Image Registration Based on Harris-SIFT Feature Subspace

摘要：

　　In order to improve the efficiency of image registration, a novel algorithm based on Harris-SIFT feature subspace is proposed First of all, the Harris corners of template are extracted, meanwhile, the SIFT feature descriptors of the obtained corners are also constructed Secondly, the principal component analysis is used to build an effective feature subspace of Harris-SIFT.Finally, the target is matched by measuring the similarity function.The experimental results show that the algorithm is robust and can improve the speed of image registration significantly.

关键词： image registration principal component analysis Harris-SIFT feature subspace similarity measure

作者: Zhang Qi Zhou Bihua Li Wan

作者单位: College of Field Engineering,PLA Univ.of Sci.& Tech.,Nanjing 210007,China

会议类型: 国际会议

会议名称: 2013 IEEE 11th International Conference on Electronic Measurement & Instruments(第十一届IEEE国际电子测量与仪器学术会议)

会议地点: 哈尔滨

会议语种:英文

页码: 176-179

在线出版日期: 2013-08-16（万方平台首次上网日期，不代表论文的发表时间）