摘要
纸张表面缺陷检测是保障纸张质量的关键环节。传统纸张缺陷检测方法存在检测精度低、实时性差等局限性。基于此,提出一种基于改进YOLOv10的纸张表面缺陷检测算法,通过优化YOLOv10网络结构,针对性地设计损失函数,并采用数据增强策略扩充训练样本,有效提高了纸张缺陷检测的精度和鲁棒性。在此基础上,搭建了嵌入式缺陷检测系统,通过模型轻量化设计和算法移植优化,实现了改进YOLOv10纸张缺陷检测算法在嵌入式平台上的高效部署。实验结果表明,该方法能够实现对纸张表面微小缺陷的实时、准确检测,为纸张质量控制提供有力支撑。
Paper surface defect detection is a crucial step in ensuring paper quality.Traditional paper defect detection methods have limitations such as low detection accuracy and poor real-time performance.To address these issues,an improved YOLOv10-based paper surface defect detection algorithm is proposed.By optimizing the YOLOv10 network structure,designing a targeted loss function,and employing data augmentation strategies to expand the training samples,the accuracy and robustness of paper defect detection are effectively enhanced.On this basis,an embedded defect detection system is built.Through model lightweight design and algorithm transplantation optimization,the improved YOLOv10 paper defect detection algorithm is efficiently deployed on an embedded platform.Experimental results show that this method can achieve real-time and accurate detection of minute defects on paper surfaces,providing strong support for paper quality control.
作者
方玉杰
李维
FANG Yujie;LI Wei(Xi’an Mingde Institute of Technology,Xi’an 710124,China;Xi’an Traffic Engineering Institute,Xi’an 710300,China)
出处
《造纸科学与技术》
2025年第8期130-133,145,共5页
Paper Science And Technology
