Page Banner

United States Department of Agriculture

Agricultural Research Service

Research Project: Quality Based Inspection and Sorting of Specialty Crops Using Imaging and Physical Methods

Location: Healthy Processed Foods Research

Title: One dimensional Linescan x-ray detection of pits in fresh cherries

Authors
item Haff, Ronald
item Pearson, Thomas
item Jackson, Eric

Submitted to: American Journal of Agricultural Science and Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: January 27, 2013
Publication Date: February 9, 2013
Citation: Haff, R.P., Pearson, T.C., Jackson, E.S. 2013. One dimensional Linescan x-ray detection of pits in fresh cherries. American Journal of Agricultural Science and Technology. 1:18-26.

Interpretive Summary: The presence of pits in processed cherries is a concern for both processors and consumers, in many cases causing injury and potential lawsuits. While machines used for pitting cherries are extremely efficient, if one or more plungers in a pitting head become misaligned, a large number of pits may pass before corrective action is taken. While x-ray imaging has the potential to detect pits, traditional commercially available equipment is expensive and bulky, and implementation on the processing line is cumbersome. An inspection system using a linear array of x-ray detectors whose outputs are combined to produce a one dimensional signal would be simpler, faster, and more economical. The data collection process is then reduced from a two dimensional image to a much simpler one dimensional signal, resulting in faster and simpler processing and classification. A computer program was developed for use in such a system that correctly identified 97.3% of pitted and 94% of unpitted cherries, with a total error rate of 3.5%. When the algorithm was adjusted to maximize removal of pitted fruit, 100% of pitted cherries were detected with a total error rate of 8.5 percent. If sample orientation is controlled after pitting, total error is reduced to 1%.

Technical Abstract: The presence of pits in processed cherries is a concern for both processors and consumers, in many cases causing injury and potential lawsuits. While machines used for pitting cherries are extremely efficient, if one or more plungers in a pitting head become misaligned, a large number of pits may pass before corrective action is taken. While x-ray imaging has the potential to detect pits, traditional commercially available equipment is expensive and bulky, and implementation on the processing line is cumbersome. An x-ray inspection system using an array of photodiode based x-ray detectors in a linescan configuration whose outputs are combined to produce a one dimensional signal would be simpler, faster, and more economical. The data collection process is then reduced from a two dimensional image to a much simpler one dimensional signal, resulting in faster and simpler processing and classification. An algorithm designed to differentiate unpitted from pitted cherries for such a system yielded recognition rates of 97.3% for the pitted and 94% for the unpitted cherries, with a total error rate of 3.5%. When the algorithm was adjusted to maximize removal of pitted fruit, 100% of pitted cherries were detected with a total error rate of 8.5 percent. If sample orientation is controlled after pitting, total error is reduced to 1%.

Last Modified: 7/27/2014
Footer Content Back to Top of Page