Near infrared hyperspectral imaging and spectral unmixing methods for evaluation of fiber distribution in enriched pasta

Pasta is mostly composed by wheat flour and water. Nevertheless, can be partially replaced fibers to provide extra nutrients in the diet. However, fiber affect technological quality of pasta if not properly distributed. Usually, determinations parameters are destructive time-consuming. The use Near Infrared-Hyperspectral Imaging (NIR-HSI), together with machine learning methods, valuable improve efficiency assessment quality. This work aimed investigate ability NIR-HSI augmented Multivariate Curve Resolution-Alternating Least Squares (MCR-ALS) for evaluation, resolution quantification distribution enriched pasta. Results showed R2V between 0.28 0.89, %LOF < 6%, variance explained over 99%, similarity pure recovered spectra 96% 98% models using control as initial estimates, respectively, demonstrating applicability MCR-ALS identification