基于图像二维熵的自适应形态学滤波方法

Adaptive morphological filter based on image 2-D entropy

为了在滤除噪声的同时保持图像的细节信息,结合已有的形态学滤波方法,提出了一种新的自适应滤波方法.综合图像灰度分布的聚集特征和空间特征,构造图像二维熵,结合形态学运算,合理设置滤波算法流程,通过连续改变结构算子的大小,观察图像二维熵的变化,合理设置滤波终止条件,通过对椒盐噪声图像的滤波测试,取得了理想的滤波效果.重点阐述了二维熵的构造方法和自适应滤波的流程设计.

To maintain the detail information of images in the process of noise removal, a new adaptive morphological filter method was proposed based on the morphological filter in use. The 2-D image entropy has been used in this filter, and it has been constructed with the gray scale of every pixel and the gray scale distribution of neighbor region pixels. With the effective morphological arithmetic open and close, we set a reasonable flow in this filter. When finished the filter operation, the 2-D image entropy would always be calculated to reflect the effect of the filter operation, then the structure element for morphological arithmetic would be enlarged continuously. Based on the terminative qualification by 2-D image entropy, the filter operation ran adaptively and effectively with salt and pepper noise image. The definition of image 2-D entropy and adaptive morphological filter were discussed particularly.