Automated Wood Surface Defects Recognition System Using Yolov4-tiny Model

• Published in: 2023 Innovations in Power and Advanced Computing Technologies, i-PACT 2023
• Main Author: Musa A.M.B.; Momin M.A.; Khairuddin A.S.M.; Khairuddin U.; Ahmad A.; Rosli N.R.
• Format: Conference paper
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2023
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85187019378&doi=10.1109%2fI-PACT58649.2023.10434717&partnerID=40&md5=43cd4e3f9457a89c70bf6c3f320786db

Wood surface detection is a process of identifying and locating wooden surfaces in an image or video using computer vision techniques. This technique can be used in various applications such as furniture manufacturing, construction, and lumber mills. Wood defect detection is an important task in the wood industry as it ensures the quality of wood products. In this study, YOLOv4-tiny algorithm is proposed to detect seven types of wood defects from wood texture images. Analysis was performed by applying several detection models to detect the wood defects. The performance of the proposed model is evaluated in terms of precision, recall, F1-score, and mAP. The algorithm has the potential to improve the efficiency and quality of the wood industry and could be applied to other similar tasks, such as identifying defects in other materials and products. © 2023 IEEE.