Lightning YOLOv4 for a Surface Defect Detection System for Sawn Lumber

Fityanul Akhyar, Ledya Novamizanti, Trianusa Putra, Elvin Nur Furqon, Ming Ching Chang, Chih Yang Lin

研究成果: 書貢獻/報告類型會議論文篇章同行評審

5 引文 斯高帕斯(Scopus)

摘要

Lumber is a primary material for the production of various types of wood products. However, many industries still carry out the lumber quality inspection process manually, relying on human sight and instinct to compare many similar objects. To streamline the inspection process, this study developed a deep learning-based surface defect detection system with a proposed 'lightning YOLOv4' model. Specifically, to improve the model's performance speed, we simplify CSPDarknet53 and path aggregation network (PANet) for the feature extraction stage of YOLOv4 by reducing the convolution layers. Moreover, we introduce the simplification technique to reduce the number of channels in CSPDarknet53 by multiplying it with the scaling coefficient. In addition, we add spatial attention module (SAM) to the structures, which can improve whole system performance on two types of lumber datasets (pine and rubber lumber). According to the experimental results, the proposed detection system improves the average precision of defect localization with the highest gap of 1.3%, as well as improves the frames per second (FPS) by 10.8 points over the baseline.

原文???core.languages.en_GB???
主出版物標題Proceedings - 5th International Conference on Multimedia Information Processing and Retrieval, MIPR 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面184-189
頁數6
ISBN(電子)9781665495486
DOIs
出版狀態已出版 - 2022
事件5th International Conference on Multimedia Information Processing and Retrieval, MIPR 2022 - Virtual, Online, United States
持續時間: 2 8月 20224 8月 2022

出版系列

名字Proceedings - 5th International Conference on Multimedia Information Processing and Retrieval, MIPR 2022

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???5th International Conference on Multimedia Information Processing and Retrieval, MIPR 2022
國家/地區United States
城市Virtual, Online
期間2/08/224/08/22

指紋

深入研究「Lightning YOLOv4 for a Surface Defect Detection System for Sawn Lumber」主題。共同形成了獨特的指紋。

引用此