Scalable and Iterative Image Super-resolution using DCT Interpolation and Sparse Representation

Saulo R. S. Reis, Graça Bressan

Abstract

In a scenario where acquisition systems have limited resources or available images do not have good quality, super-resolution (SR) techniques are an excellent alternative for improving the image quality. The traditional SR methods proposed in the literature are effective in HR image reconstruction to a magnification factor up to 2. In recent years, example-based SR methods have shown excellent results in the HR image reconstruction to magnification factor 3 or more. In this paper, we propose a scalable and iterative algorithm for single-image SR using a two-step strategy with DCT interpolation and the sparse-based learning method. The method proposed implements some improvements in the dictionary training and the reconstruction process. A new dictionary is built by using an unsharp mask technique for feature extraction. The idea is to reduce the learning time by using two different small dictionaries. The results were compared with others interpolation-based and SR methods and demonstrated the effectiveness of the algorithm proposed in terms of PSNR, SSIM and Visual Quality.

References

  1. Aharon, M., Elad, M., Bruckstein, A., 2006. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing, vol. 54, no. 11, pp. 4311-4322.
  2. Aly H. A., Dubois E., 2005. Image Up-Sampling Using Total-Variation Regularization with a New Observation Model. IEEE Transactions on Image Processing, vol. 14, no. 10, pp. 1647-1659.
  3. Baker, S., Kanade, T., 2002. Limits on super-resolution and how to break them. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 9, pp. 1167-1183.
  4. Dong, W., Zhang, L., Shi, G., 2011. Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization. IEEE Transactions on Image Processing, vol. 20, no. 7, pp. 1838-1857, Jul, 2011.
  5. Elad, M., Datsenko, D., 2009. Example-Based Regularization Deployed to Super-Resolution Reconstruction of a Single Image. Computer Journal, vol. 52, no. 1, pp. 15-30.
  6. Freeman, W. T., Jones, T. R., Pasztor, E. C., 2002. Example-based super-resolution. IEEE Computer Graphics and Applications, vol. 22, no. 2, pp. 56-65, Mar-Apr.
  7. Garcia, D. C., Dorea, C., Queiroz, R. L., 2012. Super Resolution for Multiview Images Using Depth Information. IEEE Transactions on Circuits and Systems for Video Technology, vol. 22, no. 9, pp. 1249-1256.
  8. Gonzalez, R. C., Woods, R. E., 2010. Digital Image Processing, Pearson, Third Edition.
  9. Hung, E. M., Garcia, D.C., Queiroz, R.L.D., 2011. Transform domain semi-super resolution. in ICIP'11, pp. 1193-1196.
  10. Jia, K. , Wang, X. , Tang, X., 2013. Image Transformation Based on Learning Dictionaries across Image Spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 2, pp. 367-380.
  11. Jian, S., Nan-Ning, Z., Hai, T., 2003. Image hallucination with primal sketch priors. Proceedings. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. II-729-36 vol.2.
  12. Jiji, C. V. Chaudhuri, S., 2006. Single-frame image superresolution through contourlet learning. Eurasip Journal on Applied Signal Processing, 2006.
  13. Li X., Orchard M., 2001. New Edge-Directed Interpolation. IEEE Transactions on Image Processing. vol. 10, no. 10, pp. 1521-1527.
  14. Park, S. C., Park, M. K., Kang, M. G., 2003. Superresolution image reconstruction: A technical overview. IEEE Signal Processing Magazine, vol. 20, no. 3, pp. 21-36.
  15. Qiang, W., Xiaoou, T., Shum, H., 2005. Patch based blind image super resolution. Tenth IEEE International Conference on Computer Vision, 2005. ICCV 2005, pp. 709-716 Vol. 1.
  16. Sun, D., Cham, W. K., 2007. Postprocessing of low bitrate block DCT coded images based on a fields of experts prior. IEEE Transactions on Image Processing, vol. 16, no. 11, pp. 2743-2751.
  17. Wu, Z., Yu, H., Chen, C. W., 2010. A New Hybrid DCTWiener-Based Interpolation Scheme for Video Intra Frame Up-Sampling. IEEE Signal Processing Letters, vol. 17, no. 10.
  18. Yang, J., Wright, J., Huang, T. S., 2010. Image SuperResolution Via Sparse Representation. IEEE Transactions on Image Processing, vol. 19, no. 11.
  19. Yang, S., Wang M., Chen Y., 2012. Single-Image SuperResolution Reconstruction via Learned Geometric Dictionaries and Clustered Sparse Coding. IEEE Transactions on Image Processing, vol. 21, no. 9, pp. 4016-4028.
  20. Zeyde R., Elad, M., Protter, and M. 2010. On single image scale-up using sparse-representations. Proceedings of the 7th international conference on Curves and Surfaces. pp 711-730.
  21. Zhang, W., Cham, W. K., 2011. Hallucinating Face in the DCT Domain. IEEE Transactions on Image Processing, vol. 20, no. 10, pp 2769-2779.
  22. Zhang L., Xiaoling W., 2006. An Edge-Guided Image Interpolation Algorithm via Directional Filtering and Data Fusion. IEEE Transactions on Image Processing, vol. 15, no. 8, pp. 2226-2238.
  23. Zhou F., Yang, W. Liao, Q., 2012. Single Image SuperResolution Using Incoherent Sub-dictionaries Learning. IEEE Transactions on Consumer Electronics, vol. 58, no. 3, pp. 891-897.
  24. Zibetti, M. V. W., Bazan, F. S. V. Mayer, J., 2011, Estimation of the parameters in regularized simultaneous super-resolution. Pattern Recognition Letters, vol. 32, no. 1, pp. 69-78.
Download


Paper Citation


in Harvard Style

Reis S. and Bressan G. (2015). Scalable and Iterative Image Super-resolution using DCT Interpolation and Sparse Representation . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-089-5, pages 463-470. DOI: 10.5220/0005295304630470


in Bibtex Style

@conference{visapp15,
author={Saulo R. S. Reis and Graça Bressan},
title={Scalable and Iterative Image Super-resolution using DCT Interpolation and Sparse Representation},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={463-470},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005295304630470},
isbn={978-989-758-089-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2015)
TI - Scalable and Iterative Image Super-resolution using DCT Interpolation and Sparse Representation
SN - 978-989-758-089-5
AU - Reis S.
AU - Bressan G.
PY - 2015
SP - 463
EP - 470
DO - 10.5220/0005295304630470