一种新的全相位Contourlet离散变换在图像去噪中的应用

为了实现更为优秀的利用Contourlet来实现的图像去噪,以MATLAB为仿真工具,提出了一种新的全相位Contourlet离散变换,其多级分解和重构继承了已有的基于全相位DCT(APDCT)子带滤波和全相位IDCT(APIDCT)内插的全相位Contourlet,其方向滤波则是采用一种基于DCT的全相位方向滤波器组(APDFB)。APDFB具有良好的方向选择性,而且重构算法简单,只要将各个方向图像直接相加即可。实验结果表明,将新的全相位Contourlet离散变换应用在图像去噪中,与原Contourlet相比,在信噪比有所提高的同时,图像视觉效果也更好。

The Application of a New All Phase Contourlet Discrete Transform on Image Denoising

This paper proposes a bran-new discrete transform called AP-Contourlet (All Phase Contourlet), the multi-scale decomposition and reconstruction of which are based on the APDCT (All Phase DCT) sub-band filtering and the APIDCT (All Phase IDCT) interpolation for optimizing denoising effection of Contourlet. In addition, a kind of all phase directional filter bank (APDFB) based on DCT is used for directional filtering of the AP-Contourlet. The APDFB is possessed of excellent directional selectivity, and reconstruction algorithm is so simple that only adding the directional images is needed. Experiments in image de-noising have shown that the performance of the proposed AP-Contourlet is obviously superior to the conventional Contourlet both in vision and in signal to noise ratio (SNR).