Partial fingerprint identification through correlation-based approach

Partial fingerprints are likely to be fragmentary or low quality, which mandates the development of accurate fingerprint verification algorithms. Two fingerprints should be aligned properly, in order to measure the similarity between them. Moreover, the common fingerprint recognition methods (minutiae-based) only use the limited information that is available. This affects the reliability of the output of the fingerprint recognition system, especially when dealing with partial fingerprints. To overcome this drawback, in this research, a region-based fingerprint recognition method is proposed in which the fingerprints are compared in a pixel-wise manner by computing their correlation coefficient. Therefore, all the attributes of the fingerprint contribute in the matching decision. Such a technique is promising to accurately recognise a partial fingerprint as well as a full fingerprint compared to the minutiae-based fingerprint recognition methods which only concentrate on parts of the fingerprint. The proposed method is based on simple but effective metrics that has been defined to compute local similarities which is then combined into a global score and then used to make the match/non-match decision. Extensive experiments over FVC2002 data set has proven the superiority of our method compared to the other well-known techniques reported in literature.