Journal of the Institute of Electronics and Information Engineers (전자공학회논문지)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지
DOI QR코드

DOI QR Code

Super-resolution Algorithm using Local Structure Analysis and Scene Adaptive Dictionary

국부 구조 분석과 장면 적응 사전을 이용한 초고해상도 알고리즘

  • Received : 2012.12.13
  • Published : 2013.04.25
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a new super-resolution algorithm where sharpness enhancement is merged in order to improve overall visual quality of up-scaled images. In the learning stage, multiple dictionaries are generated according to sharpness strength, and a proper dictionary among those dictionaries is selected to adapt to each patch in the inference stage. Also, additional post-processing suppresses boosting of artifacts in input low-resolution images during the inference stage. Experimental results that the proposed algorithm provides 0.3 higher CPBD than the bi-cubic and 0.1 higher CPBD than Song's and Fan's algorithms. Also, we can observe that the proposed algorithm shows better quality in textures and edges than the previous works. Finally, the proposed algorithm has a merit in terms of computational complexity because it requires the memory of only 17% in comparison with the previous work.

본 논문에서는 상호 보완 관계에 있는 초고해상도 기법과 선명도 증강 기법을 통합하여 전체적인 화질을 향상시키는 새로운 초고해상도 기법을 제안한다. 먼저 학습 과정을 통해 선명도 증강의 세기에 따라 다중의 사전을 구성하고, 고 해상도 영상을 합성할 때 영상의 국부 영역 특성에 따라 서로 다른 사전을 적응적으로 참조하도록 한다. 또한, 추가적인 후처리 과정을 통하여 저해상도 영상에 내재되어 있는 아티팩트가 초고해상도 처리에 의해 증폭되는 현상을 감소시켜 화질을 극대화한다. 모의실험 결과에 따르면 제안한 알고리즘은 객관적 화질 측면에서 비교 대상이 되는 알고리즘들에 비하여 우수함을 보였다. 특히, 영상의 선명도를 나타내는 CPBD 측면에서 bi-cubic 대비 0.3, Song 기법과 Fan 기법 대비 0.1 높게 나타났다. 또한, 주관적 화질 측면에서 영상의 질감 영역 및 경계 영역의 화질이 향상된 결과를 보이는 것을 확인하였다. 제한된 방법은 기존 방법 대비 17% 정도의 메모리만을 필요로 하므로 구현 관점에서도 장점이 있음을 알 수 있다.

Keywords

References

  1. S. C. Park, M. K. Park and M. G. Kang, "Super-resolution image reconstruction: a technical overview," IEEE Sig. Proc. Magazine, pp. 21-36, 2003.
  2. S. Farsiu, D. Robinson, M. Elad and P. Milanfar, "Fast and robust multiframe super resolution," IEEE Trans. Image Processing, vol. 13, no. 10, pp. 1327-1344, 2004. https://doi.org/10.1109/TIP.2004.834669
  3. C. Liu and D. Sun, "A bayesian approach to adaptive video super resolution," in Proc. IEEE CVPR, pp. 209-216, 2011.
  4. J. D. Ouwerkerk, "Image super-resolution survey," Image Communication, vol. 24, pp. 1039-1052, 2006.
  5. H. S. Hou and H. C. Andrews, "Cubic Spline for image Interpolation and Digital filtering," IEEE Trans, Acoustics, Speech, Signal Process, vol. 26, no. 6, pp. 508-517, 1978. https://doi.org/10.1109/TASSP.1978.1163154
  6. J. Allebach and P. W. Wong, "Edge-Directed Interpolation," Proc. Int. Conf. Image Process., vol. 3, pp. 707-710, 1996.
  7. X. Li and M. Orchard, "New Edge-Directed Interpolation," IEEE Trans. Image Processing, vol.10, no. 10, pp. 1521-1527, 2001. https://doi.org/10.1109/83.951537
  8. Q. Wang and R. Kreidieh, "A New Oriental-Adaptive Interpolation Method," IEEE Trans. Image Processing, vol. 16, no. 4, pp. 889-900, 2007. https://doi.org/10.1109/TIP.2007.891794
  9. S. M. Kwak, J. H. Moon, and J. K. Han, "Modified Cubic Convolution Scaler for Edge-Directed Nonuniform Data," Optical Eng., vol. 46, no. 10, 107001, 2007. https://doi.org/10.1117/1.2789639
  10. W. T. Freeman, T. R. Jones and E. C. Pasztor, "Example-based super-resolution," IEEE Comput. Graph. Appl., vol. 22, pp. 56-65, 2002.
  11. W. Fan and D. Yeung, "Image hallucination using neighbor embedding over visual manifolds,"in Proc. IEEE CVPR, pp. 1-7, 2007.
  12. Y. W. Tai, S. Liu, M. S. Brown and S. Lin, "Super resolution using edge prior and single image detail synthesis,"in Proc. IEEE CVPR, pp. 2400-2407, 2010.
  13. J. Sun, J. Zhu and M. F. Tappen, "Context-constrained hallucination for image super-resolution," in IEEE CVPR, pp. 231-238, 2010.
  14. K. Zhang, X. Gao, X. Li and D. Tao, "Partially supervised neighbor embedding for example-based image super-resolution," IEEE JSTSP, vol. 5, no. 2, pp. 230-239, 2010.
  15. L. Shao, H. Zhang and G. Haan, "An overview and performance evaluation of classification-based least squares trained filters," IEEE Trans. Image Processing, vol. 17, no. 10, pp. 1772-1782, 2008. https://doi.org/10.1109/TIP.2008.2002162
  16. T. Kondo, T. Fujiwara, Y. Okumura and Y. Node, "Picture conversion apparatus picture conversion method learning apparatus and learning method," US patent 6,323,905B1, 2001.
  17. Y. U. Gang, S. C. Jeong and B. C. Song, "Fast content adaptive interpolation algorithm using one-dimensional patch-based learning," J. IEEK SP, vol. 48, no. 1, pp. 54-62, 2011.
  18. S. C. Jeong and B. C. Song, "Noise-robust superresolution based on a classified dictionary," J. Electronic Imaging, vol. 19, no. 4, 2010.
  19. X. Li, K. M. Lam, G. Qiu, L. Shen and S. Wang, "Example-based image super-resolution with class-specific predictors," J. Vis. Commun. Image R., vol. 20, pp 312-322, 2009. https://doi.org/10.1016/j.jvcir.2009.03.008
  20. A. Polesel, G. Ramponi and V. J. Mathews, "Image enhancement via adaptive unsharp masking," IEEE Trans. Image Processing, vol. 9, no. 3, pp. 505-510, 2000. https://doi.org/10.1109/83.826787
  21. N. D. Narvekar and L. J. Karam, "A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection," IEEE Quality of Multimedia Experience, pp. 87-91, 2009.