Measurement of hard vitreous kernels in durum wheat by machine vision

An imaging method that detects nonvitreous regions in sound kernels of durum wheat at high speed is described. Kernels are analyzed simultaneously for individual vitreousness and individual kernel size and shape are measured concurrently. The measurement of 500 kernels per sample is adequate for highly reproducible results. Significant agreement was found between inspector-determined hard vitreous kernel percentages (HVK) and machine-determined HVK scores for export cargo samples of Canadian Western Amber Durum (CWAD), with differences between the two methods of typically +/-3%. For railcar samples of CWAD taken on delivery to the terminal, agreement between inspector-determined and machine-determined HVK scores were more variable. The variability between the two methods generally increased as the HVK score of the sample became lower. For inspector-determined HVK scores of <50%, difference between inspector and machine HVK scores for some samples was substantial. Such large differences are partially attributable to the way in which weathered kernels are assessed. Weather-damaged kernels were frequently classified as nonvitreous by the machine system due to disruption of the enveloping tissues, whereas inspector evaluations often classify weather-damaged kernels as vitreous. The speed, accuracy, and reproducibility of the machine methodology gives it enormous potential as a replacement for visual inspection of CWAD for HVK in Canadian grain terminals.