Development of an automatic grading machine for oil palm fresh fruits bunches (FFBs) based on machine vision

► Machine vision is used to automatically grade fresh-fruits bunches of oil palm. ► Stepwise discrimination (Canonical and Mahalanobis functions) to classify groups. ► Adaptive threshold algorithm showed 100% success rate for background removal. ► Group classification of FFBs resulted average success rate of 93.53%. ► Fraction classification, using Euclidean distance analysis showed 88.7% success rate.