A New Graph-based Method for Class Imbalance in Surface Defect Recognition

Surface defect recognition is an important technology to guarantee the quality of products in modern manufacturing system, but the class imbalance in the real-world production greatly influences its performance. Recently, some deep learning-based methods have been developed to address the class imbalance. Because of the inter-class similarities and the intra-class variations (ISIV) of surface defect, it is hard to apply them to solve the coupling between class imbalance and ISIV. Graph-based methods, including Graph Convolutional Network (GCN), is potential for ISIV. Therefore, this paper proposes a new graph-based method, named as Anchor-based Class-Balanced Graph Convolutional Network (ACB-GCN), to solve the class imbalance in surface defect recognition. Firstly, the proposed method constructs a class-balanced graph to address the problem that excessive information from majority classes influence the performance of graph convolution. Secondly, the proposed method defines anchor vectors in each defect to reduce the influence of ISIV on graph construction. The experimental results on four famous datasets with class imbalance demonstrate that the proposed method can effectively address the coupling between class imbalance and ISIV, and thus extract the discriminative features. Meanwhile, the proposed method achieves better performance than traditional methods and the original GCN, especially on minority classes.