Click on “Download PDF” for the PDF version or on the title for the HTML 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.

Near-Infrared (NIR) Hyperspectral Imaging – An Emerging Analytical Tool for Classification of Western Canadian Wheat Classes from Different Locations and Crop Years

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  Paper number  MBSK 10-302,  ASABE/CSBE North Central Intersectional Meeting. (doi: 10.13031/2013.36284) @2010
Authors:   Mahesh Sivakumar, Digvir S Jayas, Jitendra Paliwal, Noel D.G White
Keywords:   Near-infrared hyperspectral imaging, wheat classes, statistical classifier

A platform technology is needed for grain handling facilities in Canada to differentiate wheat classes. Near-infrared (NIR) hyperspectral imaging has recently emerged as a powerful analytical tool for conducting non-destructive quality analyses of agricultural and food samples. This study introduced a new analytical method using a NIR hyperspectral imaging system (960-1700 nm) to identify four western Canadian wheat classes at a uniform moisture level of 13%. Wheat samples used in this study were harvested during 2007, 2008, and 2009 crop years and collected from various growing locations in the prairie provinces (Manitoba, Saskatchewan, and Alberta) of Canada. Bulk samples of wheat were scanned in the 960-1700 nm wavelength region at 10 nm intervals using an Indium Gallium Arsenide (InGaAs) NIR camera. The NIR reflectance intensities of scanned images were calculated and spectral data sets were created. Principal components analysis (PCA) was used to generate scores images and loadings plots. The versatility of the NIR hyperspectral imaging system was demonstrated using NIR reflectance and PCA scores images of samples of different wheat classes. The NIR wavelengths in the region of 1260-1380 nm had the highest factor loadings out of 75 wavelengths in the range of 960-1700 nm based on the first principal component. In statistical classification, the linear and quadratic discriminant classifiers had average classification accuracies of 95.4 and 92.3%, respectively, for identifying wheat classes that included sample variations due to growing locations and crop years. Also, wavelengths in the NIR regions of 1260-1380 and 1650-1700 nm were identified as important in classifying wheat classes, identifying growing locations, and determining crop years. This work showed that hyperspectral imaging technique can be used for rapidly identifying wheat classes.

(Download PDF)    (Export to EndNotes)