结合全局信息的SIFT特征匹配算法

纪华; 吴元昊; 孙宏海; 王延杰

光学精密工程, 2009, 17 (2): 439, 网络出版: 2009-10-09

结合全局信息的SIFT特征匹配算法

SIFT feature matching algorithm with global information

论文大纲

纪华 ^1,2,*吴元昊 ¹孙宏海 ¹王延杰 ¹

作者单位

¹ 中国科学院长春光学精密机械与物理研究所,吉林长春 130033

² 中国科学院研究生院,北京 100039

特征匹配 SIFT算法全局信息 BBF算法 feature matching SIFT algorithm global information BBF algorithm

摘要

提出了结合全局信息的SIFT(Scale Invariable Feature Transformation)特征匹配算法,解决了图像中存在多个相似区域时造成的误匹配问题。在尺度空间检测出特征点,生成包含两基于局部信息的SIFT向量和基于全局信息的全局向量;采用BBF(Best Bin First)算法进行搜索,并采用欧氏距离作为度量函数进行特征向量的匹配。实验结果表明,由于在基于局部信息的SIFT向量中加入基于全局形状信息的全局向量,使得当特征点的尺度较小时,可以借助更大邻域范围内的信息对其进行描述,从而降低了由于局部信息相似而造成的误匹配的概率。所用图像误匹配的概率由19%下降到了11%,极大地改善了匹配效果。

Abstract

An improved Scale Invariable Feature Transformation(SIFT) matching algorithm with global context vector is presented to solve the problems that SIFT descriptors result in a lot mismatches when an image has many similar regions. By detecting feature points in scale space, two kinds of feature vectors, a SIFT descriptor representing local properties and a global context vector, are computed. Then, according to BBF searching strategy, the feature vectors are matched by using Euclidean distance. The experimental results indicate that the improved algorithm can describe feature points in a larger region,and can reduce mismatch probability of experimental images from 19% to 11% because global context vectors based on global shape information are induced to the SIFT vectors based local Information. These results reported above show proposed algorithm improves matching results greatly.

参考文献

[1] 丁雪梅,王维雅,黄向东.基于差分和特征不变量的运动目标检测和跟踪[J].光学精密工程,2007,15(4):570-576.

DING X M,WANG W Y,HUANG X D. New method for detecting and tracking of moving target based on difference and invariant[J]. Opt. Precision Eng., 2007,15(4):570-576.(in Chinese)

[2] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110.

[3] KOENDERINK J.The structure of images[J].Biological Cybernetics,1984,50:363-396.

[4] LINDEBERG T. Sscale-space for discrete signals[J]. IEEE Transactions PAMI, 1980, 207: 187-217.

[5] 赵辉.SIFT特征匹配技术讲义[J].盐城工学院学报(自然科学版),2007,20(2):1-5.

ZHAO H. SIFT features matching technology[J]. Journal of Yancheng Institute of Technology(Natural Science Edition),2007,20(2):1-5.(in Chinese)

[6] ERIC N M, HONGLI D, LINDA S. A SIFT descriptor with global context[J].Computer Vision and Pattern Recognition,2005(1):20-25.

[7] 周颜军. 数据结构[M]. 长春:吉林科学技术出版社,2003.

ZHOU Y J. Data Structures[M]. Changchun:Jilin Science and Technology Publishing House,2003.(in Chinese)

[8] 戚世贵. 基于图像特征点的提取匹配及应用[D]. 长春:吉林大学硕士学位论文,2006.

QI SH G. The research of features extraction registration and application[D].Changchun:Jilin University Master Degree Thesis,2006.(in Chinese)

纪华, 吴元昊, 孙宏海, 王延杰. 结合全局信息的SIFT特征匹配算法[J]. 光学精密工程, 2009, 17(2): 439. JI Hua, WU Yuan-hao, SUN Hong-hai, WANG Yan-jie. SIFT feature matching algorithm with global information[J]. Optics and Precision Engineering, 2009, 17(2): 439.

结合全局信息的SIFT特征匹配算法

关于本站 Cookie 的使用提示

全站搜索

结合全局信息的SIFT特征匹配算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索