Wood Board Defects Sorting Based on Method of Possibilistic C-Means Improved Support Vector Data Description
This paper exposes automatic classification for wooden board according to its knot defects. A four-parameter-classification vector, which includes the knot size and red component pixels of interior and exterior and boundary part of the knot, is formed to recognize the knot type. A possibilistic c-means (PCM) improved support vector data description (SVDD) method was proposed to construct a multi-classifier to classify four types of wood knots. The results obtained with our method show a real improvement of the recognition rate, which is 94%, compared to the original SVDD classifier, which recognition rate is just 86%, and experiments also testify PCM can help SVDD overcome the shortage of being sensitive to the noises and outliers.
Y. Z. Zhang et al., "Wood Board Defects Sorting Based on Method of Possibilistic C-Means Improved Support Vector Data Description", Applied Mechanics and Materials, Vols. 128-129, pp. 1288-1291, 2012