Singlewheat Kernel Color Classification Using Neural Networks

An optical radiation measurement system, which measures reflectance spectra from 400 to 2000 nm, was usedto quantify single wheat kernel color. Six classes of wheat were used for this study. A neural network (NN) using inputdata dimension reduction by divergence feature selection and by principal component analysis was used to determinesingle wheat kernel color class. The highest classification accuracy was 98.8% when the divergence feature selectionmethod was used to reduce the number of NN inputs. The highest classification accuracy was 98% when principalcomponent analysis method was used to reduce the number of NN inputs.