KLASIFIKASI TINGKAT KEMATANGAN BUAH PEPAYA CALIFORNIA DALAM RUANG WARNA HSV (HUE SATURATION VALUE) DENGAN ALGORITMA K-NEAREST NEIGHBORS

Abstract

Papaya fruit is in great demand by people at home and abroad, thus proving that this one agricultural product has become a global need that is in great demand and sought after. To determine the papaya harvest based on the color of the fruit skin, the ripeness of the papaya starts from unripe, unripe (half-ripe) and overripe so that the researchers put forward an idea to answer the problem in determining the ripeness of papaya fruit, which is mostly done manually, still has some weaknesses and requires the process is quite long, has low accuracy and is inconsistent. Based on these problems, a system was created to classify the ripeness level of papaya by utilizing the HSV color features using the K-Nearest Neighbor (K-NN) algorithm. This classification uses image processing by utilizing MATLAB software to create a classification system with three classification classes, namely raw, half cooked and cooked. The classification generated using the K-Nearest Neighbor (K-NN) algorithm shows an accuracy of 86.6667%.