一种新的基于梯度信息的自适应平滑算法研究

Research on a new self-adaptive smoothing algorithm based on gradient information

为了弥补基于梯度信息的平滑技术难以滤除脉冲噪声的不足,借鉴中值滤波理论,提出了一种新的基于梯度信息的自适应平滑算法。实验结果表明,该算法不仅可以有效滤除各种慢变化及脉冲噪声,而且在滤噪的同时能锐化目标的边缘。其单次滤波效果较基于梯度信息的平滑技术有明显改进,而且只需3次滤波即可达到比较理想的平滑效果。

For making up deficiency of troublesome straining out pulse noise based on smooth technology of gradient information, a new self-adaptive smoothing algorithm based on gradient information is presented considering the median filter theory. The experiment results show that this algorithm can not only strain effectively every slow changing and pulse noise, but also sharpen well the image edge simultaneously. The filter effect makes visible improvement than the unmodified.