The Image Extraction Using the HSV Method to Determine the Maturity Level of Palm Oil Fruit with the k-nearest Neighbor Algorithm

Abstract

The oil palm is one of the monocot oil-producing plants in Indonesia. Sorting errors in oil palm fruit is caused by a sorter error when distinguishing the color of ripe and immature oil palm fruit. In addition to inefficient time, the area of oil palm plantations is also a factor causing the sorter to make mistakes in sorting. This study aims to produce a system that can classify oil palm maturity based on feature extraction of hue, saturation, and value (HSV) color features. The HSV method is used to produce color characteristics from the image of the oil palm fruit. The classification of oil palm fruit maturity is classified using the K-Nearest Neighbor (KNN) algorithm with a dataset of 400 oil palm fruit image data with a data sharing ratio of 70% training data and 30% test data. 280 image data were used as training data which is divided into 140 image data of ripe oil palm fruit 140 image data of immature oil palm fruit and 120 image data of oil palm used as test data which is divided into 60 image data of ripe oil palm and 45 image data unripe palm oil. Based on the result of tests that have been carried out using a confusion matrix with varied k values, namely, 5 and 7, the average accuracy is 94.16%.