文献类型：期刊文献

英文题名：A Particleboard Surface Defect Detection Method Research Based on the Deep Learning Algorithm

作者：Zhao, Ziyu[1] Ge, Zhedong[1] Jia, Mengying[1] Yang, Xiaoxia[1] Ding, Ruicheng[1] Zhou, Yucheng[1,2]

第一作者：Zhao, Ziyu

通信作者：Ge, ZD[1]

机构：[1]Shandong Jianzhu Univ, Sch Informat & Elect Engn, Jinan 250101, Peoples R China;[2]Chinese Acad Forestry, Res Inst Wood Ind, Beijing 100091, Peoples R China

年份：2022

卷号：22

期号：20

外文期刊名：SENSORS

收录：;EI(收录号：20224413039946);Scopus(收录号：2-s2.0-85140845419);WOS:【SCI-EXPANDED(收录号:WOS:000873614500001)】；

基金：This research was funded by the youth fund of Shandong Natural Science Foundation, grant No. ZR2020QC174, and the Doctoral Foundation of Shandong Jianzhu University, grant No. XNBS1622, and the Taishan Scholar Advantage Characteristic Discipline Talent Team Project of Shandong Province of China, grant No. 2015162.

语种：英文

外文关键词：surface defect detection; object detection; semantic segmentation; real-time; deep learning

摘要：Particleboard surface defects have a significant impact on product quality. A surface defect detection method is essential to enhancing the quality of particleboard because the conventional defect detection method has low accuracy and efficiency. This paper proposes a YOLO v5-Seg-Lab-4 (You Only Look Once v5 Segmentation-Lab-4) model based on deep learning. The model integrates object detection and semantic segmentation, which ensures real-time performance and improves the detection accuracy of the model. Firstly, YOLO v5s is used as the object detection network, and it is added into the SELayer module to improve the adaptability of the model to receptive field. Then, the Seg-Lab v3+ model is designed on the basis of DeepLab v3+. In this model, the object detection network is utilized as the backbone network of feature extraction, and the expansion rate of atrus convolution is reduced to the computational complexity of the model. The channel attention mechanism is added onto the feature fusion module, for the purpose of enhancing the feature characterization capabilities of the network algorithm as well as realizing the rapid and accurate detection of lightweight networks and small objects. Experimental results indicate that the proposed YOLO v5-Seg-Lab-4 model has mAP (Mean Average Precision) and mIoU (Mean Intersection over Union) of 93.20% and 76.63%, with a recognition efficiency of 56.02 fps. Finally, a case study of the Huizhou particleboard factory inspection is carried out to demonstrate the tiny detection accuracy and real-time performance of this proposed method, and the missed detection rate of surface defects of particleboard is less than 1.8%.