一种基于兴趣点匹配的图像拼接方法

针对基于图像特征点的配准方法中对应特征对难以准确提取的问题，提出一种基于兴趣点匹配的图像自动拼接方法。该方法首先利用Harris角检测器提取两幅图像中的兴趣点，并在此基础上采用比较最大值法提取出对应兴趣点特征对，最后利用这些匹配特征对来实现图像的拼接。实验结果表明，这种方法能有效地去除伪匹配特征对的干扰，同时降低了误匹配的概率，对于全景图的拼接具有良好的效果。

An image mosaic method based on interest points matching

Since the corresponding pair of feature points was difficult to be extracted in feature points registration methods, an image mosaic method based on interest point matching was presented. Firstly, the interest points from two images were extracted by Harris comer detector, then the corresponding interest point pair of features were got by comparison maximum algorithm. At last the images could be stitched by the corresponding pair of features. The experiments show that this algorithm can efficiently avoid the affect of false interest point pair of features, reducing the likelihood of false matching at the same time. This algorithm can be applied in panoramic images successfully.