A novel method to match two minutiae point-sets based on the support model we proposed is presented in this paper. In this method, coarse matching is-rst performed from a number of seeds, and the re- sults are then fused to obtain a constrained corresponding relationship of minutiae in two point-sets. By using the support degree of the elements in the constrained relations, the one-to-one correspondence is-nally de-termined by comparison of similarity of local structures. Experiments show that this algorithm is robust and can deal with the translation, rotation, distortion and outlier problems well.