Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

Image Classification Model using web crawling and transfer learning

웹 크롤링과 전이학습을 활용한 이미지 분류 모델

  • Lee, JuHyeok (Dept. of Computer Science and Engineering, Hankyong National University) ;
  • Kim, Mi Hui (Dept. of Computer Science and Engineering, Hankyong National University)
  • Received : 2022.11.09
  • Accepted : 2022.12.19
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, to solve the large dataset problem, we collect images through an image collection method called web crawling and build datasets for use in image classification models through a data preprocessing process. We also propose a lightweight model that can automatically classify images by adding category values by incorporating transfer learning into the image classification model and an image classification model that reduces training time and achieves high accuracy.

딥러닝의 발전으로 딥러닝 모델들이 이미지 인식, 음성 인식 등 여러 분야에서 활발하게 사용 중이다. 하지만 이 딥러닝을 효과적으로 사용하기 위해서는 대형 데이터 세트가 필요하지만 이를 구축하기에는 많은 시간과 노력 그리고 비용이 필요하다. 본 논문에서는 웹 크롤링이라는 이미지 수집 방법을 통해서 이미지를 수집하고 데이터 전처리 과정을 거쳐 이미지 분류 모델에 사용할 수 있게 데이터 세트를 구축한다. 더 나아가 전이학습을 이미지 분류 모델에 접목해 카테고리값을 넣어 자동으로 이미지를 분류할 수 있는 경량화된 모델과 적은 훈련 시간 및 높은 정확도를 얻을 수 있는 이미지 분류 모델을 제안한다.

Keywords

Acknowledgement

This research was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No.2018R1A2B6009620)

References

  1. S. Y. Ahn, Y. M. Park, E. J. Lim, E. J. Lim, W. Choi, "Trends on Distributed Frameworks for Deep Learning," Electronics and Telecommunications Trends, Vol.31, No.3, pp.131-141,
  2. H. Kwon, Y. C. Kim, "Adversarial Case Technology Trends for Deep Learning Models," Institute of Information Security and Cryptology, Vol.31, No.2, pp.5-12, 2021. DOI: 10.1016/j.eng.2019.12.012
  3. J. H. Lee, H. M. Kim "Automated Image Classification Model Using Web Crawling," Proceedings of the Korea Information Processing Society Conference, pp.719-722, 2021. DOI: 10.3745/PKIPS.y2021m11a.719
  4. J. S. Kim, "A consideration on Big Data Utilization and Related Technologies," Review of Korea Contents Association, Vol.10, No.1, pp.34-40, 2012. https://doi.org/10.5392/JKCA.2012.12.03.034
  5. D. M. Seo, H. M. Jung, "Intelligent Web Crawler for Supporting Big Data Analysis Services," The Journal of the Korea Contents Association, Vol.13, No.12, pp.575-584, 2013. DOI: 10.5392/JKCA.2013.13.12.575
  6. Aurelien Geron, "Hands-On machine Learning with Scikit-Learn, Keras & TensorFlow 2nd Edition," O'Reilly Media, 2019.
  7. V. H Marin H. george, V. O. Elena. "A new generation of the IMAGIC image processing system," Journal of structural biology, Vol.160, pp.17-24, 1966. DOI: 10.1006/jsbi.1996.0004
  8. L. Schmarje, M. Santarossa, S. -M. Schroder and R. Koch, "A Survey on Semi-, Self- and Unsupervised Learning for Image Classification," in IEEE Access, Vol.9, pp.82146-82168, 2021. DOI: 10.1109/ACCESS.2021.3084358
  9. "Selenium", https://www.selenium.dev/ko/, 2021.
  10. "Chromedriver", https://sites.google.com/a/chromiumorg/chromedriver/, 2021.
  11. Z. Cui, Z. Gan, G. Tang, F. Liu, X. Zhu, "Image Signature Based Mean Square Error for image Quality Assessment," Chinese Journal of Electronics, Vol.24, No.4, pp.755-760, 2015. DOI: 10.1049/cje.2015.10.015
  12. K. He, X. Zhang, S. Ren, J. Sun "Deep Residual Learning for inage Recognition," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770-778, 2016. DOI: 10.48550/arXiv.1512.03385
  13. S. W. Park and D. Y. Kim, "Comparison of Image Classification Performance by Aivation Functions in Convolutional Neural Networks," Journal of Korea Multimedia Society, vol.21, no.10, pp.1142-1149, 2018. DOI: 10.9717/kmms.2018.21.10.1142
  14. J. B. Kong and M. S Jang "Association Analysis of Convolution Layer, Kernel and Accuracy in CNN," Journal of the KIECS. vol.14, no.6, pp.1153-1160, 2019. DOI: 10.13067/JKIECS.2019.14.6.1153