A Ceramic Crack Test Method Based on the Maximum Variance Ratio of Inter-Class and Intra-Class

This paper presents a method for inter-class ceramic crack detection threshold than the maximum variance within the class-based segmentation. Ceramics crack detection methods are mainly obtained by ceramic image data, image pre-processing, image segmentation, feature extraction and object recognition constitutes five links. Experimental results show that the method can be detected quickly and accurately detect whether the standard ceramic.