基于边界距离场互信息的图像配准方法

基于图像边界平均Hausdorff距离的配准方法实现简单、速度快、有较大应用价值,但对图像边界不完全对应的情况配准效果不好。提出了一种以图像边界距离场互信息作为相似度函数的图像配准方法,以参考边界的距离场和浮动二值边界为两个离散概率分布,将其互信息作为相似度函数进行配准。实验结果表明,该算法对图像内容完全一致和内容不完全对应的图像均可得到良好的配准结果。

Image registration method based on mutual information about distance field of image edges

Image registration method based on mean Hausdorff distrance was simple, fast and available in application to image registration. At the same time, due to un-identical edges extracted from images, incorrect or inaccurate registration was often obtained. A new image registration method based on mutual information about distance field of image edges was presented. The distance field of the reference image edges and the binary edge image of floating image were re- garded as two discrete probability distributions, and the mutual information between them was adopted as similarity func- tion to register images. Results of experiments show that the new method is excellent to both identical and un-identical image edges.