FingerPrint

Fingerprints serve as a primary authentication source in large-scale identity systems, boasting unique traits like distinctiveness and persistence. However, scalability concerns arise due to vast fingerprint datasets, impacting memory and computational resources. This paper presents an efficient fingerprint matching algorithm utilizing nearest neighbor minutia quadruplets (NNMQ), which maintain rotation and translation invariance. Experimental results demonstrate the algorithm’s ability to reduce both space and time complexities, validated against standard fingerprint benchmark databases such as FVC ongoing, FVC2000, and FVC2004.