Latent fingerprint matching in large databases using high performance computing

Abstract

Most of the fingerprint matching systems use the minutiae-based algorithms with matching of ridge patterns. These systems consider ridge activity in the vicinity of minutiae points, which has poorly recorded/captured exemplar prints (information). In this research, we recommend the MapReduce technique to identify a required fingerprint from the reference fingerprint database. In the proposed MapReduce process, minutiae of the latent fingerprint used as keys. The latent fingerprints are analyzed using Bezier ridge descriptors to enhance the matching of partial latent against reference prints. Since the retrieval of reference print is same as retrieval of the required document, we suggested the MapReduce model for detection of required fingerprint.