An instrumental system for cereal grain classification using digital image analysis

Abstract

A digital image processing system is described to facilitate objective inspection and classification of cereal grains. Digitized images of whole grain samples of hard red spring wheat, barley, rye and oats were obtained using a charge-coupled device (CCD) video camera interfaced to a custom-built data-acquisition system. Computer programs were written in assembly language for acquisition and preliminary processing of data from the CCD camera. FORTRAN77 programs were developed for image segmentation and feature extraction. Computed grain features include kernel length, width, area, aspect and thinness ratios, contour length and normalized central moments. Size and shape parameters were evaluated with regard to discrimination ability by stepwise discriminant analysis. Canonical discriminant analysis was applied to visualize cereal class differences and a linear discriminant model was derived. Approximately 1% of over 1100 kernels tested were incorrectly classified among wheat, oats, barley and rye in a four-way admixture. The feasibility of the methodology for instrumental determination of foreign material (‘Besatz’) in grain grading is discussed.