AN INTELLIGENT-BASED MECHATRONICS SYSTEM FOR GRADING THE IRANIAN'S EXPORT PISTACHIO NUTS INTO HULLED AND NON-HULLED GROUPS

This paper presents an intelligent based system for grading hulled and non-hulled pistachio nuts. The first step in the pistachio nuts preparation process is to hull and to peel the picked crops. In pistachio preparation terminals, the manual separation of hulled pistachios from those without hull, increases price and contamination and decreases the quality. The proposed research introduces an automatic system based on image processing technique to enhance the accuracy in detecting the hulled and non-hulled pistachio nuts. Three ordinary classifiers including: Multilayer Feed forward Neural Network (MFNN), Radial Basis Function Neural Network (RBFNN) and Support Vector Machine (SVM) are then applied to select the best classifier for pistachio nuts process. To evaluate the performance of the system 200 pistachio nuts from four native Iranian pistachio nuts varieties are used. Each variety consists of 100 hulled and 100 non-hulled nuts. Experimental results show an accuracy of 95% and average time period of about 0.02 second for the best selection of the system.

Mechatronics System, Image Processing, Machine Vision, Pistachio, Artificial Neural Networks, Classification