Dual energy X-ray image analysis for classifying vitreous kernels in durum wheat

Dual energy X-ray imaging technique makes it possible to determine the make-up of a scanned object by exploiting differences in how the scanned material interacts with X-rays at different energies. The potential of classifying vitreousness in durum wheat using dual energy X-ray images is determined in this study. Durum wheat kernels at 12% moisture content were used as samples for this study. Algorithms were developed for the logarithmic subtraction of images and for feature extraction. Histogram groups and total gray values were extracted from the dual energy subtracted images. Statistical and neural network classifiers were used for identifying vitreous and non-vitreous kernels from the sample images. Neural network classifiers correctly classified vitreous and non-vitreous kernels with 96 and 98% accuracies, respectively. The correct classification accuracies using statistical classifiers were 89 and 97%, respectively for vitreous and non-vitreous kernels. Dual energy X-ray imaging is an effective method for determining wheat hardness in durum kernels.