计算机应用 ›› 2010, Vol. 30 ›› Issue (1): 68-70.

• 图形图像处理 • 上一篇    下一篇

一种融合局部与全局信息的距离约束角点匹配算法

吴恩生1,朱敏琛2   

  1. 1. 福州大学数学与计算机科学学院
    2.
  • 收稿日期:2009-07-01 修回日期:2009-08-11 发布日期:2010-01-01 出版日期:2010-01-01
  • 通讯作者: 吴恩生
  • 基金资助:
    福建省自然科学基金项目资助;福建省科技计划重点项目资助

Corner matching method of constraints of distance combining local and global information

  • Received:2009-07-01 Revised:2009-08-11 Online:2010-01-01 Published:2010-01-01

摘要: 图像匹配技术在众多领域中都有重要应用。针对既有平移又有旋转的情形,提出了基于距离约束的角点匹配方法,首先利用角点值进行匹配点对的粗选,然后利用局部角点间距离及全局角点间距离结合进行匹配点对的选取。实验结果表明,该方法可以实现无误匹配的匹配点对,准确性高,对噪声具有一定鲁棒性,且由于匹配过程中主要利用两点间的距离关系,而不需要进行复杂的运算,所以匹配时间大幅减少,在现实中有一定的实用性。

关键词: 旋转不变, 图像拼接, 特征点提取, 角点匹配

Abstract: Image matching technology has important applications in many fields. A corner matching method of the constraints of distance was proposed to solve the rotation and translation problem between two images. Firstly the values of corners were utilized to achieve coarse matching election, and then the local and global distance between the corners was combined to select the matching corners. The experimental results show that the methods can achieve accurate matching of no unmatched conners with high accuracy, certain robustness to noise, and as a result of the main use of the distance relationship between two corners without complex calculations in the matching process, so it achieves a substantial reduction in matching time, and also has the practical value.

Key words: rotation invariant, image mosaicing, console point extraction, corner matching