The visible/near-infrared hyperspectral imaging technique was used to rapidly detect the moisture content and distribution of beef.Hyperspectral imag es of 150yellow cattle samples were collected using a visible near-infrared hy p erspectral imaging system (400-1000nm),and the region of interest (ROI) of th e samples was extracted using ENVI4.8software and the average spectral values we re calculated; The raw spectral data is preprocessed and the feature wavelength extraction is performed by using continuous projection algorithm (SPA),competit ive competitive reweighting (CARS) and non-information variable elimination alg o rithm (UVE),and the characteristic wavelengths are extracted.Partial Least Squ ares Regression (PLSR) model was preferably the best predictive model.A total o f 26abnormal samples were eliminated by Monte Carlo cross-validation; the PLSR model constructed by spectral data pre-processing by convolution smoothing (SG) method was relatively good,with R²c of 0.817and R 2p of 0.850; using CARS and S PA The UVE method preferably has 12,7,and 27characteristic wavelengths; The PLSR model established by the full-band spectrum and the extracted characterist i c band spectrum is compared.The results show that the CARS-PLSR model based on hyperspectral imaging technology has the best effect,and the R²c,R²p values ar e 0.814,0.750,respectively.RMSEC and RMSEP values of 0.477and 0.389,respect ively; The CARS-PLSR model was selected to calculate the moisture content of ea c h pixel of the beef sample.The pseudo-color map was used to visualize the mois t ure content distribution of the beef sample,and the non-destructive detection o f the moisture content of the beef and the visual expression of the distribution were realized.Detection provides theoretical support.