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.

Neural network prediction of wheat classes and moisture contents using near-infrared (NIR) hyperspectral images of bulk samples from different growing locations and crop years

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

Citation:  2011 Louisville, Kentucky, August 7-10, 2011  1110539.(doi:10.13031/2013.37219)
Authors:   Sivakumar Mahesh, Digvir S Jayas, Jitendra Paliwal, Noel D.G White
Keywords:   Near-infrared, hyperspectral imaging, neural network model, wheat

Knowledge of wheat classes and moisture contents not only determines the end use of wheat flour but also helps in developing effective storage systems for wheat. Samples of four classes of wheat (Canada Western Red Spring (CWRS), Canada Western Hard White Spring (CWHWS), Canada Western Soft White Spring (CWSWS), and Canada Prairie Spring Red (CPSR)) were obtained from five-six different locations in Manitoba, Saskatchewan, and Alberta for 2007, 2008, and 2009 crop years and conditioned to moisture contents of 13, 16, and 19%. Near-infrared hyperspectral images were acquired from bulk samples in the 960-1700 nm wavelength region at 10 nm intervals. Pair-wise average classification accuracies of 83.7 and 73.1-83.2% were obtained using a four-layer standard back propagation neural network (BPNN) model for identifying moisture contents and for discriminating wheat classes at each moisture level, respectively. Key wavelengths were identified based on their highest contributions towards classification. This work showed that NIR hyperspectral imaging can be used as a potential nondestructive tool for classifying moisture-specific wheat classes.

(Download PDF)    (Export to EndNotes)