摘要：Firstly, we applied the X-ray non-destructive testing technology to detect wood defects for getting the images. After graying the images, we calculated their GLCMS(Gray Level Co- occurrence Matrixes), then we normalized GLCMS to obtain the joint probabilities of GLCMS. The feature vectors of images, which included 13 eigenvalues of images were calculated and extracted by the joint probability of GLCMS. The fuzzy BP neural network(abbreviated as FBP) was designed by combining fuzzy mathematics and BP neural network . And the FBP neural network was regarded as the membership function of feature vectors, the outputs of the network was regarded as the degree of membership to the feature vectors in each category. We use the maximum degree of membership method for the pattern recognition of feature vectors, so the automatic identification and classification for feature vectors were achieved , and then the automatic identification of wood defects was realized. By simulated study and training many times, the results shown that the average recognition success rate of the network was more than 90%, and some FBP networks had an extremely high recognition success rate to training samples and test samples.
关键词：wood defects; Gray Level Co-occurrence Matrixes (GLCM); feature extraction; ; fuzzy BP neural network; membership function
