一种PCNN的彩色图像脉冲噪声滤波方法

New color image filtering algorithm based on PCNN

通过脉冲噪声特性总结以及对脉冲耦合神经网络(PCNN)工作机理的分析,建立了一个在RGB色彩空间上的一种基于脉冲耦合神经网络的彩色图像去噪算法及模型。首先利用PCNN的同步脉冲发放特性定位脉冲噪声点的位置;然后利用中值滤波对其进行去噪处理,并将结果与中值滤波等其他滤波方法进行了比较。实验结果表明该方法不但能够有效去除图像中的噪声,而且能够更好地保护图像细节,较传统彩色图像去噪方法有较明显的优越性。

Through summarizing the characteristics of pulse noise and analysis of PCNN＇s work principle,a novel method of color image filtering of Gause noise is presented,which based on PCNN with characteristics of human visual color consciousness in RGB color pattern.Firstly,the noisy points are located using the syn-chronous pulse burst property of PCNN,then,are locally processed using the median filter.Finally the algorithm is compared with median filtering,other filtering.Experimental results show that the median filtering algorithm based on PCNN and RGB not only can effectively remove the noise,but also can protect the details of color image better.