Cotton foreign fibers directly affect the quality of a textile product; the less foreign fibers in raw cotton, the higher the quality grade of the textile product. Based on the foreign fiber clean machine, this paper proposed an evaluation method of foreign fiber content using deep learning. First of all, a large number of images of foreign fibers were collected from different production lines and annotated to obtain the mask image dataset of foreign fibers. Secondly, by comparing the image segmentation algorithm based on deep learning, tests showed that U-Net has a better performance on different segment metrics evaluations, and U-Net is improved to realize the real-time segmentation of foreign fiber images. The actual size of the foreign fiber could be calculated through the combination of the segment result and the mechanical parameters of the machine. Finally, the test results showed that the relative error between the estimated size and the actual size was less than 4%. After the prototype test, the algorithm was deployed on the actual production line and, by comparing the algorithm data in a random time with the actual foreign fiber statistical data, the overall error was less than 2%. The test showed that the new evaluation method can fully reflect the content of foreign fiber in raw cotton.

Addressing the low accuracy and slow detection speed experienced by algorithms based on deep learning for a leather defect detection task, a lightweight and improved leather defect detection algorithm, dubbed YOLOv8-AGE, has been proposed based on YOLOv8n. In the backbone network, the EMA attention mechanism and C2f module have been fused into the C2f-EMA module, achieving performance enhancement with lower computational overhead. In the neck, the AFPN structure has been combined with the VoV-GSCSP module constructed using GSConv, to reduce the number of parameters while enhancing the model’s multi-scale detection capability. Finally, a shared convolutional layer has been introduced for simplifying the design of the detection head. Experimental results demonstrate that the improved algorithm achieves an improvement of 1.39% in mAP50 and reduces the number of parameters and GFLOPs by 9.3% and 7.41%, respectively, as compared to the original YOLOv8 model. On the dataset in this paper, there is an improvement in accuracy and detection speed over mainstream algorithms.

Printed product surface defect inspection faces critical challenges in real industrial production, including insufficient detection accuracy, poor robustness, and scarcity of labeled defective samples. This paper proposes an improved Siamese network for high-resolution printed image defect detection to address the above limitations. Original 1300 × 460-pixel printed images are segmented into 64 × 64 patches to construct a training and testing dataset. We optimize the feature measurement strategy of contrastive loss and integrate a position matching module and multi-threshold evaluation strategy to balance detection precision and stability. Quantitative experiments demonstrate that the proposed method achieves an overall accuracy of 94.35%, a precision of 91.99%, a recall of 95.17%, and an F1-score of 93.55% at the fixed threshold of 0.45. Compared with mainstream lightweight detection models including YOLOv8Lite (You Only Look Once version 8 Lite) and MobileViTv2 (Mobile Vision Transformer version 2), our method maintains a stable F1-score advantage of 10.84–24.36% under optimal threshold settings. The proposed approach achieves outstanding performance and robustness in few-shot scenarios and can be deployed for automatic quality inspection of printed parts used in power communication equipment.