采用逐级配准和分值加权的指纹匹配算法

为将2个细节点集高效而准确地配准,首先利用与细节点相关联的短脊线对细节点组合进行初选,然后采用局部特征结构匹配精选出5对细节点作为配准的候选对应点.在2个细节点集配准后的匹配中,针对采用弹性匹配算法经常出现的细节点错配的情况,提出根据匹配可信度对各匹配对的匹配分值进行加权处理,以降低其对匹配精度的影响.采用FVC2002公布的指纹库进行对比实验,结果表明该算法在匹配效率和准确性上都有明显的提高.

Fingerprint Matching Using Hierarchical Alignment and Matching Score Weighting

Fingerprint matching is an extremely difficult problem, mainly due to the large variability in different impressions of the same finger. In this paper, a robust fingerprint matching algorithm has been developed. In the alignment stage, short ridges and invariant groups of local feature vectors are used to select corresponding minutiae for the alignment of two minutiae sets efficiently and accurately. In the following stage of matching aligned minutial, a coarse matching set is achieved by the elastic matching algorithm, but there are always some false matching pairs. In order to decrease the effect of false matching pairs to the final result, a novel method is introduced to weight the matching scores, and a more reliable similarity is achieved. Experiments on four databases of FVC2002 show that this fingerprint matching technique is more accurate and efficient compared with the conventional approach.