一种噪声密度检测自适应选择策略的滤波算法

Adaptive-selection filtering strategy algorithm on noise density detection

针对灰度图像受椒盐噪声不同程度污染的滤波处理问题,提出了一种噪声密度检测自适应选择策略的滤波算法。先对被噪声污染图像进行噪声密度检测,然后根据检测结果判断图像为轻度污染还是严重污染。对于前者,用3×3窗口统计阈值(STM)的开关中值滤波算法;对于后者,采取先3×3窗口后5×5窗口统计阈值的开关中值滤波算法二次滤波。实验结果表明,该方法不但适应能力较强,而且具有较强的去噪能力和较好的图像细节保护能力。

This paper proposed an adaptive-selection filtering strategy algorithm on noise density detection for the filter problem that gray-scale was polluted by salt and pepper noise of different degree.Firstly,it detected the noise density of the polluted image,according to the detection results,the image was judged as either light polluted image or severe polluted image.For the former,it took 3×3 windows switching median filter algorithm based on statistical threshold.For the latter,it took first 3×3 last 5×5 windows switching median filter algorithm based on statistical threshold.Experimental results indicate that the proposed algorithm not only has strong adaptability but also has better image detail preservation and strong denoising ability.