Computer Engineering and Applications ›› 2013, Vol. 49 ›› Issue (10): 177-179.

Previous Articles     Next Articles

Improved algorithm of fast feature points matching

LIU Jia, CAO Zhengwen, SUN Delu, DENG Yuchen   

  1. School of Information Science & Technology, Northwest University, Xi’an 710127, China
  • Online:2013-05-15 Published:2013-05-14

一种改进的快速特征点信息匹配算法

刘  佳,曹正文,孙德禄,邓雨晨   

  1. 西北大学 信息科学与技术学院,西安 710127

Abstract: Feature points matching plays an important role in image retrieve, pattern recognition and so on. Feature detectors such as SIFT(DoG), Harris and SUSAN algorithm are good methods which yield high quality features, however they are too computationally intensive for using in real-time applications of any complexity. This paper puts forward an improved fast feature point matching algorithm. And uses the full affine method to extract the local feature points, which it was advocated by Guoshen and Jean-Michel, then uses the Random Fern to match feature points, uses RANSANC to remove dead points. The experimental results show that this method improves the image matching points, and reduces the matching time.

Key words: feature points, full affine, random fern, matching, RANSAC

摘要: 特征点匹配在图像检索、模式识别等技术中起着重要的作用。已有的匹配算法如SIFT(DoG),Harris以及SUSAN算法,虽然可以提取高质量的特征点,但是这些算法本身计算量比较大,难以将其运用于实时性要求比较高的应用中。提出一种改进的快速特征点匹配算法,采用Guoshen Yu和Jean-Michel Morel提出的全仿射方法,对局部特征点进行仿射变换并模拟摄像机成像原理,根据摄像机成像的仿射关系提取特征点并使用随机蕨类算法训练分类器,使用RANSAC去除坏点,实现对特征点的快速准确匹配。实验结果表明该方法提高了图像的匹配点数,同时降低了匹配时间。

关键词: 特征点, 全仿射变换, 随机蕨类, 匹配, RANSAC