【作者】 栾志强；

【导师】 刁鸣；

【作者基本信息】 哈尔滨工程大学 ， 通信与信息系统， 2006， 硕士

【摘要】 由Eckhorn神经元模型得到的脉冲耦合神经网络模型(PCNN)是直接观察猫的视觉皮层神经细胞并模拟其活动而得到的人工神经网络模型。PCNN不同于传统的人工神经网络模型，它是通过模拟视觉皮层神经细胞的活动而建立的神经网络模型，是对真实神经元的简化与近似。PCNN网络模型所具有的链接域特性和动态阈值衰减特性能够使状态相似的神经元同步输出脉冲，这一点充分模拟了哺乳动物视觉皮层神经元的生物特性，因而在图像分割、边缘提取、目标识别等图像处理方而获得了广泛的应用。 本文深入研究脉冲耦合神经网络的基本原理、运动行为及其特性，本论文对原始PCNN模型做了一定程度的简化，在保持PCNN链接域特性和动态阈值衰减特性的基础上减少了神经元模型的一些参数，提出更适用于图像处理的简化型PCNN模型。从理论上说，简化型PCNN可以用于图像处理的各个方面，本文只对灰度指纹图像进行了分割，又对被白噪声污染的二值指纹图像进行了去噪处理，完成了指纹识别系统中两个重要的环节。同时，实验发现简化型PCNN处理其它类型图像同样有效。 实验结果证明，本文提出的方法用于指纹图像的分割和去噪时，性能优于其它算法，满足指纹识别系统的精度要求。简化型PCNN具有很好的亮度和对比度适应性，同一图像的分割效果不受亮度、对比度不同的影响。更多还原

【Abstract】 PCNN (Pulse Coupled Neural Network) is a new kind of Artificial Neural Networks (ANN) based on the phenomena of synchronous pulse bursts in the animal visual cortex. PCNN is different from those models of traditional artificial neural network. It is constructed by simulating the activities of the neurons of visual cortex, and is the simplification and approximation of the neurons. The properties inherited in PCNN, such as linking field and the dynamic threshold, make the approximate neurons fire simultaneously, and this is very close to the natures of visual cortex of small mammals. So it has gained widely applications in image processing, such as image segmentation, edge extraction, object recognition and so on.This thesis investigates the model of PCNN, which includes its basic principles, behaviors and characteristics. In this thesis, through reducing some parameters we get a simplified PCNN which also has the linking field and the dynamic threshold, and simplified PCNN is adapt to image processing. Theoretically speaking, simplified PCNN can be used in every aspect of image processing. This thesis investigates the segmentation of fingerprint image, and the smoothing of the fingerprint image, which is polluted by Gaussian white noise. The segmentation and smoothing are two important parts of fingerprint identification system. Simplified PCNN is also effective when dealing with other kinds of image.The results of experiment show that this method mentioned in this article is superior to other algorithm when it is used in fingerprint image segmentation and smoothing. And this method has high accuracy to satisfy the demand of fingerprint identification system. Simplified PCNN has a fine adaptability of brightness and contrast. There is no difference between the images with different brightness and contrast.更多还原