计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (32): 215-216.

• 图形、图像、模式识别 • 上一篇    下一篇

PCA与PCNN结合的遥感图像分割方法

刘 瑛1,覃锡忠1,贾振红1,杨 杰2,庞韶宁3   

  1. 1.新疆大学 信息科学与工程学院,乌鲁木齐 830046
    2.上海交通大学 图像处理与模式识别研究所,上海 200240
    3.新西兰奥克兰理工大学 知识工程与开发研究所,新西兰 奥克兰1020
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-11-11 发布日期:2011-11-11

Segmentation method of remote sensed images based on principal component analysis and pulse coupled neural network

LIU Ying1,QIN Xizhong1,JIA Zhenhong1,YANG Jie2,PANG Shaoning3   

  1. 1.College of Information Science and Engineering,Xinjiang University,Urumuqi 830046,China
    2.Institute of Image Processing and Pattern Recognition,Shanghai Jiaotong University,Shanghai 200240,China
    3.Knowledge Engineering and Discovery Research Institute,Auckland University of Technology,Auckland 1020,New Zealand
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-11-11 Published:2011-11-11

摘要: 提出了一种基于主分量分析(PCA)与脉冲耦合神经网络(PCNN)结合的遥感图像分割方法。通过对图像在每个像素的邻域的基础上进行主分量分析,产生每个图像像素的特征向量,再用PCNN对得到的特征图像进行点火分割。实验结果表明,与传统方法比较,该算法在分割结果、实时性以及稳健性方面具有较强的优越性。

关键词: 脉冲耦合神经网络, 主分量分析, 遥感图像分割

Abstract: A segmentation method of remote sensed images based on principal component analysis and pulse coupled neural network is proposed.It presents principal component analysis on image based on neighborhood unions of per-pixel to obtain the eigenvector of per-pixel,then uses PCNN to set on fire to segment image with feature image.Experimental results have shown that compared with traditional method,the proposed method is stronger superiority in segmentation results、stablity and real time capability.

Key words: pulse coupled neural network, principal component analysis, remote sensed images segmentation