AUTOMATED SORTING OF PISTACHIO NUTS WITH CLOSED SHELLS

Abstract

An automated machine vision system was developed to identify and remove pistachio nuts with closed shellsfrom processing streams. The system includes a novel material handling system to feed nuts to linescan cameras withouttumbling. The camera output signals are input to digital signal processing boards which extract image featurescharacteristic of closed and open shell pistachios. The classification accuracy of this machine vision system forseparating open shell from closed shell nuts is approximately 95%. The system has a throughput rate of approximately40 nuts per second and cost of about $15,000 per channel. This throughput and cost is comparable to color sorters usedto remove other pistachio defects. Currently, closed shell pistachio nuts are removed by mechanical devices. Thesedevices also have a classification accuracy of about 95% but damage kernels in open shell pistachios by pricking themwith a needle. The needle hole can give the appearance of an insect tunnel and cause rejection by the consumer. Thenewly developed machine vision system is a non-invasive inspection method.