Background-Adaptive Surface Defect Detection Neural Networks via Positive Samples

This paper focuses on the challenge of surface defect detection in manufacturing, particularly under conditions of background variation and noise interference. To tackle this issue, a novel Background-Adaptive Surface Defect Detection Network (BANet) is proposed. The BANet enhances the defect detection capabilities by improving generalization capacity through learning comparative abilities between positive samples and testing samples. In order to mitigate the impact of three types of noise (texture variation, translation, and rotation), a Foreground Edge Attention Mechanism (FEAM) and a Spatial Transformer Module (STM) are introduced. The FEAM enhances the model's ability to differentiate between foreground and background, thereby effectively reducing texture variation noise. The STM uses affine transformations to eliminate translation and rotation noise. The effectiveness of the proposed network is validated on Optical Communication Devices (OCDs) dataset, with results indicating superior performance compared to prevailing state-of-the-art methods. The findings of this study highlight the potential of our approach in effectively addressing surface defect detection in variable backgrounds and noisy conditions, thereby contributing significantly to the quality and reliability of manufacturing processes.