Application of Independent Component Analysis in Image Processing
Shang Ma · Jisuanji gongcheng · 2011
The classical methods are very sensitive to noise when used to edge detection of noise image.Aiming at this problem,this paper presents a method of edge detection for noise image based on Independent Component Analysis(ICA).Sparse coding shrinkage algorithm based on independent component analysis is used to reduce noise component,and a processed image and other two images by geometric transformation of the processed image can be obtained.Sharpening image can be obtained by analysis the matrix information of the three images by means of ICA.Experimental results show that the method can extracts edge and texture information accurately even of image corrupted seriously by Gaussian Noise.