The Journal of Korea Robotics Society (로봇학회논문지)

Korea Robotics Society (한국로봇학회)
권호 표지
DOI QR코드

DOI QR Code

Data Augmentation Method of Small Dataset for Object Detection and Classification

영상 내 물체 검출 및 분류를 위한 소규모 데이터 확장 기법

  • Kim, Jin Yong (Dept. of Electrical and Computer Engineering, Pusan National University) ;
  • Kim, Eun Kyeong (Dept. of Electrical and Computer Engineering, Pusan National University) ;
  • Kim, Sungshin (School of Electrical and Computer Engineering, Pusan National University)
  • Received : 2020.01.29
  • Accepted : 2020.03.16
  • Published : 2020.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper is a study on data augmentation for small dataset by using deep learning. In case of training a deep learning model for recognition and classification of non-mainstream objects, there is a limit to obtaining a large amount of training data. Therefore, this paper proposes a data augmentation method using perspective transform and image synthesis. In addition, it is necessary to save the object area for all training data to detect the object area. Thus, we devised a way to augment the data and save object regions at the same time. To verify the performance of the augmented data using the proposed method, an experiment was conducted to compare classification accuracy with the augmented data by the traditional method, and transfer learning was used in model learning. As experimental results, the model trained using the proposed method showed higher accuracy than the model trained using the traditional method.

Keywords

References

  1. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, "Backpropagation applied to handwritten zip code recognition," Neural computation, vol. 1, no. 4, pp. 541-551, 1989, DOI: 10.1162/neco.1989.1.4.541.
  2. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, Columbus, OH, USA, 2014, DOI: 10.1109/CVPR.2014.81.
  3. R. Girshick, "Fast r-cnn," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, pp. 1440-1448, 2015, DOI: 10.1109/ICCV.2015.169.
  4. S. Ren, K. He, R. Girshick, and 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, June, 2015, DOI: 10.1109/TPAMI.2016.2577031.
  5. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 779-788, 2016, DOI: 10.1109/CVPR.2016.91.
  6. J. Wang and L. Perez, "The effectiveness of data augmentation in image classification using deep learning," arXiv preprint arXiv: 1712.04621, 2017, [Online], https://arxiv.org/pdf/1712.04621.pdf.
  7. D. H. Kim, Manufacturing Transition: Smart Factory, [Online], https://brunch.co.kr/@duk-hyun/44, Accessed: Jan. 26, 2019.
  8. E. Dubrofsky, "Homography estimation," B. S. thesis dissertation, THE UNIVERSITY OF BRITISH COLUMBIA, Vancouver, Canada, 2009, [Online], https://www.cs.ubc.ca/grads/resources/thesis/May09/Dubrofsky_Elan.pdf.
  9. J. Y. Kim, "Performance Improvement of Deep Learning using Data Augmentation based on Perspective Transform and Image Synthesis," M.S thesis, Pusan National University, Busan, Korea, 2020, [Online], http://www.dcollection.net/handler/pusan/000000143862.
  10. H.-C. Shin, H. R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, J. Yao, D. Mollura, and R. M. Summers, "Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning," IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1285-1298, May, 2016, DOI: 10.1109/TMI.2016.2528162.