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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 5th International Conference on Multimedia Information Processing and Retrieval, MIPR 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages184-189
Number of pages6
ISBN (Electronic)9781665495486
DOIs
StatePublished - 2022
Event5th International Conference on Multimedia Information Processing and Retrieval, MIPR 2022 - Virtual, Online, United States
Duration: 2 Aug 20224 Aug 2022

Publication series

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

Conference

Conference5th International Conference on Multimedia Information Processing and Retrieval, MIPR 2022
Country/TerritoryUnited States
CityVirtual, Online
Period2/08/224/08/22

Keywords

  • CSPDarknet53
  • PANet
  • SAM
  • Surface defect inspection system
  • YOLOv4

Fingerprint

Dive into the research topics of 'Lightning YOLOv4 for a Surface Defect Detection System for Sawn Lumber'. Together they form a unique fingerprint.

Cite this