Fast fingerprint identification for large databases

作者：

Highlights：

• A two-level parallel AFIS is proposed to deal with large databases.

• It makes possible to perform pattern identifications in arbitrarily large databases.

• The framework is flexible for any kind of databases, and any matching algorithm.

• The achieved speedup is nearly linear.

• The framework performs 400 000 matchings in 0.5 s, with no precision loss.

摘要

Highlights•A two-level parallel AFIS is proposed to deal with large databases.•It makes possible to perform pattern identifications in arbitrarily large databases.•The framework is flexible for any kind of databases, and any matching algorithm.•The achieved speedup is nearly linear.•The framework performs 400 000 matchings in 0.5 s, with no precision loss.

论文关键词：Distributed computing,Large databases,Minutiae matching,Parallel computing,Real-time fingerprint identification

论文评审过程：Received 13 March 2013, Revised 6 June 2013, Accepted 1 August 2013, Available online 14 August 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.08.002