RESEARCH ON WOOD DEFECTS CLASSIFICATION BASED ON DEEP LEARNING

Abstract

Whereas the traditional manual detection method of wood defects is problematic due time-consuming, low efficiency and low accuracy, an derived model based on ResNet-v2 was constructed. The new derived model can accurately point out the types of defects such as wormhole, live joint and dead joint on the surface of plate, improve the accuracy ofclassification, and greatly reduce the labor force. Compared with the traditional convolutional neural network, ResNet-v2 derived model has better recognition effect and stronger generalization ability. The experimental results show that the classification accuracy of ResNet-v2 derived network model based on different number of layers is more than 80%, and the classification accuracy of ResNet-v2 derived model can reach 97.27%.