Discrimination of varieties of rice using near infrared spectral by PCA and MDA model

In this research, a new method for discrimination of varieties of rice by means of near infrared spectroscopy (NIRS) was developed. First, the characteristic spectrums of rice were got through principal component analysis (PCA). The result of the analysis suggests that the reliabilities of first 4 principal components are more than 99.338%. The 2-dimontional plot was drawn with first and second principal components, which indicates that it is a good clustering analysis for classification varieties of rice. The several variables compressed by PCA were used as inputs of multiple discriminant analysis (MDA). 150 samples from three varieties were selected randomly, then they were used to build discriminated model, 30 unknown samples were predicted by this model, the recognition rate is 100%.