摘要： 提出了一种基于视网膜图像特征点可靠提取的算法,在此基础上提出了一种对视网膜图像进行分步式的图像配准方法。首先利用最小二乘法进行快速的粗配,再进一步根据特征点的对应性,利用投影变换模型进行精确配准。与传统方法相比,该方法配准精度高,可以达到亚像素级精度,整个配准过程不需要人工干预。

关键词: 图像配准, 特征点提取, 视网膜图像, 投影变换, 仿射变换

Abstract: A fully automatic hierarchical method of retinal image registration based on the geometrical feature extraction is proposed . Firstly, a small number of geometrical feature points are extracted for coarse registration using least-square method. Secondly, more feature points are extracted for advanced registration based on projective transformation. Compared with the ordinary method, this method has a better robust feature with higher accuracy, it also has a fully automatic feature so it needs little human intervention in the whole processing.

中图分类号: 

• TP391.41