Growth simulation and discrimination of five fungi from rice storage using hyperspectral reflectance imaging technique

Hyperspectral imaging system( HIS) was used in this study to acquire the spectral responses of fungi( Asp.Niger,Asp.Oryzae,Asp.Versicolor,Asp.Nidulans,P.Citrinum) inoculated on potato dextrose agar plates.Two methods for calculating HIS parameters,including the spectral response values of the wave peak at 709 nm,and the scores of the first principal component of the whole spectral range( 400 ~1000 nm) using principal component analysis( PCA),were used to simulate the growth of fungi. The results of Gompertz model revealed that the coefficients of determination( R2) of five fungi based on the score of the first principal component were 0.1781~0.9501,while R2 with 0.9095 ~ 0.9679 based on the spectral response value of the wave peak at 709 nm showed better aptitude than the previous method.In addition,fungi species can be discriminated by PCA and partial least squares discrimination analysis( PLSDA) using the spectral information of the full wavelength range. All the classification accuracy of the test group and training group sets by PLSDA models for four fungi( Asp.Niger,Asp.Oryzae,Asp. Nidulans,P.Citrinum) cultured for 48 h were 100%,with the exception of 33.33% for the classification accuracy of training group of Asp.Versicolor.This paper supplied a new technique and useful information for further study into detecting rice spoilage caused by fungi based on HIS.