@article{ART003317596},
author={Yeong-Seo Lee and Seongbae Eun and Dong-beom Shin and Jae-Heum Lee},
title={CNN-Based Thread Defect Detection System for Manufacturing Process Automation},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2026},
volume={31},
number={3},
pages={71-78}
TY - JOUR
AU - Yeong-Seo Lee
AU - Seongbae Eun
AU - Dong-beom Shin
AU - Jae-Heum Lee
TI - CNN-Based Thread Defect Detection System for Manufacturing Process Automation
JO - Journal of The Korea Society of Computer and Information
PY - 2026
VL - 31
IS - 3
PB - The Korean Society Of Computer And Information
SP - 71
EP - 78
SN - 1598-849X
AB - In this paper, we propose a deep learning-based thread error detection system for improving the quality reliability of fastening parts in automated manufacturing environments. Thread images are acquired using a camera and acceptance or rejection is automatically determined based on a convolutional neural network (CNN). To overcome recognition limitations caused by repetitive and fine thread structures, the image acquisition environment and learning strategy were designed to ensure stable performance with limited training data. Experimental results showed 85% accuracy with 84% Precision and 82% Recall, confirming suppression of false and missed detections. The results confirm that the system can be applied to automatic defect determination in manufacturing processes.
KW - Deep learning;Vision-based inspection;Thread defect detection;Convolutional neural network;Manufacturing automation
DO -
UR -
ER -
Yeong-Seo Lee, Seongbae Eun, Dong-beom Shin and Jae-Heum Lee. (2026). CNN-Based Thread Defect Detection System for Manufacturing Process Automation. Journal of The Korea Society of Computer and Information, 31(3), 71-78.
Yeong-Seo Lee, Seongbae Eun, Dong-beom Shin and Jae-Heum Lee. 2026, "CNN-Based Thread Defect Detection System for Manufacturing Process Automation", Journal of The Korea Society of Computer and Information, vol.31, no.3 pp.71-78.
Yeong-Seo Lee, Seongbae Eun, Dong-beom Shin, Jae-Heum Lee "CNN-Based Thread Defect Detection System for Manufacturing Process Automation" Journal of The Korea Society of Computer and Information 31.3 pp.71-78 (2026) : 71.
Yeong-Seo Lee, Seongbae Eun, Dong-beom Shin, Jae-Heum Lee. CNN-Based Thread Defect Detection System for Manufacturing Process Automation. 2026; 31(3), 71-78.
Yeong-Seo Lee, Seongbae Eun, Dong-beom Shin and Jae-Heum Lee. "CNN-Based Thread Defect Detection System for Manufacturing Process Automation" Journal of The Korea Society of Computer and Information 31, no.3 (2026) : 71-78.
Yeong-Seo Lee; Seongbae Eun; Dong-beom Shin; Jae-Heum Lee. CNN-Based Thread Defect Detection System for Manufacturing Process Automation. Journal of The Korea Society of Computer and Information, 31(3), 71-78.
Yeong-Seo Lee; Seongbae Eun; Dong-beom Shin; Jae-Heum Lee. CNN-Based Thread Defect Detection System for Manufacturing Process Automation. Journal of The Korea Society of Computer and Information. 2026; 31(3) 71-78.
Yeong-Seo Lee, Seongbae Eun, Dong-beom Shin, Jae-Heum Lee. CNN-Based Thread Defect Detection System for Manufacturing Process Automation. 2026; 31(3), 71-78.
Yeong-Seo Lee, Seongbae Eun, Dong-beom Shin and Jae-Heum Lee. "CNN-Based Thread Defect Detection System for Manufacturing Process Automation" Journal of The Korea Society of Computer and Information 31, no.3 (2026) : 71-78.
