计算机工程 ›› 2012, Vol. 38 ›› Issue (22): 159-162.doi: 10.3969/j.issn.1000-3428.2012.22.039

• 人工智能及识别技术 • 上一篇    下一篇

基于场强和凸壳的SIFT特征点匹配算法

张光耀,王 强,蔡昀哲,张绿云,李志欣   

  1. (广西师范大学计算机科学与信息工程学院,广西 桂林 541004)
  • 收稿日期:2012-02-21 修回日期:2012-03-28 出版日期:2012-11-20 发布日期:2012-11-17
  • 作者简介:张光耀(1983-),男,硕士,主研方向:图形图像处理,模式匹配算法;王 强,教授、博士;蔡昀哲、张绿云,硕士研究生;李志欣,副教授、博士
  • 基金项目:
    国家自然科学基金资助项目(61165009)

SIFT Feature Point Matching Algorithm Based on Field Intensity and Convex Hull

ZHANG Guang-yao, WANG Qiang, CAI Yun-zhe, ZHANG Lv-yun, LI Zhi-xin   

  1. (College of Computer Science & Information Technology, Guangxi Normal University, Guilin 541004, China)
  • Received:2012-02-21 Revised:2012-03-28 Online:2012-11-20 Published:2012-11-17

摘要: 传统尺度不变特征变换(SIFT)匹配算法的匹配结果易受参数影响。为此,提出一种于场强和凸壳的SIFT特征点匹配算法。在原始SIFT匹配方法基础上,结合特征点群的凸壳,引入引力场强概念刻画特征点群之间的空间特征关系,以进行图像点模式匹配,在匹配中充分利用特征点的几何空间信息。实验结果表明,该算法具有较高的匹配正确率,能找到更多的特征匹配点。

关键词: 点模式匹配, 尺度不变特征变换, 凸壳, 场强, 仿射

Abstract: To overcome the defects that the traditional Scale Invariant Feature Transform(SIFT) method is sensitive to parameters applied, a SIFT feature point matching algorithm based on field intensity and convex hull is proposed. Based on the traditional SIFT matching method and the convex hull of the point sets in template and observe images, a concept of the gravitational field intensity in physics is introduced to depict the space relationships between features points for image matching in this paper. The proposed algorithm makes full use of the space geometry relationship between feature points in matching process. Experimental results show that, by using the proposed algorithm, the correct rate of matching between the point sets can be greatly improved, and can get more feature matching point.

Key words: point pattern matching, Scale Invariant Feature Transform(SIFT), convex hull, field intensity, affine

中图分类号: