Abstract
Abstract
Eggshell surfaces are highly susceptible to Escherichia coli and Salmonella enteritidis, demanding rapid, non-destructive detection. This study evaluated hyperspectral imaging (HSI) for pathogen discrimination. Visible-near-infrared (Vis-NIR) and short-wave infrared systems acquired data from eggs contaminated at 103–105 CFU/mL. Raw Vis-NIR spectra with competitive adaptive reweighted sampling provided optimal features. The pathogens showed opposite reflectance trends, attributed to biofilm structural differences affecting light scattering and absorption. Classification models achieved up to 91.11% accuracy in pathogen identification and 88.89% accuracy in differentiating E. coli levels. Vis-NIR-HSI shows great potential for rapid, non-destructive eggshell pathogen detection, with a clarified mechanistic framework.