[an error occurred while processing this directive]
   
 
���¿��ټ��� �߼�����
   ��ҳ  �ڿ�����  ��ί��  Ͷ��ָ��  �ڿ�����  ��������  �� �� ��  ��ϵ����
�������պ����ѧѧ�� 2010, Vol. 36 Issue (9) :1121-1124    DOI:
���� ����Ŀ¼ | ����Ŀ¼ | ������� | �߼����� << | >>
���ڸĽ�SIFT��ͼ����׼�㷨
�� ��, �Ź���, ������*
1. �������պ����ѧ �Զ�����ѧ���������ѧԺ, ���� 100191;
2. ��������豸�о��� �������Ƽ��������Ƽ��ص�ʵ����, ���� 471004;
3. �������պ����ѧ �Զ�����ѧ���������ѧԺ, ���� 100191
Image registration approach based on improved SIFT
Liu Jian, Zhang Guohua, Huang Linlin*
1. School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China;
2. Key Laboratory of National Defense on Fire Control Technology, Luoyang Institute of Electro-optic Equipment, Luoyang 471004, China;
3. School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

ժҪ
�����
�������
Download: PDF (0KB)   HTML 1KB   Export: BibTeX or EndNote (RIS)      Supporting Info
ժҪ Ϊ������ڽϴ�̶���ת�����ŵ�ͼ����׼����,�����һ�ֻ��ڳ߶Ȳ��������任(SIFT, Scale Invariant Features Transform)��ͼ����׼�㷨.���ö���������任(LPT, Log-Polar Transform)����ͼ���ƥ��,��ͼ����ת�ǶȺ����ų߶ȱ仯�����й���,����ͼ�����У��;�ڴ�ƥ��Ļ����϶�ͼ����зֿ�,������Ϣ��ԭ����ȡ�ӿ��SIFT�����Ͳ��������,�������͵�����������;���ŷ�Ͼ����Procrustes�����㷨���ͼ���ͬ�����,������ͼ���α����,���ͼ����׼.ʵ��������:���㷨�ٶȿ졢�ȶ���ǿ,���ܴﵽ�����ؼ���ƥ�侫��.
Service
�ѱ����Ƽ�������
�����ҵ����
�������ù�����
Email Alert
RSS
�����������
����
�Ź���
������
�ؼ����� ͼ����׼   �߶Ȳ��������任   ������     
Abstract�� To resolve the problem of large angle and large scale image registration, an improved approach based on scale invariant feature transform (SIFT) is proposed. The log-polar technique was applied to estimate the parameters of rotations scales between reference image and sensed image. The images were segmented into sub-blocks and six candidates of sub-blocks were extracted according to information entropy, where SIFT features and moment features were fused to form a new feature descriptor. The image registration result was calculated from the matching points which were obtained by combining the Euclidean distance and the algorithm of iterative procrustes. The experimental results show that the proposed method is fast with high-precision.
Keywords�� image registration   scale invariant feature transform   moment features     
Received 2009-08-10;
Fund:

���տ�ѧ����������Ŀ(20085113007)

About author: �� ��(1982-),��,ɽ���ൺ��,˶ʿ��,liujian016@163.com.
���ñ���:   
����, �Ź���, ������.���ڸĽ�SIFT��ͼ����׼�㷨[J]  �������պ����ѧѧ��, 2010,V36(9): 1121-1124
Liu Jian, Zhang Guohua, Huang Linlin.Image registration approach based on improved SIFT[J]  JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2010,V36(9): 1121-1124
���ӱ���:  
http://bhxb.buaa.edu.cn//CN/     ��     http://bhxb.buaa.edu.cn//CN/Y2010/V36/I9/1121
Copyright 2010 by �������պ����ѧѧ��