대한임베디드공학회논문지 (IEMEK Journal of Embedded Systems and Applications)

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

DOI QR Code

시각 장애인을 위한 상품 영양 정보 안내 시스템

Product Nutrition Information System for Visually Impaired People

  • Jonguk Jung (School of AI, Daegu University) ;
  • Je-Kyung Lee (School of AI, Daegu University) ;
  • Hyori Kim (Department of Computer Software from Daegu University) ;
  • Yoosoo Oh (School of AI, Daegu University)
  • 투고 : 2023.07.02
  • 심사 : 2023.09.22
  • 발행 : 2023.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Nutrition information about food is written on the label paper, which is very inconvenient for visually impaired people to recognize. In order to solve the inconvenience of visually impaired people with nutritional information recognition, this paper proposes a product nutrition information guide system for visually impaired people. In the proposed system, user's image data input through UI, and object recognition is carried out through YOLO v5. The proposed system is a system that provides voice guidance on the names and nutrition information of recognized products. This paper constructs a new dataset that augments the 319 classes of canned/late-night snack product image data using rotate matrix techniques, pepper noise, and salt noise techniques. The proposed system compared and analyzed the performance of YOLO v5n, YOLO v5m, and YOLO v5l models through hyperparameter tuning and learned the dataset built with YOLO v5n models. This paper compares and analyzes the performance of the proposed system with that of previous studies.

키워드

과제정보

이 논문 또는 저서는 2022년 대한민국 교육부와 한국연구재단의 지원을 받아 수행된 연구임 (NRF-2022S1A5C2A07091326).

참고문헌

  1. S. H. Lee, M. S. Kang, "Implementation of Objec Detection and Voice Guidance System for The Visually Handicapped Using Object Recognition Technology," Journal of The Institute of Electronics and Information Engineers, Vol. 55, No. 11, pp. 65-71, 2018 (in Korean). https://doi.org/10.5573/ieie.2018.55.11.65
  2. J. T. Park, "Investigation of Consumer Issues in Braille Labeling of Food for the Visually Impaired," Investigation Report of Korea Consumer Agency, pp. 1-66, 2022 (in Korean).
  3. D. Y. Park, S. B. Lim, "Object Detection Algorithm for Explaining Products to the Visually Impaired," The Journal of the Korea Contents Association, Vol. 22, No. 10, pp. 1-10, 2022 (in Korean). https://doi.org/10.5392/JKCA.2022.22.10.001
  4. S. H. Hong, J. Y. Yeon, Y. J. Bae, "Relationship among Night Eating and Nutrient Intakes Status in University Students," The East Asian Society of Dietary Life, Vol. 23, No. 3, pp. 297-310, 2013 (in Korean).
  5. Y. S. Suh, E. K. Lee, Y. J. Chung, "Comparison of Nutritional Status by Energy Level of Night Snack in Korean Adults: Using the Data from 2005 Korean National Health and Nutrition Examination Survey," Journal of Nutrition and Health, Vol. 45, No. 5, pp. 479-488, 2012 (in Korean). https://doi.org/10.4163/kjn.2012.45.5.479
  6. Y. W. Park, J. H. Suh, S. H. Chung, J. H. Lee, M. G. Sim, "A Product Voice Guidance Service for the Visually Impaired Using Real-time Image Processing Technology Based on Deep Learning," Proceedings of Korea Information and Communications Society Conference, Vol. 76, No. 1, pp. 126-127, 2021 (in Korean).
  7. S. Virtue, A. Vidal-Puig, "GTTs and ITTs in Mice: Simple Tests, Complex Answers," Nature Metabolism, Vol. 3, No. 7, pp. 1-4, 2021. https://doi.org/10.1038/s42255-021-00340-8
  8. https://www.aihub.or.kr/aihubdata/data/
  9. J. Redmon, S. Divvala, R. Girshick, A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016.
  10. Y. H. Lee, Y. S. Kim, "Comparison of CNN and YOLO for Object Detection," Journal of the Semiconductor & Display Technology, Vol. 19, No. 1, pp. 85-92, 2020 (in Korean).
  11. J. W. Park, Y. J. Kim, "A Study on Deep Learning Performance Improvement Based on YOLOv5," Proceedings of the Korean Institute of Communication Sciences Conference, pp. 1592-1593, 2022 (in Korean).
  12. S. H. Han, D. S. Park, C. M. Lim, J. W. Jeong, "Convenience Store Product Recognition Application for the Blind," Proceedings of the Korea Information Processing Society Conference, Vol. 28, No. 2, pp. 1298-1301, 2021 (in Korean).
  13. Z. Eaton-Rosen, Felix J. S. Bragman, S. Ourselin, M. Jorge Cardoso, "Improving Data Augmentation for Medical Image Segmentation," 1st Conference on Medical Imaging with Deep Learning (MIDL 2018), Amsterdam, The Netherlands, pp. 53, 2018.
  14. S. H. Park, J. H. Kim, "Trends in Data Augmentation Techniques for Deep Learning Models," Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp. 1051-1052, 2021 (in Korean).
  15. B. Kwon, Y. Kim, H. Lee, "A Data Augmentation Approach to 28GHz Path Loss Modeling Using CNNs," 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Bali, Indonesia, pp. 825- 829, 2023.
  16. S. AbuSalim, N. Zakaria, N. Mokhtar, S. A. Mostafa, S. J. Abdulkadir, "Data Augmentation on Intra-Oral Images Using Image Manipulation Techniques," 2022 International Conference on Digital Transformation and Intelligence (ICDI), Kuching, Sarawak, Malaysia, pp. 117-120, 2022.
  17. M. J. Park, C. S. Ryu, Y. S. Kang, H. Y. Song, H. C. Baek, K. S. Park, E. R. Kim, J. K. Park, S. H. Jang, "Sorghum Panicle Detection Using YOLOv5 based on RGB Image Acquired by UAV System," Korean Journal of Agricultural and Forest Meteorology, Vol. 24, No. 4, pp. 295-304, 2022 (in Korean). https://doi.org/10.5532/KJAFM.2022.24.4.295
  18. https://docs.ultralytics.com/yolov5/tutorials/tips_for_best_training_results/#model-selection