一种基于Radon变换及快速傅里叶变换的图像配准方法

摘要

针对现有的图像配准方法的低鲁棒性问题,提出一种对噪声不敏感的多畸变图像配准方法,通过Ra-don变换估计旋转角度,利用快速傅里叶变换求解平移与伸缩.实验结果表明该方法有效提高各类图像配准的精度,并且具有较高的鲁棒性,可以有效抵抗噪声信号的干扰,具有较高的实用价值.%Aiming at the low robustness of the existing image registration methods,a noise-insensitive multi-distorted image registration method was proposed.The rotation angle was estimated by Radon transform, and the translation and expansion were solved by fast Fourier transform.Experimental results showed that this method could effectively improve the accuracy of all kinds of image registration,and had high robustness,which could effectively resist the interference of noise signals and had high practical value.