Submitted to: Applied Engineering in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: November 1, 1999
Publication Date: January 1, 2000
Citation: Pearson, T.C., Toyofuku, N. 2000. Automated sorting of pistachio nuts with closed shells. Applied Engineering in Agriculture. 16(1):91-94. Interpretive Summary: Pistachio nuts with closed shells have low consumer acceptance because they are difficult to open and may contain immature kernels. Closed shell nuts are currently separated from open shell product by mechanical devices that can damage the kernel of open shell nuts by "pricking" them with a needle. The hole created by the needle can give the appearance of an insect tunnel, ,leading to rejection by the consumer. Furthermore, the mechanical systems have a very high maintenance cost, approximately $8,000 every two years. The development of a prototype machine vision system to separate open shell from closed shell nuts is discussed. This system is able to sort nuts at a rate of 40 nuts per second and has a classification accuracy comparable to the mechanical sorters, about 95%. The cost of these image sorting machines is about $15,000 each with very low maintenance costs. Also, the machine vision system does not damage the kernel of open shell nuts.
Technical Abstract: An automated machine vision system was developed to identify and remove pistachio nuts with closed shells from processing streams. Currently, closed shell pistachio nuts are removed by mechanical devices. These devices damage kernels in open shell pistachios by "pricking" them with a needle and have maintenance costs of approximately $8,000 every two years. The needle hole can give the appearance of an insect tunnel and cause rejection by the consumer. The machine vision system includes a novel material handling system to feed nuts to linescan cameras without tumbling the nuts. The camera output signals are input to digital signal processing boards which extract image features characteristic of closed and open shell pistachios. The classification accuracy of this machine vision system is comparable to the mechanical sorters, approximately 95%. The system has a throughput rate of approximately 40 nuts per second and a cost of about $15,000 per channel with minimal maintenance costs. The newly developed machine vision system does not damage the kernels as they are inspected.