提出了一种基于图像小波包变换及与分解层次相关的自适应阈值的去噪方法。利用小波包对图像进行分解，可以同时对图像的低频和高频部分进行分解，可以更好地保留图像信息，减少噪声对图像的影响。同时对小波包树系数用自适应阈值进行软阈值处理，可以很好地保留边缘等图像信息，这一方法比采用常用的阈值明显提高了去噪图像的信噪比。通过对加噪图像的实验可以看出，本文方法不仅可以有效地去除加性高斯白噪声，而且很好地保留原图信息，对进一步图像处理有所帮助。

An image denoising scheme based on wavelet packet and level dependent adaptive threshold is proposed in this paper. By using wavelet packet, the scheme not only decomposes the image into the low frequency part but also into the high frequency part of image so that the influence of noise can be eliminated. Meanwhile, using the level dependent adaptive threshold to process wavelet packet tree coefficient with soft threshold can keep edge information and important image information better since the soft threshold can clearly make the SNR of denoised image higher than general threshold. From the experiment results, we see that such scheme can not only suppress additive Gaussian white noise but also well keep original image information. The proposed method is useful for advanced image processing.