ANN), random forests (RF), k-nearest neighbors (kNN), and the support vector machine (SVM) to classify damaged and sound fruit. The machine learning models demonstrated a high classification accuracy, with calibration and prediction accuracies exceeding 0.86 and 0.96, respectively, across all algorithms. These results underscore the potential of fluorescence imaging as a non-invasive, rapid, and cheaper method for assessing mechanical damage in green bell peppers, offering valuable applications in quality control and postharvest management.