DETERMINING VITREOUSNESS OF DURUM WHEAT USING TRANSMITTED AND REFLECTED IMAGES

Abstract

Digital imaging technology has found many applications in the grain industry. In this study, images of durumwheat kernels acquired under three illumination conditions (reflected, side-transmitted, and transmitted) were used to developartificial neural network models to classify durum wheat kernels by their vitreousness. The results showed that the modelstrained using transmitted images provided the best classification for the nonvitreousness class (100% for non-vitreous kernelsand 92.6% for mottled kernels). Results of the study also indicated that using transmitted illumination may greatly reducethe hardware and software requirements for the inspection system, while providing faster and more accurate results for inspectionof vitreousness of durum wheat.