Oil palm fresh fruit bunch ripeness classification using artificial neural network

This paper presents the ripeness classification of oil palm fresh fruit bunch (FFB) using artificial neural network (ANN). ANN method was used to automate the decision of grading oil plam FFBs, replacing the manual human grading method. A total of 80 oil palm FFB samples from unripe, underripe, ripe and overripe categories were collected. Images of oil palm FFB were obtained using a color digital camera and their color was analyzed using digital image processing techniques. Then the color features were extracted from those images. These features were used as the input parameters for ANN learning. The performance of ANN was measured by testing the network with independent test data. Results show that ANN was able to generalize four ripeness categories of oil palm FFB.