Fingerprint indexing based on minutiae-dependent statistical codes

Abstract

Methods based on minutiae matching have been extensively used in fingerprint recognition because minutiae can be reliably extracted from poor quality and noisy fingerprints. However, structures have to be defined due to minutiae displacements and irreproducibility. Some of the structures, though very efficient, incur large computational complexities. In this article, a feature vector of statistically based values derived from the minutiae pattern in a fingerprint is proposed for indexing fingerprints using the incremental search retrieval method. The proposed indexing technique in combination with the incremental retrieval method proves to have an added advantage over certain minutiae-based structures, especially when the minutiae points are numerous in a fingerprint. The feature vector for a fingerprint requires negligible storage resources and, consequently, the computational time in the retrieval of a candidate list for a query fingerprint is very little.