Research on Image Feature Matching Based on SIFT

摘要：

Image feature matching is the core of 3D reconstruction technology. This paper aiming at the issues which effect the matching accuracy that caused by translation, rotation, affine transformation between two images, has studied the Scale Invariant Feature Transform (SIFT) algorithm which have strong matching ability. In this method, adding epipolar restriction can make the objects edge information integrate and contour clear, also can effectively remove parts of the false matching. The experimental results show that the algorithm operation is faster and image matching precision is high.

关键词： Image matching SIFT Image feature point Gaussian function Feature vector

作者: Jiang Tao Yang Pingxian Guo Peng Guo Rong

作者单位: Dept. of Automation and Electronic-information, Sichuan University of Science & Engineering, Zigong, Dept. of Automation and Electronic-information, Sichuan University of Science & Engineering, Zigong,

会议类型: 国际会议

会议名称: 2012 International Conference on Electric Technology and Civil Engineering(2012 电子技术与土木工程国际会议 ICETCE 2012)

会议地点: 三峡

会议语种:英文

页码: 304-307

在线出版日期: 2012-05-18（万方平台首次上网日期，不代表论文的发表时间）