Abstract: A new noise removal algorithm is proposed for meteorological facsimile maps with zero-mean Gaussian noise, which is based on Contourlet transform. The algorithm makes full use of the inherent features of meteorological facsimile maps and the sparsity of Contourlet transform coefficients, and decomposes these meteorological facsimile maps via Contourlet transform to separate the information and noise. The experiments show the effectiveness of the proposed algorithm.

Key words: Contourlet transform, image enhancement, filtering, multiscale geometry transform, meteorological facsimile map

摘要： 针对气象传真图，提出一种基于Contourlet变换的图像增强方法。充分考虑气象传真图的自身特征和Contourlet变换系数的稀疏性，应用Contourlet变换将包含噪声的图像分解成噪声系数和信号系数，利用气象传真图的主要稀疏系数对分解图像进行增强处理。实验结果表明，该方法是一种有效的气象传真图像增强方法。

关键词: Contourlet变换, 图像增强, 滤波, 多尺度几何变换, 气象传真图