The purpose of this paper was to establish a reliable Fisher discriminant model which was able to recognize the decoction pieces of radix panacis quinquefolii and its common counterfeits rapidly, objectively and accurately. The fluorescence spectra of 90 samples (decoction pieces of radix panacis quinquefolii, radix ginseng and platycodon grandiflorum each 30 copies) that from different source were detected by a self-build staring spectral imaging instrument in this study. The experimental parameters included spectral wavelengths range from 400 to 720 nm, with the interval of 5 nm. Standard normal variate (SNV) transformation was used for spectral pretreatment, to reduce the noise information in original spectral data. According to the principle features and optimizing effect of principal component analysis (PCA) and stepwise discriminant analysis (SDA), PCA in combination with PCA was needed. At first, SNV spectral data was processed with PCA to obtain main information of spectrum distributed in the first few principal components. Then 12 principal components that with strong discriminant ability were selected from 65 principal components, and used for established the Fisher discriminant model. All kind of samples showed up a good clustering phenomenon in the scatter diagram, which plotted based on samples scores in two discriminant functions. In order to obtain an accurate discriminant result of the model, the Euclidean distance between the central of each species and the samples that under discriminate was calculated and as the gist. The result showed that the discriminant accuracy of the Fisher discriminant model in training set and prediction set was 98.33% and 96.67% respectively, demonstrating that the superior reliability and accuracy existed in the model. Therefore, fluorescence spectroscopy combined with Fisher discriminant analysis could be applied to the rapid identification between the decoction pieces of radix panacis quinquefolii and its counterfeits.