Near-infrared spectroscopy (NIRS) combined with two discriminative analysis methods including self-organization mapping (SOM) and support vector machine (SVM) were used for discriminant analysis of vinegar with different production year and brand. Continuous wavelet transform (CWT) was adopted for spectra preprocessing. Principal component analysis (PCA) was used for spectra dimension reduction and space distribution analysis. The results shown that CWT can effective eliminate spectra translation error. PCA can greatly reduce characteristic spectrum variables and improve modeling efficiency. For identification of vinegar with different production year, the CWT-PCA-SOM method can get 97.37% correct recognition rate (CRR), and the CWT-PCA-SVM method can get 100% CRR. For identification of vinegar brand, the CWT-PCA-SOM and CWT-PCA-SVM methods can obtain 100% CRR. Near-infrared spectroscopy combined with CWT-PCA-SOM and CWT-PCA-SVM methods can both obtain better analysis results for identification of vinegar with different production year and brand, and this method has good application prospect.