Palm oil fresh fruit bunch ripeness grading identification using color features

This research investigates the ripeness grading identification of the palm oil FFB using colorfeatures that are color histogram, color moment and color correlogram. Palm is harvestedduring the optimum stage of its ripeness since it improves the FFB oil quality and quantity.Harvesting wrong bunches decreases the oil extraction rate of the palm. A preliminaryresearch on the palm oil FFB grading identification is conducted. Each ripeness stage has itsown unique color. A study on color features is investigated.A new dataset of images of FFB isconstructed. A comparative study between Support Vector Machine (SVM) and Naïve Bayesclassifiers has been performed using the values of color histogram, color moment and colorcorrelogram. The results of the experiments indicate that color moment with SVM produce ahigher palm oil FFB ripeness grading identification accuracy compared to color histogramand color correlogram.Keywords: color features, fresh fruit bunch (FFB), Naïve Bayes, ripeness stage, supportvector machine.