SUSAN算法与虚拟圆技术在图像配准中的应用

The Application of SUSAN Algorithm and Virtual Circles in Image Registration

图像配准是数字图像处理中的一个重要研究方向。在本文中把SUSAN算法和虚拟圆技术结合起来,提出了一种新的图像配准方法。经过SUSAN算法处理并二值化后的图像去除了原图像中的大部分信息,只保留了明显的边缘信息,这样就大大提高了虚拟圆的提取速度。试验表明这种新的配准方法具有简单、高效并具有较高的准确度等优点。

Image registration is an important research direction in digital image processing. In this paper, by combining SUSAN edge extraction algorithm with virtual circle method, ithis page has constructed a novel image registration method. After SUSAN processing and binarization, an image can contain only salient edges, with most information eliminated. Experimental results shows that the proposed method has features of simplicity, high efficiency and acceptable accuracy.