Research on classification of wood texture based on Gauss-Markov random field

To classify wood by its texture, rank 2-5 Gauss-Markov Random Field (Gauss-MRF) models were established. Parameters of the 2-5 rank Gauss-MRF models for 300 wood samples' surface texture were estimated using least mean square (LMS). The data analysis shows that: 1) different texture parameters have a clear scattered distribution, 2) the main direction of texture is the direction represented by the maximum parameter of Gauss-MRF parameters, 3) for those samples having the same main direction, the finer the texture is, the greater the corresponding parameter is, and the smaller the other parameters are; and the higher the rank of Gauss-MRF is, the more clearly the texture is described. On the condition of the rank-2 Gauss-MRF model, parameter theta 1, theta 2 of tangential texture are smaller than that of radial texture, while theta 3 and theta 4 of tangential texture are greater than that of radial texture. According to the value of separated criterion, the parameter of the rank-5 Gauss-MRF is used as feature vector for BP neural network classification. As a result, the ratio of correct reaches 88%. Conclusion: rank-5 Gauss-MRF model is valid to classify wood texture.