Skip to main content
ARS Home » Pacific West Area » Albany, California » Western Regional Research Center » Healthy Processed Foods Research » Research » Publications at this Location » Publication #314009

Title: Detection of fruit-fly infestation in olives using X-ray imaging: Algorithm development and prospects

Author
item Haff, Ronald - Ron
item Jackson, Eric
item MOSCETTI, ROBERTO - University Of Tuscia
item MASSANTINI, RICCARDO - University Of Tuscia

Submitted to: American Journal of Agricultural Science and Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 11/13/2015
Publication Date: 12/12/2015
Citation: Haff, R.P., Jackson, E.S., Moscetti, R., Massantini, R. 2015. Detection of fruit-fly infestation in olives using X-ray imaging: Algorithm development and prospects. American Journal of Agricultural Science and Technology. 4(1):1-8.

Interpretive Summary: A computer program was developed to automatically detect olive fruit fly infestations in x-ray images of olives. A total of 249 olives with various degrees of infestation and 161 non-infested olives were tested. Each olive was x-rayed on film and digital images were acquired with a film scanner at a resolution of 59 pixels per cm. Features extracted from the images were tested by the program and error rates for detection of the infestations obtained. Feature selection involved pixel intensity values and pixel derivative values at each pixel location in the image. The ability of the algorithm to differentiate infested and non-infested olives was tested. Internal damage to the olive was a factor in detection; with slight damage correctly identified 50% of the time and severe damage correctly identified 86% of the time. Non-infested olives were correctly identified with 90% accuracy.

Technical Abstract: An algorithm using a Bayesian classifier was developed to automatically detect olive fruit fly infestations in x-ray images of olives. The data set consisted of 249 olives with various degrees of infestation and 161 non-infested olives. Each olive was x-rayed on film and digital images were acquired with a film scanner at a resolution of 59 pixels per cm. Features extracted from the images were submitted to the classification algorithm and error rates for detection of the infestations obtained. Feature selection involved pixel intensity values and pixel derivative values at each pixel location in the image. The ability of the algorithm to differentiate infested and non-infested olives was tested. Internal damage to the olive was a factor in detection; with slight damage correctly identified 50% of the time and severe damage correctly identified 86% of the time. Non-infested olives were correctly identified with 90% accuracy.