AdaptiveDet: Defect Detection for Digital Printing Fabric with Complex Background

During the digital printing process, the fabric defects need to be accurately detected to ensure product quality. However, the defects are difficult to effectively distinguish from the background, which can cause degradation of detection model performance. To solve this problem, a defect detection model incorporating adaptive attention mechanisms, AdaptiveDet, was proposed for digital printing fabric. First, the initial anchor box was generated using the K-means++ algorithm to better adapt to the complex target shape. Second, the backbone network could be reconfigured using the adaptive CBS module, allowing higher-level features to be extracted and interference with non-critical features to be reduced. Then, the neck network was reconfigured using the ELAN-EVC module so that the model could learn both global and local feature representations to capture information more accurately about minor defects. Finally, the DyHead framework was adopted in the head of YOLOv7-Tiny to enhance the model’s sensitivity to spatial information, which lead to excellent performance in the complex background defect detection task. The experimental results show that the proposed model performs well on the DPFD-DET dataset with mAP@.5 of 93%, which outperforms other detection models. This shows that it could meet the demand for high-precision defect detection for digital printing fabric.