In order to solve the problem of the high mismatching rate of feature points in course of image matching, a novel matching strategy based on SURF feature points is propose. Euclidean nearest neighbor distance ratio method is used to match the extracted SURF features roughly, and then statistical information of the corresponding gray neighborhood of each feature point is obtained. Then, more robustness matching pairs can be gotten with Pearson correlation coefficient. Experimental results show that this method can effectively improve the matching accuracy and meet real-time requirements.