Abstract: The image matching technique based on Scale Invariant Feature Transform is studied，and the fake matching points are eliminated effectively by adding epipolar restriction in this method.A new matching method which combines feature matching and area matching，edge feature and corner feature，is depicted，and the experiments show that the matching time can be reduced，and precision can be improved by using this method.

摘要： 对目前匹配能力很强的基于SIFT特征的图像匹配方法进行研究，并在该方法中加入极线约束，有效去除了大部分虚假匹配。提出以特征匹配与区域匹配相结合、边缘特征与角点特征相结合的立体匹配方法。实验证明该方法不仅能够有效地缩短匹配时间，还能达到较高的匹配精度。