Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (15): 184-186.

• 图形、图像、模式识别 • Previous Articles     Next Articles

Method for image registration based on condition number and Zernike moments

GONG Qu,GUO Feifei,YANG Ya   

  1. College of Mathematics & Physics,Chongqing University,Chongqing 400044,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-05-21 Published:2011-05-21

条件数和Zernike矩在图像配准中的应用

龚 劬,郭飞飞,杨 亚   

  1. 重庆大学 数理学院,重庆 400044

Abstract: An automatic image registration method based on the condition number and Zernike moments of interest points is proposed.Firstly the harris corner detector is used to gain the interest points and remove some Pseudo feature points with condition number.Then,the improvement Zernike moments as the description of the feature points,the matching point pairs are obtained by comparing the Euclidean distance of the Zernike moments,which are computed around a circular neighborhood centered at the feature point.And estimating the transformation parameters mapping the input image to the reference one by applying RANSAC.Experimental results illustrate the proposed algorithm is robust to translation,rotation,and slight scaling.

Key words: Harris corner detection, condition number, Zernike moments, RANdom SAmple Consensus(RANSAC)

摘要: 提出了一种基于条件数和泽尼克矩的图像配准算法。首先用Harris角点检测器提取特征点并通过条件数去掉一些伪特征点;用改进的Zernike矩作为特征点的描述子,通过比较各个特征点圆形邻域泽尼克矩的欧式距离得到初始匹配点对;用RANSAC估计待配准图像和基准图像之间的变换参数,实验表明,该算法在图像存在比例缩放、旋转等情况下有很好的配准效果。

关键词: Harris角点检测, 条件数, Zernike矩, 随机抽样一致性