Portable NIR spectrometers was used for the identification of six kinds of food-contacted plastic material including polyethylene terephthalate (PET), high-density polyethylene (HDPE), low-density polyethylene (LDPE), polyvinyl chloride (PVC), polystyrene (PS) and polycarbonate (PC). Four kinds of spectral preprocessing methods including 5-point smoothing, multivariate scattering correction (MSC), first-order derivative and standard normal variable transformation (SNV) were used to preprocess the spectra of plastic samples. Principal component analysis (PCA) and partial least squares-discriminant analysis (PLS-DA) were used to analyze the spectral space distribution of plastic samples and establish qualitative discriminant models. The results showed that six kinds of food-contacted plastic material could be clearly separated in the first three principal component spaces after the pretreatment of SNV and MSC methods. The PLS-DA combined with SNV could be used to get a concise plastic material qualitative discriminant model, and the correct recognition rates (CRR) were 100% both for calibration and prediction datasets. The method was expected to be a reference method for rapid identification of food-contacted plastic materials.