Identification of selected internal wood characteristics in computed tomography images of black spruce: a comparison study

摘要: The feasibility of identifying internal wood characteristics in computed tomography (CT) images black spruce was investigated using two promising classifiers: the maximum likelihood classifier (MLC) and back propagation (BP) artificial neural network (ANN) classifier. Nine image features including one spectral feature (gray level values), a distance feature, seven textural were employed to develop classifiers. selected be identified included heartwood, sapwood, bark, knots. Twenty cross-sectional CT log randomly results suggest that both classifiers produced high classification accuracy. Compared with MLC (80.9% overall accuracy), BP ANN had better performance (97.6% accuracy). Moreover, statistical analysis reveals heartwood used this study is easiest identify by either compared other three features. also separability characteristic from mainly related moisture content.