基于控制点图像配准方法的研究

Research of image registration based on control points

图像配准是图像融合等其他图像处理应用的前提,是目前图像处理中的热点。如何在MATLAB环境下利用特征点对图像进行配准,简述了图像配准的方法,具体应用MATLAB提供的人机交互的方法在参考图像与浮动图像之间进行匹配控制点的选择确定几何变换关系,对比分析了不同的插值技术对配准的影响并确定了相对较优的方法对图像灰度赋值,对输入图像进行空间几何变换,获得配准图像。仿真实验表明,该方法简便易行,获得的配准效果较好。

Image registration is the premise of image fusion and other image processing applications. It is also the hot spot in the image processing. This paper describes image registration based on characteristic points under MATLAB environment. Firstly, we represent the methods of image registration, and then select the matching points using human-computer interaction methods provide by MATLAB between the reference image and the floating. Comparative analysis of different interpolation techniques for alignment are offered. Meanwhile, we determine the better methods to assign gray values, then make use of these control points to confirm geometric transformations. Finally, we perform the geometric transformation in connection with the input images to obtain registration results. Simulation results show that the method is easy to implement and we can obtain effective registration results.