首页 | 官方网站   微博 | 高级检索  
     

基于组合不变矩特征的空中目标识别方法
引用本文:曾万梅,吴庆宪,姜长生. 基于组合不变矩特征的空中目标识别方法[J]. 电光与控制, 2009, 16(7)
作者姓名:曾万梅  吴庆宪  姜长生
作者单位:南京航空航天大学自动化学院,南京,210016;南京航空航天大学自动化学院,南京,210016;南京航空航天大学自动化学院,南京,210016
基金项目:火力控制技术国防科技重点实验室资助 
摘    要:根据NMI特征和Jan Flusser提出的仿射不变矩各自的特点和适用条件,提出了一种组合不变矩.利用组合不变矩提取图像的不变特征向量,并结合Fisher线性判别准则,实现了对空中目标的Fisher线性判别器(FLDA)的分类识别.同时,考虑到识别的快速性方面,对FLDA进行了改进,提出了主分量分析(PCA)与FLDA相结合的识别算法.仿真实验结果表明,该方法具有较高的识别精度和速度.

关 键 词:图像识别  目标识别  仿射不变矩  组合不变矩  Fisher线性判别器  主分量分析

Recognition Method of Aerial Targets Based on Combined Invariant Moments
ZENG Wanmei,WU Qingxian,JIANG Changsheng. Recognition Method of Aerial Targets Based on Combined Invariant Moments[J]. Electronics Optics & Control, 2009, 16(7)
Authors:ZENG Wanmei  WU Qingxian  JIANG Changsheng
Affiliation:College of Automation Engineering;Nanjing University of Aeronautics and Astronautics;Nanjing 210016;China
Abstract:A new combined invariant moment was presented according to the characteristics of NMI's feature and affine invariant moment proposed by Jan Flusser with their application conditions.The feature vector of the aerial target was extracted by using combined invariant moments.With the help of Fisher linear discriminant rule,the aerial target classification was implemented successfully based on Fisher Linear Discriminant Analysis(FLDA).At the same time,considering the speediness requirement of recognition, the FL...
Keywords:image recognition  target recognition  affine invariant moment  combined invariant moment  Fisher linear discriminant analysis  principal component analysis  
本文献已被 CNKI 万方数据 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-23

京公网安备 11010802026262号