A Novel Fingerprint Indexing Approach Focusing on Minutia Location and direction

Biometrics identification systems containing a largescale database have been gaining increasing attention. In order to speed up searching in a large-scale fingerprint database, fingerprint indexing algorithm has been studied and introduced into biometrics identification system. One critical component of a fingerprint indexing algorithm is the feature extraction method. Majority of researchers developed the features by combining minutia with other information, such as ridge, singularities, orientation filed, etc. Instead, this paper will focus on only using minutia location and direction to extract features. The performance of proposed fingerprint indexing approach was evaluated on several public databases by being compared to the start-of-the- art fingerprint indexing method - minutia cylinder-code (MCC) - indexing as a benchmark. The experimental results show that the proposed approach gives equivalent performance or even outperforms MCC indexing method on the tested databases.