中文摘要：

小波变换作为一种多尺度信号分析方法，在图像处理中得到了重要的应用．图像处理的一个重要研究方向就是去噪．由于图像含有大量的边缘，因此用于图像处理的小波基必须具有良好的边缘检测性能和较强的平滑噪声能力．但是，目前还难以找到具有这样特性的正交小波基．本文利用信号的多相位表示理论，提出了一种基于Haar小波的三通道正交完全重建滤波器组，并推导出它在图像去噪中的软门限方法．试验表明，该滤波器组用于图像去噪可以得到很好的结果．

英文摘要：

As a new tool of signal analysis, wavelet transform has been successfully used in image processing. One of the most important fields of image processing is denoising. Since image contains plenty of edges, the wavelet basis used in image denoising should have the nice properties of edge-preserving and noise-smoothing.However,it is difficult to find such a wavelet basis. In this paper, based on the theory of multi-phase representation of signal, a 3-channel orthogoml perfect reconstruction filter bank is designed and the conesponding soft thresholding algorithm used in image denoising is deduced too. Examples show that the filter bank is effective in image denoising.