基于改进型YOLOv8的木材缺陷检测及分类

打开文本图片集

关键词：木材缺陷；目标检测；深度学习；YOLOv8；特征提取；多尺度融合；算法优化；智能识别 中图分类号：S781.1 文献标识码：A DOI：10.7525/j.issn.1006-8023.2025.04.011

Abstract：Aimingatthebotteneck problemof insufficientadaptabilityof traditionaldefectdetection methodsinautomated wood processng industry，research onintellgentdetectiontechnologybasedondeep learning iscarriedout，and adatasetcovering multi-species woodcharacteristicsand typicaldefecttypes is proposed.Applyingobjectdetectiontechnology to defect detection，using dilation wise residual（DWR）module to optimize C2f module，and proposing task aligned dynamic detection head （TADDH）and feature focusing spread pyramid network （FSPN） to impove YOLOv8 algorithm（DFT-YOLO）.The experimental results showed that a significant improvement in accuracy，reaching 96.8%， which was 7.9 higher than the original model.On the averageaccuracyof the keyevaluation indicators mAP50 and mAP50-95，the impoved model reached 93. 8% and 75.2% ，respectively，increasing by 6.8% and 17.5% ，respectively.While improving the detection accuracy，the number of parameters of the model had decreased by approximately 1/6 （ 16.2% ）.The impoved model can provide a lightweight detection method for wood defects.

KeyWords：Wood defect；target detection；deep learning;YOLOv8；feature extraction；multi-scalefeature integration; computational optimization；intelligent recognition

0引言

中国作为全球木材消费的重要市场，面临环保政策日益严格和公众环保意识提升的双重挑战。（剩余19737字）