[an error occurred while processing this directive]
���¿��ټ��� �߼�����
   ��ҳ  �ڿ�����  ��ί��  Ͷ��ָ��  �ڿ�����  ��������  �� �� ��  ��ϵ����
�������պ����ѧѧ�� 2006, Vol. 32 Issue (11) :1333-1336    DOI:
���� ����Ŀ¼ | ����Ŀ¼ | ������� | �߼����� << | >>
�Ի۽�, ����, �ֹ���, ����*
�������պ����ѧ ������ѧ���繤��ѧԺ, ���� 100083
Improved independent component analysis applied to classification hyperspectral imagery
Zhao Huijie, Li Na, Jia Guorui, Dong Chao*
School of Instrument Science and Opto-electronics Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China

Download: PDF (1396KB)   HTML 1KB   Export: BibTeX or EndNote (RIS)      Supporting Info
ժҪ ��Զ����ɷַ�����ʹ�ó�����ֵ���ʱ��������ֲ����Ž������,�Լ�������ѧϰ�㷨ʱ��Ԫ���������������,���Ŵ��㷨������ɷַ�������,����ģ�ͽ��иĽ�,������ʺ��ڸ߹��������޼ල�����ģ��.���㷨������󻯷Ǹ�˹�Խ��гɷֵ�ͳ�ƶ����Զ���,�����Ľ��ۻ���-�����Ϊ�Ŵ��㷨����Ӧ�Ⱥ���.��Ӧ�÷�����,�����㷨Ӧ������ɨʽ�߹��׳�����(PHI,Push-broom Hyperspectral technique Imager)���ݵ�������ܹ����ȫ�����Ž�,��û��������Ϣ�����ʵ�ֵ���ľ�ϸ����;�봫ͳ�߹����޼ල�����㷨�Ƚ�,�������㷨��������,�����и��ߵķ��ྫ�Ⱥ�׼ȷ��.
Email Alert
�ؼ����� �Ŵ��㷨   �����ɷַ���   �޼ල����   �߹���ң��     
Abstract�� To avoid the disadvantage of getting into local optimum solution with general numerical computation methods in the general independent component analysis and the restriction of neuron activation functions of neural learning algorithm, an improved model of independent component analysis (ICA) based on genetic algorithm was proposed for the unsupervised classification of hyperspectral data. In the proposed algorithm, the maximizing non-Guassianity was used to measure the statistical independence of the components, and the forth-order cumulant, kurtosis, was adopted as fitness function in genetic algorithm. In the application, the global optimum solution can be obtained and the fine plant classification can be implemented without any prior information when the proposed algorithm is applied to the push-broom hyperspectral technique imager (PHI) data. Moreover, compared with the conventional unsupervised classification algorithm of hyperspectral data, the proposed algorithm is more applicable and can obtain the better precision and accuracy.
Keywords�� genetic algorithm   independent component analysis   unsupervised classification   hyperspectral remote sensing     
Received 2006-04-30;
About author: �Ի۽�(1966-),Ů,����������,����, hjzhao@buaa.edu.cn.
�Ի۽�, ����, �ֹ���, ����.�Ľ������ɷַ����ڸ߹���ͼ������е�Ӧ��[J]  �������պ����ѧѧ��, 2006,V32(11): 1333-1336
Zhao Huijie, Li Na, Jia Guorui, Dong Chao.Improved independent component analysis applied to classification hyperspectral imagery[J]  JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2006,V32(11): 1333-1336
http://bhxb.buaa.edu.cn//CN/     ��     http://bhxb.buaa.edu.cn//CN/Y2006/V32/I11/1333
Copyright 2010 by �������պ����ѧѧ��