Fingerprint indexing using minutiae-based invariable set of multidimensional features

In fingerprint identification, exhaustive search demands a huge response time for large database and hence impractical in many real-life applications. To alleviate this limitation, researchers advocate indexing technique to narrow down the search space. In this work, we investigate three different indexing techniques (linear, clustered and clustered kd-tree) with invariable set of features for a fingerprint identification system. In our approach, we consider local topology of minutiae using two closest points triangle for index key generation. The features are invariant to rotation and scaling and hence, the approach can deal with fingerprints form different devices and sensors. The proposed approach has been tested on NIST DB4 and FVC 2004 databases. Experimental results substantiate the error rate of 0.35%, 1.5% and 2.45% at penetration rate 15% in NIST DB4 for linear search, clustered search and clustered kd-tree search, respectively. For FVC 2004 databases, we attain 0%, 1.36% and 5.45% for FVC2004 DB1, 0%, 2.73% and 4.09% for FVC2004 DB2, 2.27%, 5.0% and 5.91% for FVC2004 DB3 and 0%, 1.36% and 5.0% for FVC2004 DB4 when penetration rate is 15.45% in linear, cluster and clustered kd-tree searches, respectively. The result is indeed comparable to the existing approaches reported in the recent literature.