The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Image Classification using Deep Learning-Based Transfer Learning

딥 러닝 기반의 전이 학습을 이용한 이미지 분류에 관한 연구

  • Jung-Hee Seo (Dept. of Computer Engineering, Tongmyong University)
  • 서정희 (동명대학교 컴퓨터공학과)
  • Received : 2023.04.11
  • Accepted : 2023.06.17
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

For a long time, researchers have presented excellent results in the field of image retrieval due to many studies on CBIR. However, there is still a semantic gap between these search results for images and human perception. It is still a difficult problem to classify images with a level of human perception using a small number of images. Therefore, this paper proposes an image classification model using deep learning-based transfer learning to minimize the semantic gap between images of people and search systems in image retrieval. As a result of the experiment, the loss rate of the learning model was 0.2451% and the accuracy was 0.8922%. The implementation of the proposed image classification method was able to achieve the desired goal. And in deep learning, it was confirmed that the CNN's transfer learning model method was effective in creating an image database by adding new data.

오래전부터 연구자들은 CBIR에 대한 많은 연구로 인해 이미지 검색 분야에 우수한 결과를 제시하였다. 그러나 이미지에 대한 이러한 검색 결과와 사람이 인식하는 결과 사이에 의미적 격차는 여전히 존재한다. 적은 수의 이미지를 사용하여 사람이 인식하는 수준의 이미지를 분류하는 것은 아직까지 어려운 문제이다. 따라서 본 논문은 이미지 검색에서 사람과 검색 시스템의 이미지의 의미적 격차를 최소화하기 위해 딥 러닝 기반의 전이 학습을 이용한 이미지 분류 모델을 제안한다. 실험 결과, 학습 모델의 손실률은 0.2451%, 정확도는 0.8922%로 제안한 이미지 분류 방법의 구현은 원하는 목표를 달성할 수 있었다. 그리고 딥 러닝에서 CNN의 전이 학습 모델 방법이 새로운 데이터를 추가하여 이미지 데이터베이스를 구축하는데 효과적인 결과를 확인할 수 있었다.

