西安工程大学学报2025，Vol.39Issue(3)：59-69,11.DOI:10.13338/j.issn.1674-649x.2025.03.008
基于SAC-YOLO的轻量化织物疵点分割算法
Lightweight fabric defect segmentation algorithm based on SAC-YOLO
摘要
Abstract
Aimed at the problems of low detection accuracy and complex model in the process of fabric defect detection,a lightweight fabric defect segmentation algorithm based on SAC-YOLO was proposed.Firstly,a lightweight down-sampling module,ADown,with stronger extraction ca-pabilities,was introduced in the Backbone part to improve accuracy while reducing model parame-ters.SENetv2 attention mechanism was then incorporated into the C2f module to enhance the model's ability to extract semantic and detailed information of small defect targets.Secondly,the Neck layer uses a multi-scale feature fusion module,significantly reducing the model parameters and computational load.Finally,the Inner-CIoU loss function was introduced to replace the origi-nal CIoU bounding box regression loss function,accelerating the model convergence speed and im-proving the model generalization ability.Experimental results show that compared to the im-proved YOLOv8s,the proposed model reduces the parameter count by 45.8% and the computa-tional load by 8.8 billion floating-point operations.The mAP50 and mAP50-95 of defect detection are improved by 0.5% and 1.7% ,respectively.The precision,recall,mAP50,and mAP50-95 of segmen-tation are improved by 1.3%,0.2%,0.4%,and 1.4%,respectively.Compared with other main-stream segmentation algorithms,the improved algorithm model shows superior performance in both detection and segmentation.关键词
织物疵点检测/YOLOv8/图像分割/注意力机制Key words
fabric defect detection/YOLOv8/image segmentation/attention mechanism分类
轻工业引用本文复制引用
张周强,李成,王康旭,陈芙蓉,崔芳斌..基于SAC-YOLO的轻量化织物疵点分割算法[J].西安工程大学学报,2025,39(3):59-69,11.基金项目
功能性纺织材料及制品教育部重点实验室开放课题(2024FTMP016) （2024FTMP016）
陕西省自然科学基础研究计划项目(2023JCYB288) （2023JCYB288）
西安工程大学专业学位研究生教学案例项目(24yjxa109) （24yjxa109）
