Wood Defects Classification Using a SOM/FFP Approach with Minimum Dimension Feature Vector
This paper describes the design and implementation of a wood defect classifier. The defects are four different types of knots found in wood surfaces. Classification is based on features obtained from Gabor filters and supervised and non supervised artificial neural networks are used as classifiers. A Self-organizing neural network and a fuzzy Self-organizing neural network were designed as classifiers. The fuzzy SONN shows a reduction on the training time and had a better performance. A final classifier, a feedforward perceptron using the weights of the fuzzy SONN as initial weights turn to be the best classifier with a performance of 97.22% in training and 91.17% in testing. The perceptron classifier surpasses a human inspector task which has a maximum performance of 85%.
KeywordsWood Surface Gabor Filter Gabor Feature Fuzzy Parameter Defect Sample
Unable to display preview. Download preview PDF.
- 3.Lampinen, J., Smolander, S., Korhonen, M.: Wood Surface Inspection System Based on Generic Visual Features. In: International Conference on Artificial Neural Networks ICANN 1995, Paris (1995)Google Scholar
- 4.Lampinen, J., Smolander, S.: Wood Defect Recognition: A Comparative Study. In: Proc. of workshop on Machine Vision in Advanced Production, Oulu, Finland, pp. 2–6 (1994)Google Scholar
- 5.Kauppinen, H., Silven, O., Piirainen, T.: Self Organizing Map Based User Interface for Visual Surface Inspection. In: Proc. 11th Scandinavian Conference on Image Analysis, Kangerlussuaq, Greenland, pp. 801–808 (1999)Google Scholar
- 6.G-SOM tool, University of Oulu Department of Electrical Engineering, http://www.oulu.fi/research/imag/gsom/
- 8.Kohonen, T.: Self Organizing Maps, 2nd edn. Springer Series in Information Sciences (1995)Google Scholar
- 9.Kim, D.S., Huntsberger, T.L.: Self-organizing Neural Networks for Unsupervised Pattern Recognition. In: Proceedings of Tenth Annual International Phoenix Conference on Computers and Communications, March 27-30, pp. 39–45 (1991)Google Scholar