FaceVACS DBScan

The data for FaceVACS-DBScan are databases of biometric identities and closely related data. The biometric identities are trusted face photographs. The product is used to support the biometric identification, comparison, similarity check and verification of persons that are members of a large group of persons.

Human beings can perform all those biometric identifications and comparisons. However, human beings are not capable of working with large reference groups, due to their limited processing capabilities in terms of throughput and their limited concentration capabilities.

The product overcomes this human weakness by supporting inspectors working with such large reference groups. Human inspectors let the product do all the inspections of non-similar identities automatically whilst controlling the similarity thresholds. They can let the system propose and present them all the similar identities in an appropriate manner. Thus, human inspectors can focus with all their concentration on the most similar identities only. This saves time and effort and is more effective, more valuable and less error prone.


Features

  • Based on the proven FaceVACS face recognition technology
  • Scalable to networked configurations of computers, serves multi- million person sized databases
  • Flexible and comfortable match list handling that allows sorting, rearranging, browsing, filtering and more
  • Batch and interactive enrollments and identifications
  • Multiple facial images per case
  • Extensive and flexible management of additional case related data
  • Auditable configurable journal for revision purposes and for general usage
  • Integrator's Kit for easy integration into existing systems
  • Prebinning by bin sets
  • One to few requests
  • High Availability Option
  • In addition to hardware bound now also Dongle bound activation
  • Updated Web Serivce API as part of Integrators' Kit

Specification

  • Scalable and robust client-server application
  • Template density per computing node up to 2 million
  • Throughput more than 1 million comparisons per second on a single XEON CPU
  • Runs on Windows 2003 Server / XP and Linux SLES10
  • Requires SQL 92 compliant database
  • Oracle 9i / 10g recommended

Gallery

Log In or Register