Adaptive Image Denoising Based on Sparse Decomposition

Article Preview

Abstract:

Different behaviors of image information and noise in sparse decomposition were studied to identify the differences between image information and noise. According to the different coherences between image (or residual image), noise and over-complete dictionary, image information and noise are distinguished. One image adaptive filtering is realized by taking coherent ratio threshold as the constraints of extracting available information.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

2932-2935

Citation:

Online since:

October 2011

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Mallat S, Zhang Z. Matching pursuit with time-frequency dictionaries[J], IEEE Trans. On Signal Processing, 1993, 41(12): 3397-3415.

DOI: 10.1109/78.258082

Google Scholar

[2] Bergeau, F., and Mallat, S., Matching pursuit of images[A], Proceeding of IEEE-SP, Oct, 1994, Piladelphia, PA, USA, pp.330-333.

Google Scholar

[3] Li Yu-xin, Yin Zhong-ke. Fast algorithm for MP sparse decomposition and its application in speech recognition[J]. Computer Engineering and Applications, 2010, 46(1) : 122-128.

Google Scholar

[4] Zhang Wenyao. Low Rate Speech Coding Research Based on MP Method[D], PhD thesis, Beijing: Graduate School of Chinese Academy of Sciences (Software Research). 2002, 10.

Google Scholar