首页 | 本学科首页   官方微博 | 高级检索  
     

改进的模糊熵与图像局部信息相结合的遥感图像分割新算法
引用本文:黄宁宁,贾振红,何迪,杨杰,庞韶宁.改进的模糊熵与图像局部信息相结合的遥感图像分割新算法[J].四川激光,2010(6):20-22.
作者姓名:黄宁宁  贾振红  何迪  杨杰  庞韶宁
作者单位:[1]新疆大学信息科学与工程学院,新疆乌鲁木齐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
基金项目:科技部国际科技合作项目(项目编号:2009DFA12870)
摘    要:针对传统的一维最大模糊熵图像分割算法没有考虑图像的局部信息而对噪声十分敏感的这一不足,本文提出了结合图像局部信息的一维模糊熵图像分割算法。该算法将图像的空间信息和像素信息引入到一维模糊熵图像分割算法中,并运用微正则退火算法对一维最大模糊熵进行改进,从而提高了传统的一维最大模糊熵分割精度。实验结果表明,该算法显示了很好的分割效果和较强的抗噪性能。

关 键 词:一维模糊熵  微正则退火  局部信息  遥感图像分割

A new algorithm for remote sensing image segmentation based on the combination of the improved fuzzy entropy and local information
HUANG Ning-ning,JlA Zhen-hong,HE Di,YANG Jie,PANG Shao-ning.A new algorithm for remote sensing image segmentation based on the combination of the improved fuzzy entropy and local information[J].Laser Journal,2010(6):20-22.
Authors:HUANG Ning-ning  JlA Zhen-hong  HE Di  YANG Jie  PANG Shao-ning
Affiliation:1.College of Information Science and Engineering,Xinjiang University,Urumuqi 830046,China;2.Institute of Image Processing and Pattern Recognition,Shanghai Jiao Tong University,Shanghai 200240,China;3.Knowledge Engineering and Discovery Research Institute,Auckland University of Technology,Auckland 1020,New Zealand)
Abstract:Aiming at the problem of the conventional maximum one-dimensional fuzzy entropy algorithm is noise sensitive because of not taking into account the spatial informations.An image segmentation method via maximum one-dimensional fuzzy entropy algorithm with spatial information is presented.The method combines the standard maximum one-dimensional fuzzy entropy algorithm with spatial informations and pixel informations.Maximum one-dimensional fuzzy entropy algorithm is modified by the microcanonical annealing.The experimental results show that the proposed method can segment the image effectively and properly and the new algorithm is shown to be effective in image segmentation and has good performance of resisting noise.
Keywords:one-dimensional fuzzy entropy  microcanonieal annealing  local information  remote sensing image segmentation
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号