The analysis of the wood types is important in many industrial sectors such as the furniture industries and the wood panel production. Different woods have different aspects, properties and costs. The analysis of the wood type is very important to guarantee that the final product has the required features and characteristics. Unfortunately, the analysis made by human experts is not rapid and it presents a not standardized accuracy due to the operator's capabilities and tiredness. The presented paper shows how that it is effectively possible to accurately classify the wood types by the analysis of the fluorescence spectra in real time and during the production activities. In particular, the paper presents a prototype schema and a set of techniques suitable to extract features from the spectra and how to used the extracted feature to train an inductive classification system. Results show that a good accuracy in the classification can be achieved, and that the proposed setup can be used also in realtime industrial processes.
A classification method for wood types using fluorescence spectra / P. Camorani, M. Badiali, D. Francomacaro, M. Gamassi, V. Piuri, F. Scotti, M. Zanasi - In: Instrumentation and Measurement Technology Conference Proceedings, 2008. IMTC 2008. IEEEPiscataway : IEEE, 2008. - ISBN 9781424415403. - pp. 1312-1315 (( Intervento presentato al 12. convegno Instrumentation and Measurement Technology Conference (IMTC) tenutosi a Victoria nel 2008.
A classification method for wood types using fluorescence spectra
V. Piuri;F. ScottiPenultimo
;
2008
Abstract
The analysis of the wood types is important in many industrial sectors such as the furniture industries and the wood panel production. Different woods have different aspects, properties and costs. The analysis of the wood type is very important to guarantee that the final product has the required features and characteristics. Unfortunately, the analysis made by human experts is not rapid and it presents a not standardized accuracy due to the operator's capabilities and tiredness. The presented paper shows how that it is effectively possible to accurately classify the wood types by the analysis of the fluorescence spectra in real time and during the production activities. In particular, the paper presents a prototype schema and a set of techniques suitable to extract features from the spectra and how to used the extracted feature to train an inductive classification system. Results show that a good accuracy in the classification can be achieved, and that the proposed setup can be used also in realtime industrial processes.File | Dimensione | Formato | |
---|---|---|---|
05_2008_imtc_2008_postprint_ok.pdf
accesso aperto
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
5.04 MB
Formato
Adobe PDF
|
5.04 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.