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

  • 제52권3호
  • /
  • Pages.154-161
  • /
  • 2015
  • /
  • 2287-5026(pISSN)
  • /
  • 2288-159X(eISSN)
대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지
DOI QR코드

DOI QR Code

멀티프레임 예제기반 초해상도 영상복원을 이용한 UHD TV 영상 개선

UHD TV Image Enhancement using Multi-frame Example-based Super-resolution

  • 정석화 (중앙대학교 첨단영상대학원) ;
  • 윤인혜 (중앙대학교 첨단영상대학원) ;
  • 백준기 (중앙대학교 첨단영상대학원)
  • Jeong, Seokhwa (Dept. of Image Engineering, Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University) ;
  • Yoon, Inhye (Dept. of Image Engineering, Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University) ;
  • Paik, Joonki (Dept. of Image Engineering, Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University)
  • 투고 : 2014.12.11
  • 심사 : 2015.03.03
  • 발행 : 2015.03.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

기존의 예제기반 초해상도 복원은 다수의 외부영상을 이용한 사전 생성 방법과 단일 영상을 이용한 자기참조 예제기반 복원 방법이 있지만, 입력영상의 특성과 패치사전에 따라 복원 성능이 저하되는 문제점이 있다. 이러한 문제점을 개선하기 위해서, 본 논문에서는 멀티 프레임의 움직임 정보를 이용하여 적응적 패치 선택을 통한 초해상도 영상복원 방법을 제안한다. 제안하는 초해상도 영상 복원 방법은 3가지 단계로 구성된다. i) 인접한 프레임간의 움직임 정보를 이용한 로컬 영역을 정의, ii) 단계적 열화를 이용한 적응적 패치 검색 방법, iii) 최적의 패치검색을 통한 패치 결합 및 초고해상도 영상복원이다. 결과적으로 제안하는 방법은 인접한 프레임간의 움직임 정보와 단계적 열화를 이용하여 패치를 검색함으로써 패치 검색의 정확성을 높여주고, 동영상에서 부자연스러운 현상이 제거된 초해상도 영상 복원이 가능하다. 실험결과에서는 기존의 초해상도 영상복원 방법과 비교할 때 복원 부작용이 감소되어 자연스럽게 복원된 영상을 제공하는 동시에, peak-to-peak signal noise ratio (PSNR)과 structural similarity measure (SSIM)를 사용한 객관적 성능 향상을 보인다.

A novel multiframe super-resolution (SR) algorithm is presented to overcome the limitation of existing single-image SR algorithms using motion information from adjacent frames in a video. The proposed SR algorithm consists of three steps: i) definition of a local region using interframe motion vectors, ii) multiscale patch generation and adaptive selection of multiple optimum patches, and iii) combination of optimum patches for super-resolution. The proposed algorithm increases the accuracy of patch selection using motion information and multiscale patches. Experimental results show that the proposed algorithm performs better than existing patch-based SR algorithms in the sense of both subjective and objective measures including the peak signal-to-noise ratio (PSNR) and structural similarity measure (SSIM).

키워드

참고문헌

  1. T. Lehmann, C. Gonner, and K. Spitzer, "Survey: interpolation methods in medical image processing," IEEE Trans. Medical Imaging, vol1. 18, no. 11, pp. 1049-1075, November 1999. https://doi.org/10.1109/42.816070
  2. W. Freeman, T. Jones, and E. Pasztor, "Example-based super-resolution," IEEE Computer Graphics and Applications, vol. 22, no. 2, pp. 56-65, March/April 2002. https://doi.org/10.1109/38.988747
  3. D. Glasner, S. Bagon, and M. Irani, "Super-resolution from a single image," Proc. IEEE Int. Conf. Computer Vision, pp. 349-356, September 2009.
  4. G. Freedman and R. Fattal, "Image and video upscaling from local self-examples," ACM Trans. Graphics, vol. 30, no. 2, pp. 12.1-12.11, April 2011.
  5. S. Farsiu, M. Robinson, M. Elad, and P. Milanfar, "Fast and robust multiframe super resolution," IEEE Trans. Image Processing, vol. 13, no. 10, pp. 1327-1344, October 2004. https://doi.org/10.1109/TIP.2004.834669
  6. S. Farsiu, M. Elad, and P. Milanfar, "Multiframe demosaicing and super-resolution of color images," IEEE Trans. Image Processing, vol. 15, no. 1, pp. 141-159, January 2006. https://doi.org/10.1109/TIP.2005.860336
  7. W. Bai, J. Liu, M. Li, and Z. Guo, "Multi-frame super-resolution using refined exploration of extensive self-examples," MMM, pp. 403-413, January January 2013.
  8. C. Cho, J. Jeon, and J. Paik, "Example-based super-resolution using self-patches and approximated constrained least squares filter," Proc. IEEE Int. Conf. Image Processing, pp. 2140-2144, October 2014.
  9. S. Jeong, I. Yoon, J. Jeon, and J. Paik, "Multi-frame example-based super-resolution using locally directional self-similarity," Proc. IEEE Int. Conf. Consumer Electronics, to appear, January 2015.
  10. L. Xu, S. Zheng, and J. Jia, "Unnatural L0 sparse representation for natural image deblurring," in Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1107-1114, June 2013.
  11. C. Shen, W. Hwang, and S. Pei, "Spatially-varying out-of-focus image deblurring with L1-2 optimization and a guided blur map," in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, pp. 1069-1072, March 2012.
  12. J. Yang, J. Wright, T. Huang, and Y. Ma, "Image super resolution via sparse representation," IEEE Trans. Image Processing, vol. 19, no. 11, pp. 2861-2873, November 2010. https://doi.org/10.1109/TIP.2010.2050625
  13. S. H. Kim, S. B. Cho, "Super-Resolution Algorithm Using Motion Estimation for Moving Vehicles", Jounal of The Institute of Electronics Engineers of Korea, vol. 49SP, no.4, pp. 23-31, July 2012.

피인용 문헌

  1. 복수영상기반 초해상도 색상인식능력향상 알고리즘의 무인기 적용 vol.45, pp.3, 2017, https://doi.org/10.5139/jksas.2017.45.3.180