대한임베디드공학회논문지 (IEMEK Journal of Embedded Systems and Applications)

대한임베디드공학회 (Institute of Embedded Engineering of Korea)
권호 표지
DOI QR코드

DOI QR Code

엣지 컴퓨팅 환경에서 적용 가능한 딥러닝 기반 라벨 검사 시스템 구현

Implementation of Deep Learning-based Label Inspection System Applicable to Edge Computing Environments

  • 투고 : 2022.02.11
  • 심사 : 2022.03.24
  • 발행 : 2022.04.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

키워드

과제정보

본 논문은 한국전자통신연구원 연구운영지원사업의 일환으로 수행되었음 (22ZD1100, 대경권 지역산업 기반 ICT 융합기술 고도화 지원사업).

참고문헌

  1. B. D. Kang, O. H. Kwon, C. U. Seong, J. D. Jeon, J. S. Eom, J. H. Kim, J. W. Lee, S. K. Kim, "Effective Face Detection Using Principle Component Analysis and Support Vector Machine," Journal of Korea Multimedia Society, Vol. 9, No. 11, pp. 1435-1444, 2006.
  2. H. Y. Maeng, J. H. Kim, Y. H. Ko, "Image Allignment Method Based on CUDA SURF for Multi-Spectral Machine Vision Application," Journal of Korea Multimedia Society, Vol. 17, No. 9, pp. 1041-1051, 2014 (in Korean). https://doi.org/10.9717/KMMS.2014.17.9.1041
  3. S. B. Hong, S. W. Hong, K. H. Lee, "Recognition Direction Improvement of Target Object for Machine Vision based Automatic Inspection," Journal of Korea Institute of Information and Communication Engineering, Vol. 23, No. 11, pp. 1384-1390, 2019 (in Korean). https://doi.org/10.6109/JKIICE.2019.23.11.1384
  4. H. Y. Kim, J. S. Cho, "Exterior Vision Inspection Method of Injection Molding Automotive Parts," Journal of Institute of Korean Electrical Electronics Engineers, Vol. 23, No. 2, pp. 127-132, 2019 (in Korean).
  5. S. M. Yoon, S. H. Lee, "Development of Defect Inspection System for Polygonal Containers," Journal of Institute of Korean Electrical Electronics Engineers, Vol. 25, No. 3, pp. 485-492, 2021 (in Korean).
  6. M. J. Kim, J. H. Shin, "Development of Defect Inspection System for Polygonal Containers," Korean Journal of Computational Design and Engineering, Vol. 25, No. 3, pp. 246-255, 2020 (in Korean). https://doi.org/10.7315/cde.2020.246
  7. G. H. Kang, J. M. Shon, G. W. Sim, "Comparative Analysis of Anomaly Detection Models using AE and Suggestion of Criteria for Determining Outliers," Journal of the Korea Society of Computer and Information, Vol. 26, No. 8, pp. 23-30, 2021 (in Korean). https://doi.org/10.9708/JKSCI.2021.26.08.023
  8. H. J. Park, Y. W. Lee, B. G. Kim, "Efficient Tire Wear and Defect Detection Algorithm Based on Deep Learning," Journal of Korea Multimedia Society, Vol. 24, No. 8, pp. 1026-1034, 2021 (in Korean). https://doi.org/10.9717/KMMS.2021.24.8.1026
  9. S. Ren, K. He, R. Girshick, J. Sun, "Faster R-Cnn: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 6, pp. 1137-1149, 2016. https://doi.org/10.1109/TPAMI.2016.2577031
  10. J. Redmon, S. Divvala, R. Girshick, A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016.
  11. P. Adarsh, P. Rathi, M. Kumar, "YOLO v3-Tiny: Object Detection and Recognition using One Stage Improved Model," 2020 6th International Conference on Advanced Computing and Communication Systems, pp. 687-694, 2020.
  12. B. G. Han, J. G. Lee, K. T. Lim, D. H. Choi, "Design of a Scalable and Fast YOLO for Edge-Computing Devices," Sensors, Vol. 20, No. 23, 2020.
  13. Y. S. Jung, K. H. Park, "O-ring Size Measurement Based on a Small Machine Vision Inspection Equipment," Journal of the Korea Industrial Information Systems Research, Vol. 19, No. 4, pp. 41-52, 2014 (in Korean). https://doi.org/10.9723/JKSIIS.2014.19.4.041
  14. B. J. Park, K. S. Hahn, H. J. Lee, "Automated Visual Inspection System of Junction Box Using Color Inspection and Template Matching," Journal of Korea Multimedia Society, Vol. 13, No. 3, pp. 392-399, 2010 (in Korean).
  15. D. M. Ko, K. S. Choi, "Accurate PCB Outline Extraction and Corner Detection for High Precision Machine Vision," Journal of the Semiconductor & Display Technology, Vol. 16, No. 3, pp. 53-58, 2017 (in Korean).
  16. G. S. Kim, S. Lee, J. S. Cho, "A Learning-Based Visual Inspection System for Part Verification in a Panorama Sunroof Assembly Line Using the SVM Algorithm," Journal of Institute of Control, Robotics and Systems, Vol. 19, No. 12, pp. 1099-1104, 2013 (in Korean). https://doi.org/10.5302/J.ICROS.2013.13.9041
  17. D. H. Kim, S. B. Boo, H.C . Hong, W. G. Yeo, N. Y. Lee, "Machine Vision-Based Defect Detection Using Deep Learning Algorithm," Journal of the Korean Society For Nondestructive Testing, Vol. 40, No. 1, pp. 47-52, 2020 (in Korean). https://doi.org/10.7779/jksnt.2020.40.1.47
  18. G. A. Ryu, K. H. Yoo, "Application of Manufacturing Process Data Classification Using Image Data based CNN," Journal of Information Technology and Architecture, Vol. 15, No. 3, pp. 337-343, 2018 (in Korean). https://doi.org/10.22865/JITA.2018.15.3.337
  19. R. Girshick, "Fast r-cnn," Proceedings of the IEEE International Conference on Computer Vision, pp.1440-1448, 2015.
  20. K. He, G. Gkioxari, P.Dollar, R. Girshick, "Mask R-Cnn," Proceedings of the IEEE International Conference on Computer Vision, pp. 2961-2969, 2017.
  21. J. Redmon, A. Farhadi, "Yolov3: An Incremental Improvement," Computer Vision and Pattern Recognition, pp. 1804-2767, 2018.
  22. A. Bochkovskiy, C. Y. Wang, H. Y. M. Liao, "Yolov4: Optimal Speed and Accuracy of Object Detection," arXiv preprint arXiv:2004.10934, 2020.
  23. C. Y. Wang, A. Bochkovskiy, H. Y. M. Liao, "Scaled-Yolov4: Scaling Cross Stage Partial Network," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13029-13038, 2021.
  24. Y. Li, Z. Han, H. Xu, L. Liu, X. Li, K. Zhang, "YOLOv3-lite: A Lightweight Crack Detection Network for Aircraft Structure Based on Depthwise Separable Convolutions," Applied Sciences, Vol. 9, No. 18, 2019.
  25. https://github.com/AlexeyAB/darknet/