Combining SURF with MSER for image matching

Many local features such as Speeded Up Robust Features (SURF) have been widely utilized in image matching due to their notable performances. However, the original SURF algorithm ignores the geometric relationship among SURF features. To overcome this drawback, an improved method combining SURF with Maximally Stable Extremal Regions (MSER) for image matching is proposed in this paper. By combining SURF features into groups and measuring the geometric similarity among features, the discriminative power of the grouped features has been significantly increased. Simulations show that the proposed method outperforms the original SURF algorithm both in match ratio and repeatability.