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.

Detection of Sprout-Damaged Wheat Using Thermal Imaging

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

Citation:  Applied Engineering in Agriculture. 26(6): 999-1004. (doi: 10.13031/2013.35900) @2010
Authors:   R. Vadivambal, V. Chelladurai, D. S. Jayas, N. D. G. White
Keywords:   Sprout damage, Thermal imaging, Wheat, Statistical classification, Artificial neural network

Sprout-damaged wheat affects the quality of flour resulting in poor qualities of bread, pasta, cookies, or any other product prepared from the wheat. The most common methods to determine sprout-damaged kernels include visual inspection, falling number, and rapid visco analyzer. These methods are either subjective or destructive and are time consuming. We tested the use of thermal imaging to detect sprout damage based on heat radiated by healthy and sprouted wheat kernels. An infrared thermal camera was used to collect images of healthy and sprout-damaged kernels and the images were analyzed using Matlab. Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and Artificial Neural Network (ANN) were used to classify healthy and sprout-damaged kernels. The classification accuracies were: for LDA 88.2% and 98.1%, for QDA 88.7% and 95.1%, and for ANN 99.4% and 91.7%, respectively, for healthy and sprout-damaged kernels. The results have shown that thermal imaging has a potential to determine sprout-damaged wheat kernels from the healthy kernels.

(Download PDF)    (Export to EndNotes)