Classification of oil palm fresh fruit bunches utilising multiband optical sensors

Abstract

Indonesia, as the world's largest palm oil producer, faces the challenge of improving crude palm oil (CPO) production efficiency through the classification of fresh fruit bunch (FFB) maturity levels. This study aims to develop a FFB classification system using multiband optical sensors based on visible light and near-infrared spectra. A total of 191 FFB samples were classified into two categories, namely ripe and unripe, using the reflectance of the NIR spectrum. Results show that the combination of visible and NIR spectra at a wavelength of 660 nm has high accuracy in detecting oil content in FFB. The classification model based on oil content showed an accuracy of 66.7%, better than the visual inspection model (52.1%). This study shows the great potential of optical sensor technology to improve the efficiency and quality of the palm oil industry in Indonesia.