Classification of Wood Plates by Neural Networks and Fuzzy Logic

The automated visual inspection is an important task for the industrial productivity. It could be applied for quality control or for replacing manual work under dangerous or repetitive activity. The classification stage in quality control of the industrial production is often based on the human knowledge. It seems, therefore, to be a great concern to supply an automated visual inspection system with fuzzy or ambiguous data. The neuro-fuzzy system is a good way to do this. This work contributes with a new approach for the classification of wood plates in pencil production. The method is based on two neural networks, each one working with just an input feature. The results of the neural networks are combined through fuzzy logic giving the system a greater classification power than those that use traditional methods. The system is characterized by being agile, repetitive, with a defined classification pattern and low cost.