首页 | 本学科首页   官方微博 | 高级检索  
     

基于二阶矩的SIFT特征匹配算法
引用本文:钟金琴,檀结庆,李莹莹,辜丽川.基于二阶矩的SIFT特征匹配算法[J].计算机应用,2011,31(1):29-32.
作者姓名:钟金琴  檀结庆  李莹莹  辜丽川
作者单位:1. 合肥工业大学计算机与信息学院2. 合肥工业大学3.
基金项目:国家自然科学基金资助项目(60773043;30800663)
摘    要:针对图像视角变化而导致的匹配率低的问题,提出基于二阶矩的SIFT特征匹配算法.算法在尺度空间检测出特征点,用仿射的二阶矩来估计特征点的椭圆邻域,把椭圆邻域梯度的主方向作为该特征点的方向,生成特征向量,最后采用欧氏距离作为度量函数进行特征向量的匹配.实验表明,改进后的算法继承了SIFT算法对图像缩放、旋转等不变性,而且增...

关 键 词:尺度空间  二阶矩  仿射不变  SIFT算法
收稿时间:2010-06-30
修稿时间:2010-08-11

SIFT feature matching algorithm based on second moment matrix
ZHONG Jin-qin,TAN Jie-qing,LI Ying-ying,GU Li-chuan.SIFT feature matching algorithm based on second moment matrix[J].journal of Computer Applications,2011,31(1):29-32.
Authors:ZHONG Jin-qin  TAN Jie-qing  LI Ying-ying  GU Li-chuan
Affiliation:ZHONG Jin-qin1,3,TAN Jie-qing2,LI Ying-ying1,GU Li-chuan4(1.School of Computer and Information,Hefei University of Technology,Hefei Anhui 230009,China,2.School of Science,3.School of International Business,Anhui University,Hefei Anhui 230031,4.School of Information and Computer,Anhui Agriculture University,Hefei Anhui 230036,China)
Abstract:An improved Scale Invariable Feature Transformation(SIFT) matching algorithm based on second moment matrix was presented to solve the problems that SIFT results in low matching ratio when view point of image changed.Feature points were detected in scale space and each feature point neighborhood was estimated by affine second moment matrix,then feature vectors were computed by dominant orientation assignment to each feature point based on elliptical neighboring region,finally the feature vectors were matched...
Keywords:scale space  second moment matrix  affine invariance  Scale Invariable Feature Transformation(SIFT) algorithm  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》下载全文
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