The Journal of Bigdata (한국빅데이터학회지)

Korea Bigdata Society (한국빅데이터학회)
권호 표지
DOI QR코드

DOI QR Code

Food Image Classification using Deep Learning

딥러닝을 이용한 음식 이미지 분류 기술 개발

  • 이가경 (한국항공대학교 소프트웨어학과) ;
  • 임세연 (한국항공대학교 소프트웨어학과) ;
  • 양진이 (한국항공대학교 인공지능학과) ;
  • 유민정 (한국항공대학교 인공지능학과) ;
  • 김선옥 (한국항공대학교 인공지능학과)
  • Received : 2023.11.24
  • Accepted : 2023.12.14
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study was conducted with the aim of improving the food image classification model of a health care application targeting Koreans in their twenties. 546,194 images were collected from the Public Data Portal and AI Hub, and 175 food classes were constructed. The ResNet artificial intelligence model was trained and validated. Additionally, we deeply investigated the reasons for the relatively lower recognition accuracy of the actual food images, and we attempted various methods to optimize the model's performance as a solution.

본 연구는 20대와 한국인을 대상으로 한 건강관리 애플리케이션의 음식 이미지 분류 모델을 개선하는 것을 목표로 진행되었다. AI Hub에서 546,194개의 이미지를 수집하여 175개의 음식 클래스를 구성하였으며, ResNet 인공지능 모델을 학습하고 검증하였다. 추가적으로, 실제 촬영한 음식 이미지에 대한 인식 정확도가 상대적으로 낮게 나타나는 원인에 대해 고찰하고, 이를 해결하기 위한 방안으로 모델 성능을 최적화를 위한 다양한 방법을 분석하였다.

Keywords

Acknowledgement

이 출판물은 2021년도 한국항공대학교 교비지원 연구비에 의하여 지원된 연구의 결과임. 이 연구는 과학기술정보통신부의 재원으로 한국지능정보사회진흥원의 지원을 받아 구축된 "건강관리를 위한 음식 이미지", "음식 이미지 및 영양 정보 텍스트"을 활용하여 수행된 연구입니다. 본 연구에 활용된 데이터는 AI 허브(aihub.or.kr)에서 다운로드 받으실 수 있습니다.

References

  1. 김미현, 연지영, "충청지역 일부 대학생의 코로나-19 이후 식생활 변화, 가정간편식과 배달음식 이용 실태," Journal of Nutrition and Health, vol. 54, no. 4, pp. 383-397, 2021. https://doi.org/10.4163/jnh.2021.54.4.383
  2. K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778.
  3. Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems 25 (2012).
  4. Sultana, Farhana, Abu Sufian, and Paramartha Dutta. "Advancements in image classification using convolutional neural network." 2018 Fourth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN). IEEE, 2018.
  5. Rawat, Waseem, and Zenghui Wang. "Deep convolutional neural networks for image classification: A comprehensive review." Neural computation 29.9 (2017): 2352-2449. https://doi.org/10.1162/neco_a_00990
  6. Paszke, Adam, et al. "Pytorch: An imperative style, high-performance deep learning library." Advances in neural information processing systems 32 (2019).
  7. Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
  8. Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).
  9. Huang, Gao, et al. "Densely connected convolutional networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
  10. Xie, Saining, et al. "Aggregated residual transformations for deep neural networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
  11. Liang, Jiazhi. "Image classification based on RESNET." Journal of Physics: Conference Series. Vol. 1634. No. 1. IOP Publishing, 2020.
  12. Ebrahimi, Mohammad Sadegh, and Hossein Karkeh Abadi. "Study of residual networks for image recognition." Intelligent Computing: Proceedings of the 2021 Computing Conference, Volume 2. Springer International Publishing, 2021.
  13. Zhang, Qi. "A novel Res Net101 model bas ed on dense dilated convolution for image classification." SN Applied Sciences 4 (2022): 1-13. https://doi.org/10.1007/s42452-021-04881-1
  14. Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
  15. Girshick, Ross. "Fast r-cnn." Proceedings of the IEEE international conference on computer vision. 2015.
  16. Jung, Heechul, et al. "ResNet-based vehicle classification and localization in traffic surveillance systems." Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2017.
  17. Song, Xingguo, Kewei Chen, and Zhongqing Cao. "ResNet-based image classification of railway shelling defect." 2020 39th Chinese Control Conference (CCC). IEEE, 2020.
  18. Yahya, Ali Abdullah, et al. "A Novel Image Classification Method Based on Residual Network, Inception, and Proposed Activation Function." Sensors 23.6 (2023): 2976.