Abstract: Image registration is used in many practical problems in diverse fields, and it is an important step in those applications. A new algorithm for image registration based on artificial immune network is proposed. It takes Partial Hausdorff distance as the similarity metric, and uses artificial immune network to find the optimal transformation parameters. Experimental results show that the proposed approach is a promising method for registration of image, and can be a good solution for image registration.

Key words: image registration, artificial immune network, Partial Hausdorff distance

摘要： 图像配准在很多领域得到了广泛应用，而且是其中不可缺少的步骤。该文提出了一种基于人工免疫网络算法的图像自动配准方法，该方法利用Partial Hausdorff距离作为相似测度，采用人工免疫网络算法寻找最优解。实验证明该方法可以很好地配准各种图像，为图像配准提供较好的解决方法。

关键词: 图像配准, 人工免疫网络算法, Partial Hausdorff距离

CLC Number: 

• TP391.41