Click on the underlined title to access the document or go back to the Search Results screen to download the PDF version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.
Wavebands selection for a hyperspectral reflectance and transmittance imaging system for quality evaluation of pickling cucumbers
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.orgCitation: 2009 Reno, Nevada, June 21 - June 24, 2009 096872.
Authors: Diwan Prima Ariana, Renfu Lu
Keywords: Hyperspectral imaging, Transmittance, Reflectance, Near-infrared, Nondestructive, Wavelength selection, Cucumbers, Internal Defect, Quality.
Hyperspectral imaging under transmittance mode has shown promising results for detecting internal defect in pickling cucumbers, however, the technique still cannot meet the online speed requirement because it needs to acquire and process a large amount of image data. This study was conducted on selecting important wavebands as a basis for developing an online imaging system to detect internal defect in pickling cucumbers. 'Journey' pickling cucumbers were subjected to mechanical stress to induce damage in the seed cavity. Hyperspectral transmittance/reflectance images were acquired from normal and defective cucumbers using a prototype hyperspectral reflectance (400-740 nm)/ transmittance (740-1,000 nm) imaging system. Optimal wavelengths were determined by correlation analysis on single, ratio, and difference of two pairs of wavelengths. A global image thresholding method was applied to the selected spectral images to identify defective cucumbers. Images at 740 nm were the best for single waveband classification with an overall accuracy of 87%. For ratios of two wavebands, 925 nm and 940 nm resulted in an overall classification accuracy of 85%, and for differences of two wavebands, images at 745 nm and 850 nm were the best with a classification accuracy of 91%. All the selected wavebands were in the near infrared region, which is more effective for internal defect detection compared to the visible region.