交通运输系统工程与信息

交通运输系统工程与信息 ›› 2012, Vol. 12 ›› Issue (1): 48-54.

• 智能交通系统与信息技术 • 上一篇    下一篇

PCNN模型耦合参数的优化及车辆图像分割

杨娜1,2，陈后金*1，李艳凤1，郝晓莉1   

  1. 1. 北京交通大学 电子信息工程学院，北京 100044; 2. 中北大学 信息与通信工程学院，太原 030051
  • 收稿日期:2011-11-18 修回日期:2011-12-23 出版日期:2012-02-25 发布日期:2012-03-06
  • 作者简介:杨娜（1977-），女，山西长治人，讲师，博士生.
  • 基金资助:

    国家自然科学基金(60972093);高等学校博士学科点专项科研基金（20110009110001）.

Coupled Parameter Optimization of PCNN Model and Vehicle Image Segmentation

YANG Na 1,2, CHEN Hou-jin 1, LI Yan-feng1, HAO Xiao-li1   

  1. 1. School of Electronic Information Engineering, Beijing Jiaotong University, Beijing 100044, China; 2. School of Information and Communication Engineering, North University of China, Taiyuan 030051, China
  • Received:2011-11-18 Revised:2011-12-23 Online:2012-02-25 Published:2012-03-06

PDF

被引次数

33

摘要： 脉冲耦合神经网络（PCNN）具有良好的图像分割特性，但神经网络参数的选取对分割效果有较大影响，如何自适应地选择网络参数是脉冲耦合神经网络应用研究的重要内容.本文首次从脉冲耦合神经网络的耦合特性出发，结合神经计算原理及图像局部区域的灰度特性，提出了脉冲耦合神经网络耦合参数的优化算法.首先利用Hebb学习规则对脉冲耦合神经网络模型的链接权值矩阵进行更新，然后利用图像局部区域的均方差自适应确定神经元链接强度系数，最后将优化的PCNN模型应用于运动车辆图像分割.通过耦合参数的优化，增强了神经元之间的耦合强度，与传统PCNN的车辆分割结果相比，较好地避免了过分割和欠分割现象，提高了运动车辆图像中车牌区域的分割质量，为后续车辆特征的提取奠定了良好的基础.

关键词: 信息技术, 优化PCNN模型, Hebb规则, 局域均方差, 运动车辆, 图像分割

Abstract: The pulse coupled neural network (PCNN) has good properties for image segmentation. While the segmentation effect significantly depends on the parameter selection of PCNN. Thus, the adaptive parameter choice is important for the PCNN application research. The coupled parameter optimization algorithm based on the coupling characteristics is proposed, which combines the neural calculation principle and characteristics of grayscale in the image local area. First, the connection weight matrix of the PCNN model is updated in terms of the Hebb rule. Then the correlation strength factor between different regions is adaptively determined by local mean square deviation. Finally, the vehicle images are segmented by the PCNN model with optimized parameters. Compared with traditional PCNN image segmentation, the proposed method increases the coupling strength between neurons and avoids oversegmentation and undersegmentation. The segmentation quality of license plate images on the moving vehicles is improved, which lays a good foundation for the subsequent feature extraction.

Key words: information technology, optimized pulse coupled neural networks model, Hebb rule, local mean square deviation, moving vehicle, image segmentation

中图分类号: