JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE)

Previous Articles     Next Articles

Improvement for non-local means using data driven kernel

SUN Zhong-gui1, CHEN Jie2   

  1. 1. Department of Mathematics Science, Liaocheng University, Liaocheng 252000, Shandong, China;
    2. Library of Liaocheng University, Liaocheng 252000, Shandong, China
  • Received:2013-12-13 Online:2014-05-20 Published:2014-06-04

PDF (PC)

893

Abstract: The isotropy defect of non-local means (NLM) was pointed out with the help of model analysis. Further, an improved version of NLM was developed to compensate such a weakness. Compared with the original one, the new version based on the data driven kernel and encouraging experimental results are exhibited.

Key words: image denoising, non-local means, data-driving, kernel methods

[1] WANG Peng-ming, ZHONG Mao-sheng, LIU Zun-xiong. Multiple kernel learning in denoising space [J]. J4, 2012, 47(5): 49-52.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright 2018 © Editorial office of JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE)
Supported by Beijing Magtech Co.Ltd