Abstract: There are some problems in manual detection because it is necessary to grade the wood board through its surface defects.In order to solve the problem of wood surface defect recognition,a convolution neural network model integrating ViT is proposed to improve the accuracy of defect recognition.For this purpose,four kinds of wood surface defect pictures of crack,wormhole,knot and texture are collected,in which the number of crack and wormhole pictures is far less than that of knot and texture.In order to solve the problem of sample imbalance in model training,ProGAN is used to train crack and wormhole pictures and generate pictures of the same type of defects,so as to increase their number and keep the number of four kinds of pictures balanced.Before the experiment,the data of defect images are enhanced and salt and pepper noise is added to sort out the required image data set.Based on the convolutional neural network model fused with ViT,two models with different activation functions are tested by using the data set.It is found that the model using GELU as the activation function has higher perfor-mance.The model performance at different transformer depths is tested,and the highest accuracy of model defect identification can reach 98.54%.Experiments show that the convolutional neural network model fused with ViT is feasible,which provides a new idea for the automatic detection of wood surface defects.

Key words: Wood surface defects, ProGAN, ViT, Convolutional neural network, Deep learning