<![CDATA[This research develops an avocado fruit ripeness classification system using the K-Nearest Neighbor algorithm based on color feature extraction. Data was collected from 150 Mentega variety avocado samples with three ripeness categories: unripe, semi-ripe, and ripe. The classification process involved image preprocessing, extraction of RGB and HSV color components, and implementation of the KNN algorithm. Results showed the highest accuracy of 95.56% at k=9 using Euclidean Distance metric, with Mean R and Mean H components having the strongest correlation to avocado ripeness levels. The system was successfully implemented with a user-friendly graphical interface, enabling automatic classification with a processing time of 1.2 seconds per image. Compared to other classification methods such as Random Forest and SVM, KNN showed the best performance in modeling avocado color features, offering an effective and efficient solution for the Pagar Alam City Agriculture Department in determining avocado fruit ripeness levels.]]>
Copyrights © 2025
