PCNN赋时矩阵高斯噪声滤除算法  

Gaussian noise filtering algorithm based on PCNN time matrix

作　　者：张文兴[1] 闫海鹏[1] 王建国[1] 

机构地区：[1]内蒙古科技大学机械工程学院,内蒙古包头014010

出　　处：《中国测试》2016年第8期108-112,共5页China Measurement & Test

基　　金：国家自然科学基金(21366017);内蒙古自治区研究生科技创新资助项目(S20141012711);内蒙古自治区教育厅自然科学一般项目(NJZY13144)

摘　　要：为消除图像降噪过程中传统降噪方法对图像边缘和细节的影响,提出一种基于改进脉冲耦合神经网络(pulse coupled neural network,PCNN)赋时矩阵的有效滤除高斯噪声算法。该算法将PCNN模型的突触联结强度改进为随神经元与其周围神经元相似程度不同而变化的可变值,并将PCNN神经元的点火时间记录在赋时矩阵中,根据点火时刻判断噪声点,选择滤波方式。实验结果表明:该算法能够有效去除高斯噪声,具有较强的降噪性能及很好的边缘与细节保护能力。To eliminate the effect of the traditional de-noising methods on the edges and details of images during image de-noising, a gaussian noise filtering algorithm based on Pulse Coupled Neural Network （PCNN） time matrix is proposed. The synaptic coupling strength of the PCNN model is defined as a variable whose value is dependent on the similarity among different neurons. Meanwhile, the ignition times of PCNN neurons are recorded in the time matrix. The noise point and the filtering method can be determined according to the corresponding time matrix elements. Experimental results show that the proposed algorithm can filter Gaussian noise effectively, and is more capable for the protection of edges and details of images.

关 键 词：脉冲耦合神经网络 赋时矩阵 高斯噪声 突触联结强度 可变值 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]