Defect detection of bamboo strips based on LBP and GLCM features by using SVM classifier

With the improvement of bamboo mat production, the higher requirements have been proposed for the using of bamboo strips which makes the defect detection of bamboo strips vital for mat quality. Various defects emerge in the bamboo strips will greatly affect product quality and reduce the productive efficiency. In fact, the defect detection of bamboo strips by manpower can not be guaranteed in terms of efficiency and quality, then forcing companies to work with automatic systems in this area. In this paper, we propose a method for defect detection of bamboo strips using a set of features based on LBP (Local Binary Pattern) and GLCM (Gray-level Co-occurrence Matrix). In the image preprocessing, we use the threshold algorithms to extract the region of interest (ROI), and then the two algorithms are combined to detect the texture of the ROI region and finally the SVM classifier is used to classify the bamboo strips. Experimental results show that the algorithms have a good performance on defect detection. The accuracy of the classification is 97.76%, which can greatly improve the productive efficiency.