본문 바로가기
KERD
논문KCI 등재

대형 이미지 데이터셋 구축을 위한 이미지 이진화 기반데이터 증강 기법

Data augmentation technique based on image binarization for constructing large-scale datasets

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

초록

딥러닝은 다양한 컴퓨터 비전 문제를 해결할 수 있지만, 대량의 데이터셋이 필요하다. 본 논문에서는 대형 이미지 데이터셋을 구축하기 위해 이미지 이진화 기반 데이터 증강 기법을 제안한다. 이미지 이진화를 사용하여 특성을 추출하고 추출된 나머지 픽셀을랜덤하게 배치하여 새로운 이미지를 생성한다. 생성된 이미지는 원본 이미지와 유사한 품질을 보여주며, 딥러닝 모델에서도 뛰어난성능을 보였다.

Abstract

Deep learning can solve various computer vision problems, but it requires a large dataset. Data augmentationtechnique based on image binarization for constructing large-scale datasets is proposed in this paper. By extractingfeatures using image binarization and randomly placing the remaining pixels, new images are generated. Thegenerated images showed similar quality to the original images and demonstrated excellent performance in deeplearning models

참고문헌 (16)

  1. Tang, H., "A survey on multimodal deep learning for image synthesis: Applications, methods, datasets, evaluation metrics, and results comparison", IEEE Access, 8, pp.919~145 (2020)[DOI]
  2. Connor Shorten, "A survey on Image Data Augmentation for Deep Learning", Journal of Big Data, 6(1), pp.1~48 (2019), Springer Science and Business Media LLC[DOI]
  3. Lin, T. -Y., "Focal loss for dense object detection", Proceedings of the IEEE international conference on computer vision, pp.2980~2988 (2018)
  4. Zhong, Z., "Random erasing data augmentation", IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(2), pp.564~578 (2018)[DOI]
  5. Gao, Y., "Augmenting supervised neural networks with unsupervised objectives for large-scale image classification", Proceedings of the IEEE International Conference on Computer Vision, pp.2624~2633 (2019)
  6. Zhao, H., "augmentation for dataefficient GAN training", Proceedings of the IEEE, 2020, 6489~6498
  7. Siddiquee, M. R., "AugmentGAN: Deep Learning Augmentation for Medical Image Segmentation", IEEE Access, 7, pp.113305~113314 (2019)
  8. Connor Shorten, "A survey on Image Data Augmentation for Deep Learning", Journal of Big Data, 6(1), pp.1~48 (2019), Springer Science and Business Media LLC[DOI]
  9. Niblack, W., "Adaptive thresholding using the integral image", Proceedings of the workshop on Document Analysis Systems, pp.21~28 (1994)
  10. Nobuyuki Otsu, "A Threshold Selection Method from Gray-Level Histograms", IEEE Transactions on Systems, Man, and Cybernetics, 9(1), pp.62~66 (1979), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  11. Deng, J., "ImageNet: A Large-Scale Hierarchical Image Database", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2009)
  12. Z. Wang, "Image Quality Assessment: From Error Visibility to Structural Similarity", IEEE Transactions on Image Processing, 13(4), pp.600~612 (2004), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  13. Wang, Z., "Multiscale structural similarity for image quality assessment", Proceedings of the Thirty-Seventh Asilomar Conference on Signals, Systems &Computers, 2, pp.1398~1402 (2003)
  14. H.R. Sheikh, "Image information and visual quality", IEEE Transactions on Image Processing, 15(2), pp.430~444 (2006), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  15. Jocher, Glenn, "YOLOv5: A Universal Object Detector Made for Production", arXiv preprint arXiv:2104.02123, ~ (2021)
  16. He, Kaiming, "Deep Residual Learning for Image Recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp.770~778 (2016)

관련 논문AI추천

이 간행물의 다른 논문 (17건)