ICA Based Wavelet Transform and Its Application to Image Separation
Yan Chen · Modern Electronics Technique · 2007
This paper proposes a kind of new Independent Component Analysis(ICA) method based on Wavelet transform and its application to image separation.According to the research,the steady-state error of the Natural Gradient Algorithm is inverse proportional to the kurtosis of the sources when the probability distribution function of each source is the same.In addition,in the wavelet transformation,it enhances picture the signal to noise ratio by using the wavelet threshold value to de-noise.Finally,the experiments results show that the proposed method is effective.