Early detection of beef-quality indicators using hyperspectral imaging combined with pixel-based segmentation method corresponding to fat and protein region

This study investigated the utilization of hyperspectral imaging (HSI) in conjunction with pixel-based segmentation to predict the thiobarbituric acid-reactive substances (TBARS) and volatile basic nitrogen (VBN) content in beef. Hyperspectral images were acquired in the visible near-infrared (VIS-NIR) and shortwave infrared (SWIR) ranges to examine temporal alterations in the fat and protein regions. A partial least squares discriminant analysis (PLS-DA) model was employed to segment fat and protein pixels, followed by a partial least squares regression (PLSR) model to predict the TBARS and VBN content from the segmented spectra. The SWIR range yielded the most accurate predictions, with an R p 2 of 0.899 for the early freshness indicators. Utilizing hyperspectral information from individual fat and protein pixels, rather than modeling the entire beef image, resulted in enhanced prediction accuracy for R p 2 of TBARS (0.814–0.899) and VBN (0.394–0.532) in the early stages of storage. These findings elucidate the potential of HSI with pixel-based segmentation as a nondestructive and real-time methodology for precise monitoring of beef freshness. • Hyperspectral imaging (HSI) combined with pixel-based segmentation effectively predicts TBARS and VBN content in beef. • The PLS-DA model effectively differentiates fat and protein pixels, improving the prediction accuracy for TBARS and VBN. • The SWIR range offers better prediction accuracy for early detection of freshness indicators than the VIS-NIR range. • Utilizing hyperspectral data from segmented fat and protein pixels enhances predictive performance compared to using the entire beef image. • This nondestructive, real-time monitoring method shows promise for evaluating beef freshness and could be applied to other meats in future studies.