Detection and classification of areca nuts with machine vision

Abstract

In this study, we present an application of neural networks and image processing techniques for detecting and classifying the quality of areca nuts. Defects with diseases or insects of areca nuts were segmented by a detection line (DL) method. Six geometric features (i.e., the principle axis length, the secondary axis length, axis number, area, perimeter and compactness of the areca nut image), 3 color features (i.e., the mean gray level of an areca nut image on the R, G, and B bands), and defects area were used in the classification procedure. A back-propagation neural network classifier was employed to sort the quality of areca nuts. The methodology presented herein effectively works for classifying areca nuts to an accuracy of 90.9%.