IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Analysis of Deep Learning-based Image Super Resolution Methods

딥 러닝 기반의 초해상도 이미지 복원 기법 성능 분석

  • Received : 2020.02.03
  • Accepted : 2020.03.27
  • Published : 2020.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Convolutional Neural Networks (CNN) have been used extensively in recent times to solve image classification and segmentation problems. However, the use of CNNs in image super-resolution problems remains largely unexploited. Filter interpolation and prediction model methods are the most commonly used algorithms in super-resolution algorithm implementations. The major limitation in the above named methods is that images become totally blurred and a lot of the edge information are lost. In this paper, we analyze super resolution based on CNN and the wavelet transform super resolution method. We compare and analyze the performance according to the number of layers and the training data of the CNN.

Keywords

References

  1. S. Park, M. Park, M. Kang, "Super-resolution Image Reconstruction : A Technical Overview," Journal of IEEE Transactions on Signal Processing Magazine, Vol. 20, No. 3, pp. 21-36, 2003. https://doi.org/10.1109/MSP.2003.1203207
  2. M. Irani, S. Peleg, "Improving Resolution by Image Registration," Journal of Computer Vision Graphical Image Processing : Graphical Models and Image Processing, Vol. 53, No. 3, pp. 231-239, 1991.
  3. R. R. Schultz, R. L. Stevenson, "Extraction of High-resolution Frames from Video Sequences," Journal of IEEE Transactions on Image Processing, Vol. 5, No. 6, pp. 996-1011, 1996. https://doi.org/10.1109/83.503915
  4. J. Yang, J. Wright, T. S. Huang, Y. Ma, "Image Super-resolution via Sparse Representation," Journal of IEEE Transactions on Image Processing, Vol. 19, No. 11, pp. 2861-2873, 2010. https://doi.org/10.1109/TIP.2010.2050625
  5. Freeman W. T, Jonesm T. R, Pasztor E. C. "Example-based Super-resolution," Journal of IEEE Transactions on Computer Graphics and Applications, Vol. 22, No. 2, pp. 56-65, 2002. https://doi.org/10.1109/38.988747
  6. K. Simonyan, A. Zisserman, "Very Deep Convolutional Networks for Large-scale Image Recognition," pp. 1-14, 2015.
  7. Lim, Bee, "Enhanced Deep Residual Networks for Single Image Super-resolution," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 136-144, 2017.
  8. Dong, Chao, "Image Super-resolution Using Deep Convolutional Networks" Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 38, No. 2, pp. 295-307, 2016. https://doi.org/10.1109/TPAMI.2015.2439281
  9. J. Kim, J. Lee, K. Lee. "Accurate Image Super-resolution Using Very Deep Convolutional Networks" Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646-1654, 2016.
  10. Guo, Tiantong, "Deep Wavelet Prediction for Image Super-resolution," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 104-113, 2017.
  11. H. Lee, H.Y. Jung, G.S. Choi, "Super-Resolution Based on Convolutional Neural Network Training Wavelet Transform Data," Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp. 268-269, 2017 (in Korean).
  12. O. Russakovsky, D. Jia, S. Hao, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, F.-F. Li, "ImageNet Large Scale Visual Recognition Challenge," International Journal of Computer Vision, Vol. 115, No. 3, pp. 211-252, 2015. https://doi.org/10.1007/s11263-015-0816-y
  13. H. D. Nguyen, "Deep Learning-based SISR (Single Image Super Resolution) Method Using RDB (Residual Dense Block) and Wavelet Prediction Network," Korea Polytechnic University M.S thesis, 2019.
  14. Y. Bengio, P. Simard, P. Frasconi, "Learning Long-term Dependencies with Gradient Descent is Difficult. Neural Networks," Journal of IEEE Transactions on Vol. 5, No. 2, pp.157-166, 1994.
  15. D. Martin, C. Fowlkes, D. Tal, J. Malik, "A Database of Human Segmented Natural Images and Its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics," Proceedings of IEEE Conference on Computer Vision, pp. 416-423, 2001.
  16. J. Yang, J. Wright, T. S. Huang, Y. Ma, "Image Superresolution via Sparse Representation," Journal of IEEE Transactions on Image Processing, Vol. 19, No. 11, pp. 2861-2873, 2010. https://doi.org/10.1109/TIP.2010.2050625
  17. C. Bevilacqua, A. Roumy, M. Morel, "Low-complexity Single-image Super-resolution Based on Nonnegative Neighbor Embedding," Proceedings of British Machine Vision, pp. 1-10, 2012.
  18. R. Zeyde, M. Elad, M. Protter, "On Single Image Scale-up Using Sparse-representations. In Curves and Surfaces," Proceedings of International Conference on Curves and Surfaces, pp. 711-730, 2012.
  19. S. Mallat, A Wavelet Tour of Signal Processing: the Sparse Way, Academic press, 2008.
  20. R. Timofte, E. Agustsson, L. Van Gool, M.-H. Yang, L. Zhang, "Ntire 2017 Challenge on Single Image Super-resolution: Methods and Results," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 114-125, 2017.