The authentication of fish maw is of considerable importance for preventing product substitution and protecting market confidence in high-value aquatic foods. This study developed a rapid and nondestructive authentication strategy by combining hyperspectral imaging (HSI) with wavelength selection and a Kolmogorov–Arnold Network (KAN) to discriminate 10 commercially representative fish maw varieties. Hyperspectral datasets were collected in the visible and near-infrared (VNIR, 400–1000 nm) and short-wave infrared (SWIR, 900–1700 nm) regions. To improve spectral quality and model robustness, four preprocessing methods (SG, SG−MeanNor, SG−DT, and SG−SNV) were evaluated, followed by the construction of PLS-DA, SVM, MLP, CNN, and KAN models. Feature wavelengths were subsequently selected separately from the VNIR and SWIR spectra using CARS, iVISSA, and SPA to establish reduced-variable authentication models. The results showed that SG-DT achieved the best overall preprocessing effect, confirming its ability to reduce spectral noise and baseline variation. In addition, SWIR-based models consistently outperformed VNIR-based models, suggesting that compositional information captured in the SWIR region played an important role in fish maw authentication. Among all tested models, the SWIR@SG-DT-SPA-KAN model exhibited the best performance, achieving 98.67% accuracy, 98.75% precision, 98.67% recall, and 98.64% F1-score using only 16 SPA-selected wavelengths from the SG-DT-preprocessed SWIR spectra. This study demonstrates that HSI coupled with feature wavelength and KAN modeling can provide an accurate and efficient tool for fish maw authentication. More importantly, the reduced-wavelength model offers practical potential for developing fast and cost-effective multispectral systems for authenticity screening in the aquatic food market.
Xia et al. (Mon,) studied this question.