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 #286740
Title: Automatic image analysis and spot classification for detection of fruit fly infestation in hyperspectral images of mangoes

Author
item Haff, Ronald - Ron
item SARANWONG, SIRINNAPA - National Food Research Institute - Japan
item THANAPASE, WARUNEE - Kasetsart University
item JANHIRAN, ATHIT - Kasetsart University
item KASEMSUMRAN, SUMAPORN - Kasetsart University
item KAWANO, SUMIO - National Food Research Institute - Japan

Submitted to: Postharvest Biology and Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/3/2013
Publication Date: 7/7/2013
Citation: Haff, R.P., Saranwong, S., Thanapase, W., Janhiran, A., Kasemsumran, S., Kawano, S. 2013. Automatic image analysis and spot classification for detection of fruit fly infestation in hyperspectral images of mangoes. Postharvest Biology and Technology. 86:23-28.

Interpretive Summary: Interpretive Summary: An computer program has been developed to identify spots generated in Near Infrared based images of mangoes infested with fruit fly larvae. The algorithm incorporates a number of standard image processing techniques to identify locations of infestations in the images. Each of four image processing steps involves adjustable parameters which were iteratively tested to find the optimal combination for detection in terms of false positive and false negative results. For algorithm parameters selected to minimize false negative results, a false negative error rate of 1.0% was achieved with 11.1% false positive error and 6.0% overall error in heavily infested samples. For the same sample set, the lowest overall error rate achieved was 2.0%, with 1.0% false positive and 3.0% false negative. For samples with lower infestation rates, the error rates were much higher, the lowest overall error being 12.3%. This therefore demonstrates the feasibility of Near Infrared based imaging for fruit fly detection while highlighting the need for technology with improved resolution and signal to noise ratio to allow detection of single larvae.

Technical Abstract: An algorithm has been developed to identify spots generated in hyperspectral images of mangoes infested with fruit fly larvae. The algorithm incorporates background removal, application of a Gaussian blur, thresholding, and particle count analysis to identify locations of infestations. Each of the four algorithm steps involves adjustable parameters which were iteratively tested to find the optimal combination for detection in terms of false positive and false negative results. For algorithm parameters selected to minimize false negative results, a false negative error rate of 1.0% was achieved with 11.1% false positive error and 6.0% overall error in heavily infested samples. For the same sample set, the lowest overall error rate achieved was 2.0%, with 1.0% false positive and 3.0% false negative. For samples with lower infestation rates, the error rates were much higher, the lowest overall error being 12.3%. This therefore demonstrates the feasibility of hyperspectral imaging for fruit fly detection while highlighting the need for technology with improved resolution and signal to noise ratio to allow detection of single larvae.