Improving SSC detection accuracy of cherry tomatoes by feature synergy and complementary spectral bands combination

Abstract

The visible/near-infrared (VIS/NIR) spectroscopy technique has been extensively employed for the non-destructive detection of soluble solids content (SSC) in fruit. However, some existing algorithms and modeling optimization methods for improving the detection accuracy of SSC may be applicable to specific conditions and not universal. To break through this bottleneck problem, we propose a potentially universal strategy based on feature synergy and spectral bands combination of multiple detection modes. Firstly, compared with the commonly used halogen lamp, the xenon lamp was utilized to cover the ultraviolet (UV) range and match the characteristic information of different sugars (glucose, fructose, and sucrose). Furthermore, the spectral fusion method was employed to combine the reflectance and transmittance spectra to improve the cherry tomatoes SSC prediction accuracy with comprehensive data in the UV/VIS/NIR region. Finally, the best results were achieved by the partial least square regression (PLSR) model with spectral bands fusion, yielding the results of R2p, RMSEP, and RPD as 0.9653, 0.1998%, and 5.31, respectively. The same conclusion can also be verified when predicting the SSC in strawberries. Overall, this strategy is potentially universal to improve the prediction accuracy of SSC in fruit by matching light source spectra with characteristic absorption, as well as utilizing comprehensive spectral information in the 200–1100 nm range, providing valuable insights for the practical application of nondestructive detection of fruit internal quality.