Page Banner

United States Department of Agriculture

Agricultural Research Service

Research Project: SORTING AGRICULTURAL MATERIALS FOR DEFECTS USING IMAGING AND PHYSICAL METHODS Title: Spectral Band Selection for Optical Sorting of Pistachio Nut Defects

Authors
item Haff, Ronald
item Pearson, Thomas

Submitted to: Transactions of the ASABE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: June 1, 2006
Publication Date: August 15, 2006
Citation: Haff, R.P., Pearson, T.C. 2006. Spectral Band Selection for Optical Sorting of Pistachio Nut Defects. Transactions of the ASABE. 49(4): 1105-1113

Interpretive Summary: Pistachio plants use sorting machines to remove defects and contaminants from the product, as well as to sort the product into different categories. Many of these sorting machines use Near Infrared (NIR) Spectroscopy to separate the product into the appropriate categories. This is accomplished by using beam splitting mirrors and band pass filters to reduce the full spectrum light source to one or two particular frequencies, and the intensity of light detected at these particular frequencies provides the basis for sorting. The ability of the machines to sort accurately therefore depends on the selection of the appropriate frequencies, and therefore the use of the proper mirrors and filters. This study describes a technique for finding the frequencies that give the best sorting accuracy for any particular category of product. The technique was tested on a commercially available sorting machine given the task of sorting “small inshell” (small nuts with the shell intact) and shell halves from the stream of nuts with no shells (“kernels”). Results were 1.2% false negative (bad product accepted) for small inshell and 1.8% false negative for half shells with 0.15% false positive (good product rejected) vs. 2.4%, 1.7%, and 0.7% respectively using the spectral bands recommended by the manufacturer. Given the success of this technique in pistachio sorting experiments, it is believed that it could be applied to any commodity sorted using commercially available, dual wavelength, NIR sorting devices.

Technical Abstract: A technique using near infrared spectroscopy (NIR) was developed for selecting the optimum spectral bands for use in dual wavelength sorting machines commonly found in food processing plants. A variation of a nearest neighbor classification scheme selected the two optimum spectral bands given NIR spectra from both sides of an object. The optimum bands were determined for two cases; when both sides contain the defect of interest (AND logic) or when the defect appears on a single side (OR logic). A commercially available sorting machine was used to compare the sorting accuracy using the spectral bands determined with this technique to that using bands recommended by the manufacturer. The product stream tested was the removal of “small inshell” (small nuts with the shell intact) and shell halves from the stream of nuts with no shells (“kernels”). Results for the selected spectral bands averaged 1.2% false negative (fn) for small inshell and 1.8% fn for half shells with 0.15% false positive (fp) vs. 2.4%, 1.7%, and 0.7% respectively using the spectral bands recommended by the manufacturer. Optimum spectral bands were also determined and reported for a variety of other defects and unwanted materials commonly sorted in the pistachio processing plant including adhering hull, stained, sticks, mold, insect damage and/or webbing, and black spots. Given the success of this technique in pistachio sorting experiments, it is believed that it could be applied to any commodity sorted using commercially available, dual wavelength, NIR sorting devices.

Last Modified: 10/25/2014
Footer Content Back to Top of Page