基于PCNN神经网络的图像去噪算法研究  

An Image De-noising Algorithm Based on PCNN

作　　者：邹文洁[1] 

机构地区：[1]南华大学机械工程学院,湖南衡阳421001

出　　处：《计算机仿真》2008年第8期234-237,共4页Computer Simulation

摘　　要：图像噪声的去除一直是图像处理领域的难点,以往介绍的去噪方法主要用于去除二值图像的噪声,不能用于灰度图像的去噪,而且在去噪的同时会引起图像的模糊,为了解决问题,根据PCNN的工作原理和噪声的特点提出了一种改进的基于PCNN的去噪方法。计算机仿真实验结果表明该方法能在有效去除椒盐噪声的同时,很好地保留了图像的细节,防止了图像的模糊,对图像的恢复、图像的识别是十分有益的,但对于严重的高斯噪声,去除效果还不是很理想,该算法有待改进。The removal of image noise is always a difficult problem in the field of image processing. Conventional methods,which may make the image blurred, are mainly used for denoising of binary image, cannot be applied for gray image. For solving this problem, the paper proposes an improved method based on PCNN, according to the operating theory of PCNN and the characters of noise. The computer simulation experiment result proves that the method is perfect for image with noise of salt and pepper and has a good ability in keeping the details of image. This is very benficial to image restoration and image recognition. However, the method is not perfect for image with serious gauss noise and so it is to be improved.

关 键 词：脉冲耦合神经网络 椒盐噪声 图像去噪 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]