|Ariana, Diwan - USDA-FAS|
Submitted to: Experiment Station Bulletins
Publication Type: Experiment Station
Publication Acceptance Date: January 5, 2007
Publication Date: January 11, 2007
Citation: Ariana, D., Lu, R. 2007. Imaging technique for detection of internal defects of pickling cucumbers. Michigan Agricultural Experiment Station Bulletins. p.18-24. Technical Abstract: Pickling cucumbers are susceptible to damage during harvest and postharvest handling and processing. While it is easier to detect external defects, it is difficult to detect internal defects such as bruises and hollow or split cucumbers. Hyperspectral imaging technique under transmittance mode was investigated for detection of internal defect in pickling cucumbers such as carpel suture separation or hollow cucumbers caused by mechanical stress. A hyperspectral transmittance imaging system was developed for acquisition of both spatial and spectral information from pickling cucumbers. Experiments were conducted on 'Journey' and 'Vlaspik' cucumber samples over the six day period after they were subjected to dropping or rolling under load which simulated damage caused by mechanical harvesting and handling systems. Results showed that transmittance values for both defective and normal cucumbers were higher in the near-infrared range (700-950 nm) than that of the visible range (450-700 nm). Transmittance spectra of defective and normal cucumbers were similar in shape but higher in magnitude for the defective cucumbers. Average classification accuracies of 90.2%, 98.7%, and 95.4% were achieved using the partial least squares-discriminant analysis method, whereas accuracies of 89.1%, 94.6%, and 90.5% were achieved using the image segmentation method for Journey, Vlaspik, and the mixed variety model respectively. Hyperspectral transmittance imaging technique has the potential for nondestructive and rapid detection of internal defect in pickling cucumbers.