Feature matching based on multi-pose faces has become more important in recent years. And it can be used in many fields, such as video monitoring, identity recognition, and so on. In this paper, SIFT algorithm is combined with AdaBoost algorithm, and a method of feature matching based on a multi-pose face is established. Firstly, the face region is extracted from multi-pose face images by AdaBoost. Secondly, SIFT characteristic vectors of the main regions are extracted and matched. The images of the ORL face DB are used in this paper, and some pictures taken in the experiment are used too. The matching results are acceptable and reasonable. Based on multi-pose face, it can be used to research face feature matching, face recognition, video monitoring and 3-D face reconstruction.