Mango Ripeness Detection Based on Color Features Using Digital Image Processing

Abstract

The classification of mango Golek ripeness is crucial for ensuring product quality and its economic value, especially in industrial applications. Manual and subjective ripeness determination often leads to inconsistency, resulting in decreased harvest quality and market value. This study aims to classify the ripeness of Golek mangoes into three categories: unripe, semi-ripe, and ripe, using digital image processing based on HSV and LAB color features combined with the K-Nearest Neighbor (KNN) algorithm. The dataset consists of 300 images, split into 80% training data and 20% testing data. The proposed method includes image acquisition, preprocessing, segmentation, morphological operations, feature extraction, and classification. The results show that the combination of HSV and LAB color features is effective in distinguishing ripeness levels, with an accuracy of 81.67% on the testing data and an average precision, recall, and F1-Score of 82%. Consistent color patterns in the unripe and semi-ripe categories enhance accuracy, while fluctuations in color intensity in the ripe category pose challenges. This approach shows potential for implementation in automatic sorting systems in industry.