Neural network classification of defects in veneer boards


Pham D., Sagiroglu Ş.

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE, cilt.214, sa.3, ss.255-258, 2000 (SCI-Expanded) identifier identifier

Özet

Learning vector quantization (LVQ) networks are known good neural classifiers which provide fast and accurate results for many applications. The aim of this work was to test if this network paradigm could be employed for the classification of wood sheet defects. Experiments conducted with LVQ networks have shown that they provide a high degree of discrimination between the different types of defects and potentially can perform defect classification in real time.