Differentiation of alfalfa and sweet clover seeds via multispectral imaging

It is hard to remove sweet clover seeds from alfalfa seed lots by conventional methods, affecting the purity of seed lots and resulting losses in for alfalfa hay production as well as seed yield. However, the discrimination of sweet clover seed contaminates in alfalfa seed lots is difficult without special training. In this study, multispectral imaging with object-wise multivariate image analysis was evaluated for its potential to separate sweet clover and alfalfa seeds. Principal component analysis (PCA), linear discrimination analysis (LDA), partial least squares discriminant analysis (PLSDA), AdaBoost and support vector machine (SVM) methods were applied to classify seeds of sweet clover and alfalfa according to their morphological features and spectral traits or a combination thereof. The results showed that an excellent classification could be achieved based on a combination of morphological features and spectral data in a tested data set. Seed classification accuracy was up to 99.58% in a validation set with the LDA model, which was better than the PLSDA (68.19%), AdaBoost (96.95%) and SVM (98.47%) models. Thus, multispectral imaging together with chemometric multivariate analysis is a promising technique to identify sweet clover seeds in alfalfa seed lots with high efficiency.