An improved method of denoising shrink-function by NSCT

The threshold filtering based on multi-resolution is composed of the soft threshold and hard threshold. For the soft shrink-function, the filtered signal is excessively smooth. For the hard shrink-function, the filtered signal associated with the Gibbs phenomenon in the signal mutation after filtering. The contraction function presented in this paper is between soft and hard. Through its coefficients modification, the filtered signal reaches a reasonable balance between excessively smoothness and edge oscillation. Based on the analysis, this paper shows the PSNR comparison values and the image using different filtering methods. The comparative results show that the improved method eliminates the oscillation phenomena and retain some details effectively while removes noise from image.