基于正交小波变换的图象去噪算法的改进

An Improved Algorithms of Image Denosing Based on Orthogonal Wavelet Transform

本文在BayesShrink阈值的基础上,提出了一种计算更有效的自适应的阈值估计,并针对传统的软、硬阈值函数在去噪中的不足,提出一种新的去噪阈值函数,最后将所提出的图象去噪方法与传统方法进行了实验比较,实验结果表明该方法在图象去噪中取得较好的效果,有效地提高了信号去噪所得信噪比增益。

This paper proposes an efficient threshold estimation method for image denoising based on BayesShrink. So the traditional methods for noise reduction using wavelet soft threshold function and hard threshold function have some defects, an improved threshold function is proposed, At the end, experiments have been done between this new method and the traditional methods. The experiment results indicate that this new method achieves better effect on reducing noise and gets higher SNR gain for the reconstructed signal.