基于边缘特征和相位相关的图像配准

Image registration based on edge character and phase correlation

由于拍摄时间不同、传感器的抖动等原因,成像系统产生的序列图像之间具有一定的位移矢量。研究了一种基于边缘和相位相关的图像配准方法,首先提取图像边缘,然后进行归一化相位相关,从而估算出序列图像之间的位移量。实验结果表明,该方法的配准精度明显优与传统的相位相关方法,并对噪声具有较强的抑制能力。

Because of different imaging time,sensor jitter and other reasons,it exist translational motion between a sequences of images produced by imaging system.In this paper,an image registration method based on edge character and phase correlation is researched,a normalized phase correlation is applied after extracting edge character,then it can estimate the translation vector between two similar images.The experiments show that this method has better registration accuracy than the traditional normalized phase correlation method,and shows better robustness against noise.