Pattern Recognition of Wood Defects Types Based on Hu Invariant Moments

Abstract

The recognition of wood defects is very significant for reasonable selection and scientific utilization of wood. X-ray was adopted as a measure method for wood nondestructive testing. The difference of X-ray intensity after exposure is tested in order to judge whether the wood defects exist or not. Then the defects images were processed effectively. A group of describing shape features parameters can be defined by extending Hu invariant moments theory. Those parameters not only have translation invariance, scaling invariance, rotation invariance, but also have lower computational complexity. Input the feature parameters into neural network after pretreatment, and then recognize the wood defects. The experimental results show that the ratio of recognition attains 86%. It is shown that this method is very successful for detection and classification of wood defects. This study offers a new method for automatic recognition of wood defects.