Moisture Content Detection of Hot-Air-Dried Lemon Slices Using Hyperspectral Image Feature Fusion

Moisture content (MC) is an important indicator affecting the quality of dried lemon slices. To achieve rapid and non-destructive MC detection, this study developed a lemon slice MC detection model based on the fusion of image texture and spectral features. A total of 240 lemon slices were dried at 80 ∘C, and hyperspectral imaging (HSI) data and reference MC values were collected at different drying times. Competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE) were used to select characteristic wavelengths. Image texture features were extracted using the gray-level co-occurrence matrix (GLCM), and the spectral features and image texture features were concatenated and fused. Kernel principal component analysis (KPCA) was then applied to reduce the dimensionality of the fused feature set. Finally, support vector machine (SVM), general regression neural network (GRNN), and partial least squares (PLS) models were established for MC detection. The results showed that the spectral-feature-based models achieved good predictive performance. The image texture-feature-based models also demonstrated predictive capability, whereas spectral–texture feature fusion further improved prediction accuracy. Among all models, the PLS model based on the spectral–texture fused features achieved the best performance, with a coefficient of determination of prediction (Rp2) of 0.9890 and a root mean square error of prediction (RMSEP) of 0.1916 g/g in the prediction set. These results indicate that HSI combined with spectral–texture feature fusion provides a promising approach for rapid MC detection in lemon slices.