基于数学形态学的图像去噪方法研究

在噪声污染图像的处理中,运用数学形态学的理论和方法,提出了一种多结构元素自适应确定权重的算法,在此基础上构造开、闭运算的串、并复合形态滤波器。在形态滤波过程中,采用由小到大的多结构元进行处理以达到几乎全部滤除噪声的目的。实验表明,这类滤波器不仅可以有效地抑制图像中的噪声,而且较好地保持了图像的几何特征。

Research Based on Mathematics Morphology Image Chirp Method

In noise pollution image processing, use mathematics morphology theory and method, a multi-structural element auto-adapted determinations weights algorithm is brought up, and based on it series and parallel compound morphology filter of opened and closed operation is structured. In morphology filter process, uses by small to big multi-structural element is carried on processing to achieve nearly complete filter eliminates noise goal. Experiment indicates this filter may not only effectively suppress in image noise, but also preferably maintain image geometry characteristic.