Research on surface microdefect detection method for metal parts based on YOLOv5

Biao Xiao

doi:10.1117/12.3048482

12 November 2024 Research on surface microdefect detection method for metal parts based on YOLOv5

Biao Xiao

Author Affiliations +

Proceedings Volume 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) ; 133951Q (2024) https://doi.org/10.1117/12.3048482
Event: International Conference on Optics, Electronics, and Communication Engineering, 2024, Wuhan, China

Abstract

To improve the accuracy of identifying non-conforming parts and improve production efficiency, this paper proposes an intelligent identification method for micro defects in metal parts based on the YOLOv5 algorithm. This method first preprocesses the collected images and then extracts part features by enhancing fixed features, extracting image defect feature points, and training the YOLO network. Then, based on the YOLOv5 algorithm, an intelligent recognition model is established to achieve intelligent recognition of micro defects in parts. The experimental results show that the detection accuracy of this method is higher than 93.9%, with an average detection time of 2.57ms, which is better than the comparison method and has an ideal detection effect.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Biao Xiao "Research on surface microdefect detection method for metal parts based on YOLOv5", Proc. SPIE 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) , 133951Q (12 November 2024); https://doi.org/10.1117/12.3048482

Access the abstract

PROCEEDINGS
4 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Detection and tracking algorithms

Metals

Feature extraction

Education and training

Defect detection

Data modeling

Image processing

Show All Keywords

RELATED CONTENT

Improved EAST scene text detection based on ResNet-50
Proceedings of SPIE (April 14 2023)

Insulator detection based on improved YOLOv5s
Proceedings of SPIE (August 15 2023)

Detection of defects on the end face of small motor...
Proceedings of SPIE (August 16 2024)

Research on parking detection algorithm based on yolov8
Proceedings of SPIE (October 11 2023)

Small sample PCB defect detection based on meta feature enhancement
Proceedings of SPIE (June 13 2024)

Insulator defect detection algorithm based on attention mechanism
Proceedings of SPIE (November 08 2024)

Study on the detection of viscose filament defects based on...
Proceedings of SPIE (August 10 2023)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years