Submitted to: American Association of Cereal Chemists Meetings
Publication Type: Other
Publication Acceptance Date: 8/1/2003
Publication Date: 9/28/2003
Citation: Xie, F. Determining vitreous wheat kernels using reflectance and transmittance image analysis. Poster presented at the the American Association of Cereal Chemists Annual Meeting. 2003
Interpretive Summary: ABSTRACT ONLY PUBLICATION IS A POSTER AT A MEETING
Technical Abstract: Vitreousness is an important attribute in assessing the quality of wheat. High vitreousness indicates high protein content, harder, coarser granulation, higher yield of semolina, superior pasta color, improved cooking quality, and sells for a premium. The current method of evaluating vitreousness of samples of wheat is subjective and tedious. The objective of this study was to evaluate an automated machine vision inspection system for detecting wheat vitreousness using reflectance and transmittance images. Two subclasses of durum wheat were investigated in this study, hard and vitreous of amber color (HVAC) durum wheat and not hard and vitreous of amber color (NHVAC). A total of 4907 kernels in the calibration set and 4407 kernels in the validation set were imaged using a Foss Cervitec 1625 Grain Inspector. Classification models were developed with stepwise discriminant analysis and a neural network (ANN). A discriminant model correctly classified 94.9% of HVAC and 91.0% of NHVAC in the calibration set, and 92.4% of HVAC and 92.7% of NHVAC in the validation set. Among all the kernels, mottled kernels were the most difficult to classify. Both reflectance and transmittance images were helpful in classification. In conclusion, the automated vision-based wheat quality inspection system may provide the grain industry with a rapid, objective, and accurate method to determine the vitreousness of durum wheat. This grading method could greatly reduce grain inspector subjectivity and labor and benefit wheat producers, processors, and handlers.