Abstract:

To improve the efficiency of wood defects identification, a method based on the convolutional neural network was proposed. A convolutional neural network was presented to recognize the wood defect, and the numbers of training samples were determined by an incremental learning method; the corresponding network structure was designed, and the time consumption could be reduced. Experimental results showed that the preprocessing of a complex image was not needed, and the multiclass defects could be recognized with high accuracy, small complexity and good robustness, while the inherent shortcomings of the traditional algorithm were overcame.

Key words: wood defects, convolutional neural networks, image processing, learning methods, incremental