Title :
An Adaptive Image Denoising Algorithm Based on Wavelet Transform and Independent Component Analysis
Author :
Liu Zongang;Wang Tong
Author_Institution :
Inf. &
Abstract :
Independent Component Analysis(ICA) Is a kind of effective method for separating independent noise source. This paper proposed an improved Wavelet ICA filter, which could segregate the noise from Image. The suggested method using wavelet dimension reduction and normalizing the signal reduced the dimensionality through ICA that find independent noise characteristics and solve the problem of Non-orthogonality by using Morlet wavelet if necessary. We compared this algorithm with Principal Component Analysis (PCA) and FastICA by experiment to verify the effectiveness of the proposed method. The results show that the method proposed in this paper is much better than PCA and FastICA in image denoising.
Keywords :
"Principal component analysis","Wavelet transforms","Maximum likelihood detection","Nonlinear filters","Band-pass filters","Noise reduction","Image denoising"
Conference_Titel :
Intelligent Systems Design and Engineering Applications (ISDEA), 2015 Sixth International Conference on
DOI :
10.1109/ISDEA.2015.36