摘要
提出了一种新的基于脉冲耦合神经网络算法的图像选点滤波方法,首先介绍了脉冲耦合神经网络算法模型,分析了噪声的特点。然后提出新的算法:用脉冲耦合神经网络构造图像像素点火时间矩阵,根据时间矩阵判别该点应采取怎样的滤波算法。最后通过图像质量评价方法对实验结果作了分析,结果证明该方法有效可靠,能够抑制高斯噪声和脉冲噪声。
This paper puts forward a new algorithm to remove mixed Gaussian noise and impulse noise for image based on the time matrix of Pulse Coupled Neural Networks （PCNN）. It analysis the features of noise and introduces the modal of PCNN at first, then puts forward the new algorithm, that is to get a map of time matrix from spatial image information to time information generated from PCNN. At last, it introduces the image quality evaluation method, discusses the select standard of the points and shows the experiment results.
出处
《山西电子技术》
2009年第3期3-4,9,共3页
Shanxi Electronic Technology
基金
山西省自然基金资助(2007012003)
