Identification of the Distilled Spirits Fluorescence Spectroscopy Based on the PCA and SVM

The spectral features of the different kinds of the distilled spirits are different from each other. In this paper, 4 kinds of distilled spirits(with 10 brands)were selected as the objects. Their absorption and three-dimensional fluorescence spectra induced by ultraviolet light (200nm-500nm)have been studied respectively. We have extracted the characteristic parameters of their three-dimensional fluorescence spectra by PCA. As a result, we have found that it is effective to discriminate different distilled spirits by three typical parameters. The support vector machine (SVM) is used to assort the main characteristic root books which are abstracted by the PCA. The species identification of the distilled spirits will be realized by it. The experiment results show that it is effective to extract the main feature of the spectroscopy. The classify speed is greatly increased. The discrimination is 96.32. The fact has proved that the classification´s accuracy rate of distilled spirit with different brands is very high.