Image Denoising Based on Least Squares Support Vector Machines
Han Liu, Yong Guo, Gang Zheng · 2006
Wavelet image denoising has been one of important method of denoising for image processing in recent years. In this paper, The denoising operators used in wavelet domain based on least squares support vector machines (LS-SVM) are obtained and image denoising using proposed operators is given, based on the principle of wavelet denoising. In the experiment of image denoising, the influence of different parameters has been studied when two kernel functions are chosen for least squares support vector machines. Compared with the method of WaveShrink and Median Filter under different signal-to-noise ratio (SNR), results show that the proposed image denoising technique is effective in removing Gaussian noise and preserving edge information well.