Abstract
Laver (Pyropia spp.) is a major seaweed that is cultivated and consumed globally. Although quality standards for laver products have been established, traditional physicochemical analyses and sensory evaluations have notable drawbacks regarding rapid-quality inspection. Not all relevant physicochemical quality indices, such as texture, are typically evaluated. Therefore, in this study, we investigated the use of hyperspectral imaging to rapidly, accurately, and objectively determine the quality of dried laver. Hyperspectral images of 25 dried laver samples were captured in the short-wave infrared range from 980 to 2576 nm to assess their moisture, protein content, cutting stress, and other key quality indicators. Spectral signatures were analyzed using partial least-squares discriminant analysis (PLS-DA) to correlate the spectral data with three primary quality index values. The performance of PLS-DA was compared with that of the variable importance in projection score and nonlinear regression analysis methods. The comprehensive quality grading model demonstrated accuracies ranging from 96 to 100%, R(2) values from 75 to 92%, and root-mean-square errors from 0.14 to 0.25. These results suggest that the PLS-DA regression model shows great potential for the multivariate analysis of hyperspectral images, serving as an effective quality grading system for dried laver.