A novel hierarchical fingerprint matching algorithm with low complexity is proposed, which is suitable for resource-constrained applications. By analyzing different support levels from coarse to fine matching based on the non-fixed local minutiae spatial relationships, the matching score is chosen from the sparse matrix representing the similarity. Experimental results show that the performance of the proposed algorithm is efficient and that it can be used in real resource-constrained platforms. We have implemented our fingerprint verification system using the proposed preprocessing and matching algorithms on the embedded platform including ARM920T (SUMSUNG S3C2410) and DSP (TMS320VC5509A).