Wood Defect Classification Based on Two-Dimensional Histogram Constituted by LBP and Local Binary Differential Excitation Pattern

A classification algorithm based on LBP and local binary differential excitation pattern is presented for the classification of the crack and the linear mineral line on the surface of the birch veneer. The local binary differential excitation pattern (LB_DEP) is a texture description model proposed in this paper, which is generated by the combination of LBP and Weber's Law and describes the incidence relation between the image texture and the human visual perception. And the feature extracted by LB_DEP is expressed in a one-dimensional histogram. Then we establish a two-dimensional (2D) histogram constituted by the one-dimensional (1D) histogram of LBP and LB_DEP after being normalized and consolidated. Finally, the 2D histogram is used to classify the defects with Euclidean distance classifier. In addition, we establish an automatic optical inspection system for the birch ice cream bar. We also conduct the experiments with the images captured by the system. The results demonstrate that, compared with the state-of-the-art methods, our proposed algorithm can provide a better classification effect for the crack and the mineral line-the Recall, Precision and FNR are 0.930, 0.943 and 0.070 respectively. And the time consumption is 0.1416 s, which belongs to the millisecond level as with the compared methods.