Real-time detection system for polishing metal surface defects based on convolutional feature concentration and activation network

This study aims to improve the accuracy and efficiency of detecting defects on polished metal surfaces by developing a new detection system. A network model explicitly designed for detecting defects on polished metal surfaces and a convolutional feature concentration and activation network (CFCANet) are proposed in this paper. This model significantly enhances the recognition of tiny defects by introducing a small-target detection head, ensuring high-precision detection results. In addition, the feature concentration and activation (FCA-C2f) module proposed in this study enhances the model's sensitivity to anisotropic features, thereby improving defect detection accuracy. The content-aware reassembly of features (CARAFE) upsampling algorithm is used instead of traditional nearest-neighbour interpolation methods to effectively preserve detailed information and improve the quality and efficiency of upsampling. By optimising the lighting conditions and using composite light source illumination technology, the probabilities of missed detections and false alarms can be reduced. Combined with the CFCANet detection network, the defect detection performance of the proposed method on polished metal surfaces is effectively enhanced. To validate the effectiveness of the proposed method, a new dataset for detecting defects on polished metal surfaces, PMS-DET, was constructed in this study and validated on the NEU-DET dataset. Experimental results show that CFCANet effectively improves the defect detection accuracy on polished metal surfaces, achieving a mAP0.5:0.95 value of 42.4 % on the PMS-DET dataset, an increase of 11.9 %. The model parameters are reduced by 6.7 %, and the detection speed is improved by 28.1 %. Compared with existing detection models, this research method demonstrates significant improvements in detection accuracy, model size and computational efficiency, especially regarding GFLOPs and detection speed, proving its potential application value in practical industrial scenarios.