脉冲耦合神经网络及基于此的图像分割与图像压缩-计算机应用技术专业毕业论文.docxVIP

摘要摘要 摘要 摘要 本文主要研究了脉冲耦合神经网络(PCNN-一Pulse Coupled Neural Network) 的运行行为、离散PCNN的自动波传播特性和基于改进型PCNN的图像分割及其 在图像压缩中的应用。首先分析了脉冲耦合神经网络的基本模型及其运行行为， 深入研究了PCNN自动波的传播条件、传播速度、传播方向等问题。在PCNN的 应用研究中，主要是图像分割和图像压缩，本文结合人类视觉系统(HVS)对图像各 个区域敏感度不同这一特性，对通常的PCNN模型进行了改进，分析了改进模型的 特性及其参数优化原理，提出了基于改进型PCNN的图像分割算法。该算法是一种 自适应的有效图像分割方法并且较好地仿真了人类视觉系统特性，在此基础上进 行了基于图像内容的图像压缩，在压缩比和重建图像主观视觉感知质量上均达到 了较好的性能。通过对离散PCNN的自动波传播特性深入的分析，及其在图像分割、 图像压缩应用中给出的有效实用的计算方法，最终得出这样的结论：脉冲耦合神 经网络在图像处理中有着广泛的应用前景。 ’一 关键词： 脉冲耦合神经网络，自动波，图像分割，图像信息，图像压缩 AbsttactABSTRACT Absttact ABSTRACT This paper presents the model ofpusle-coupled neural networks(PCNN)、analysis of running behavior、autowave travelling of discrete PCNN and the application of PCNN image processing．Based the analysis of PCNN’s model and work principle，the condition for the autowave in the PCNN is studied．About the application of PCNN． image segmentation and image compression is mainly studied，based the property of Human Vision System(HVS)that human eye’s sensitivity to an image varies with different regions of an image where different regions correspond different information of the image，Pulse Coupled Neural Network(PCNN)model is modified for image segmentation．The modified PCNN stimulated by input image has outputs of pulses with many pulse values other than only two according the local intensity variation of pixels in the put image．This results in segmentation of the image with respect local information delivered by the image．The proposed self-adaptive segmentation algorithm is applied image compression and performs well in both compression and subjective perceptual quality of the reconstructed image．Through the study of the discrete PCNN autowave traveling and the effective applicable image processing methods based PCNN，we can gain conclusion that the application ofPCNN to image processing is broad and prosperous． Key Words：Pulse·Coupled Neural Networks；Antowave；Image Segmentation；Image Information；Image compression S3s93；创新性声明 S3s93； 创新性声明 本人声明所呈交的论文是我个人在导师指导