J4 ›› 2010, Vol. 37 ›› Issue (2): 300-304.doi: 10.3969/j.issn.1001-2400.2010.02.021

• Original Articles • Previous Articles     Next Articles

Image denoising based on wave atoms and cycle spinning

SONG Yi-mei;SONG Guo-xiang   

  1. (School of Science, Xidian Univ., Xi'an  710071, China)
  • Received:2009-02-17 Online:2010-04-20 Published:2010-06-03
  • Contact: SONG Yi-mei E-mail:ymsong@mail.xidian.edu.cn

Abstract:

A new method for image denoising is presented, which colligates the strongpoint of the wave atoms transform and Cycle Spinning.Due to lack of translation invariance of the wave atoms transform,image denoising by coefficient thresholding would lead to Pseudo-Gibbs phenomena. Cycle Spinning is employed to avoid the artifacts.Experimental results show that the method can remove noisy and remaining edges, while Pseudo-Gibbs phenomena are controled efficiently, and can get a better visual effect and PSNR gains compared with the methods like simplex wave atoms or wavelet denoising using Cycle Spinning.And in heavy background noise, this advantage is significant.

Key words: image processing, denoising, wavelet transforms, wave atoms, translation invariance, cycle spinning