In this study, fungi-contaminated peanut samples which had infected under designed storage condition were prepared. Short- wave infrared (SWIR) imaging spectroscopy at 970 –2500 nm was used to acquire hyperspectral images. And the objectives of this study were to: 1) target on the spectral characteristics of fungi-contamination as well as its particular spectral responses at the wavelength range of (SWIR); 2) detect and identify the fungi- contaminated peanuts among multi-breeds to have a reliable identification method; 3) apply joint exploitation of both spectral and spatial information to identify the peanut so that the identification map can be used for future separation as in industry application.