Industrial, Environmental and Biometric Informatics Laboratory
Università degli Studi di MilanoDepartment of Computer Science
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 non-uniform accuracy related mainly to the operatorís experience and attention. We have studied 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. We have researched two hardware setups, different feature sets, and classification techniques able to proper categorize wood panels.
Schema of the acquisition setups
Schema of the wood classification approach