earticle

논문검색

An Improved Fast Nonlocal Means Filter Using Patch-oriented 2DPCA

초록

영어

In former work [18], we propose a scheme to more efficiently preselect similar patches for the nonlocal means filter, based on the Patch-oriented two-dimensional principal component analysis (2DPCA) technique. Although the method can yield good results, the computational complexity remains high. For this reason, in this paper we proposed an improvement of the work, which is fast and directly employs features extracted by the patch-oriented 2DPCA to compute the weights. The new approach has been tested on a commonly-used standard test image database. The results demonstrate that our method can significantly improve the denoising effect.

목차

Abstract
 1. Introduction
 2. NL-means Filter Methods
 3. The Fast 2DPCA based NL-means Filter
 4. Experimental Results
 5. Conclusion
 Acknowledgements
 References

저자정보

  • Yuhui Zheng School of Computer and Software, Nanjing University of Information Science and Technology
  • Jianwei Zhang College of Math and Statistics, Nanjing University of Information Science and Technology
  • Shunfeng Wang College of Bin Jiang, Nanjing University of Information Science and Technology
  • Jin Wang School of Computer and Software, Nanjing University of Information Science and Technology
  • Yunjie Chen College of Math and Statistics, Nanjing University of Information Science and Technology

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

      0개의 논문이 장바구니에 담겼습니다.