Abstract: In this study, binary and ternary adulterated samples of camellia oil were obtained by adding corn oil, rice oil and soybean oil into camellia oil at different concentrations, and the near-infrared Raman spectra of all samples were measured. The adulteration of camellia oil was successfully identified by combining Raman spectroscopy with linear discriminant analysis. The results show that Raman spectroscopy combined with principal component analysis can effectively distinguish different kinds of vegetable oils, and identify the camellia oil adulteration. In the binary adulteration model of camellia oil, the classification accuracy of training samples and the discriminant accuracy of predicted samples are both 100%. In the ternary adulteration model of camellia oil, the classification accuracy of training samples is 99.2%, and the discrimination accuracy of predicted samples is 96.8%.