The classification of wood types is needed in many industrial sectors, since it can provide relevant information concerning the features and characteristics of the final product (appearance, cost, mechanical properties, etc.). This analysis is typical in the furniture industries and the wood panel production. Usually, the analysis is performed by human experts, is not rapid, and has a nonuniform accuracy related mainly to the operator's experience and attention. This paper presents a methodology to effectively cope with the design of an automatic wood types classification system based on the analysis of the fluorescence spectra suitable for real-time applications. This paper presents an experimental set up based on a laser source, a spectrometer, and a processing system, and then, it discusses a set of techniques suitable to extract features from the spectra and how to exploit the extracted feature to train an inductive classification system capable to properly classify the wood types. Obtained experimental results show that the proposed approach can achieve a good accuracy in the classification and requires a limited computational power, hence allowing for the application in real-time industrial processes.