Data-Driven Semantic Segmentation Method for Detecting Metal Surface Defects

Accurate semantic segmentation is crucial for monitoring the quality of metal surfaces in industrial production. To solve the issues of the scarce quantities and uneven distributions of metal surface defects, challenging to achieve real-time detection and hardware integration, and hard to capture boundary information, this study proposes a dual-attention multiscale residual aggregation network (DMRAN), category weight (CW) calculation method, defect migration topology method (DMT), and loss calculation method for dual boundary attention (DBA). The methods solved the technical issues by aggregating the multiscale information of the original image and exerting attention, changing the weight coefficients of categories, expanding the datasets using the topology of the defects of defective samples to a defect-free image, and paying dual attention to the boundaries of ground truth (GT) and predicted image. Compared to the 15 mainstream methods and our previous work, this study achieved a favorable performance on five public datasets with 5.1 M parameters and real-time inference speed of 37.5 frames/s. Additionally, this study demonstrates commendable robustness in the presence of noise. Our code locates at https://github.com/zz-ux/Metal-surface-defect-detection.