Calibration Transfer from Micro NIR Spectrometer to Hyperspectral Imaging: a Case Study on Predicting Soluble Solids Content of Bananito Fruit (Musa acuminata)

Calibration transfer from a handheld micro NIR spectrometer (NIR-point, 939–1602 nm, 6.2 nm) to a desktop hyperspectral imaging (NIR-HSI) for predicting soluble solids content (SSC) of bananito flesh was investigated in the study. Different spectral pre-processing and standardization methods were employed for correcting spectra so as to minimise spectral differences between NIR-point and NIR-HSI. Results show that application of standard normal variate (SNV) reduced spectral differences from 31.49 to 8.96%. The best standardization method was developed based on piecewise direct standardization (PDS) algorithm using ten transfer samples. The developed PLS model yielded a high prediction performance (R2p = 0.922 and RMSEP = 1.451%) for predicting SSC of validation samples using the NIR-point spectra. After SNV and standardization, the model was successfully transferred to NIR-HSI data, giving a comparable prediction accuracy of R2p = 0.925 and RMSEP = 1.592%. The results illustrated the potential of transferring calibration models from a simple and easy-available micro NIR spectrometer to a more expensive and sophisticated hyperspectral imaging system, when the spatial distribution of quality information is required.