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.

Identification of Classes and Moisture Contents for Location-specific and Crop year-specific Wheat Samples Using the Near-Infrared (NIR) Hyperspectral Imaging

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

Citation:  Paper number  MBSK 10-404,  ASABE/CSBE North Central Intersectional Meeting. (doi: 10.13031/2013.36288) @2010
Authors:   Mahesh Sivakumar, Digvir S Jayas, Jitendra Paliwal, Noel D.G White
Keywords:   Near-infrared hyperspectral imaging, wheat classes, statistical classifier

Accurate segregation, proper drying, and safe storage can be possible when wheat classes and their moisture levels are properly identified. The potential of using a near infrared (NIR) hyperspectral imaging system to identify four western Canadian wheat classes each at 13, 16, and 19% moisture contents was investigated. Wheat samples harvested during 2007, 2008, and 2009 crop years were collected from various locations in Manitoba, Saskatchewan, and Alberta. An Indium Gallium Arsenide (InGaAs) NIR camera was used to scan bulk samples of wheat in the 960-1700 nm wavelength region at 10 nm intervals. Calculated relative reflectance intensities of the scanned images were used for forming spectral data set. Scores images and loadings plots were generated using the principal component analysis (PCA). In both 16 and 19% moisture content (m.c.) wheat, the highest factor loadings were in the region of 1260-1390 nm out of 75 NIR wavelengths in the 960-1700 nm range. In overall identification of four wheat classes independent growing locations, crop years, and moisture levels, average classification accuracies were of 80.6 and 76.3% for the linear discriminant analysis (LDA) and the quadratic discriminant analysis (QDA), respectively. For both 16 and 19% m.c. wheat, wavelengths in the NIR regions of 1000-1200 and 1260-1390 nm were important in identifying wheat classes independent of growing locations and crop years. This study establishes that NIR hyperspectral imaging study can be used as a comprehensive tool for identifying wheat classes and moisture levels.

(Download PDF)    (Export to EndNotes)