Keywords

References

  1. W. Plant and G. Schaefer, "Image Retrieval on the Honeycomb Image Browser," Proceedings of 2010 IEEE 17th International Conference on Image Processing, Hong Kong, Sept. 2010, pp. 3161-3164.
  2. J. Chen, J.-L. Shen, J. Zhang, and K. Wangsa, "A Novel Multimedia Database System for Efficient Image/Video Retrieval Based On Hybrid-Tree Structure," Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, Dalian, Aug. 2006, pp. 4353-4358.
  3. A. Barman and S. K. Shah, "A Graph-Based Approach for Making Consensus-Based Decisions in Image Search and Person Re-Identification," IEEE Transactions On Pattern Analysis And Machine Intelligence, vol. 43, no. 3, Mar. 2021, pp. 753-765. https://doi.org/10.1109/TPAMI.2019.2944597
  4. D. Edmundson and G. Schaefer, "A Browsing Approach To Online Photo Search Results," IEEE Transactions On Pattern Analysis And Machine Intelligence, vol. 43, no. 3, Mar. 2021, pp. 753-765. https://doi.org/10.1109/TPAMI.2019.2944597
  5. A. J. M. Traina, S. Brinis, G. V. Pedrosa, L. P. S. Avalhais, and C. T. Jr., "Querying on large and complex databases by content: Challenges on variety and veracity regarding real applications," Information Systems, vol. 86, 2019, pp. 10-27. https://doi.org/10.1016/j.is.2019.03.012
  6. J. Ye, Z. Xu, and Y. Ding, "Image search scheme over encrypted database," Future Generation Computer System, vol. 87, 2018, pp. 251-258. https://doi.org/10.1016/j.future.2018.02.045
  7. Y. Liu, Y. Peng, D. Hu, Da. Li, K. P. Lim, and N. Ling, "Image Retrieval using CNN and Low-level Feature Fusion for Crime Scene Investigation Image Database," Proceedings, APSIPA Annual Summit and Conference, Hawaii, U.S.A., Nov. 2018, pp. 1208-1214.
  8. L. Zhu, W. Yu, C. Zhang, Z. Zhang, F. Huang, and H. Yu, "SVS-JOIN: Efficient Spatial Visual Similarity Join for Geo-Multimedia," Proceedings, APSIPA Annual Summit and Conference, Hawaii, U.S.A., Nov. 2018, pp. 1208-1214.
  9. H. Jiang, Z. Diao, T. Shi, Y. Zhou, F. Wang, W. Hu, X. Zhu, S. Luo, G. Tong, and Y.-D. Yao, "A review of deep learning-based multiple-lesion recognition from medical images: classification, detection and segmentation," Computers in Biology and Medicine, vol. 157, May 2023, pp. 1-22.
  10. S. Kadry, R. G. Crespo, E. Herrera-Viedma, S. Krishnamoorthy, and V. Rajinikanth, "Classification of Breast Thermal Images into Healthy/Cancer Group Using Pre-Trained Deep Learning Schemes," Procedia Computer Science, vol. 218, 2023, pp. 24-34.
  11. G. R. d. Silva, I. B. Rosmaninho, E. Zancul, V. R. d. Oliveira, G. R. Francisco, N. F. d. Santos, K. d. M. Macedo, A. J. d. Silva, E. K. d. Lima, M. E. B. Lemo, A. Maldonado, M. E. G. Moura, F. H. d. Silva, and G. S. Guimaraes, "Image dataset of urine test results on petri dishes for deep learning classification," Data in Brief, vol. 47, 2023, pp. 1-8.
  12. F. H. D. Araujo, R. R. V. Silva, F. N. S. Medeiros, D. D. Parkinson, A. Hexemer, C. M. Carneiro, and D. M. Ushizima, "Reverse image search for scientific data within and beyond the visible spectrum," Export Systems With Applications, vol. 109, 2018, pp. 35-48. https://doi.org/10.1016/j.eswa.2018.05.015
  13. R. Zhang and Z. Zhang, "Effective Image Retrieval Based on Hidden Concept Discovery in Image Database," IEEE Transactions on Image Processing, vol. 16, no. 2, Feb. 2007, pp. 562-572. https://doi.org/10.1109/TIP.2006.888350
  14. J. Wang, W.-J. Yang, and R. Acharya, "Efficient Access to and Retrieval from a Shape Image Database," IEEE Transactions on Image Processing, vol. 16, no. 2, Feb. 2007, pp. 562-572. https://doi.org/10.1109/TIP.2006.888350
  15. P. Punitha and D. S. Guru, "An Effective and Efficient Exact Match Retrieval Scheme for Symbolic Image Database Systems Based on Spatial Reasoning: A Logarithmic Search Time Approach," IEEE Transactions on Knowledge and Data Engineering, vol. 18, no. 10, Oct. 2006, pp. 1368-1381. https://doi.org/10.1109/TKDE.2006.154
  16. E. Valle, M. Cord, and S. Philipp-Foliguet, "3-Way-Trees: A Similarity Search Method For High-Dimensional Descriptor Matching," IEEE Transactions on Knowledge and Data Engineering, vol. 18, no. 10, Oct. 2006, pp. 1368-1381. https://doi.org/10.1109/TKDE.2006.154
  17. X. Li, X. Yang, Z. Ma, and J.-H. Xue, "Deep metric learning for few-shot image classification: A Review of recent developments," Pattern Recognition, vol. 138, 2023, pp. 1-15.
  18. E. Alibek and K. C. Kim, "Metal Surface Defect Detection and Classification using EfficientNetV2 and YOLOv5", J. of The Korea Institute of Electronic Communication Sciences, vol. 17, no. 4, 2022. pp. 577-586,
  19. S. Park and S. Yoo , "Avocado Classification and Shipping Prediction System based on Transfer Learning Model for Rational Pricing, J. of The Korea Institute of Electronic Communication Sciences, vol. 18, no. 2, 2023, pp. 329-336.