Sponsor Links
Northstar Recruiting
Northstar uses their industry knowledge to recruit top talent for Biometric and Identity Management companies.
ZK Software
ZKSoftware is one of the leading MultiBio and RFID providers in the world. We have branches in New Jersey, Sao Paulo, Dubai, Johannesburg, Madrid and Dubai
BIO-key
BIO-key develops and licenses advanced biometric finger identification technologies that are cost effective, scalable and easy to deploy.
IEEE CBP
Increase your knowledge and establish credibility in the field of biometrics with the IEEE Certified Biometrics Professional™ (CBP) Program.
ZN Vision Technologies and Unisys Corporation Partner on U.S. Government Project
Aug-21-03
BOCHUM, Germany-ZN Vision Technologies AG, Germany, today announced its agreement with Unisys Corp. (NYSE: UIS) to support the U.S. Government's research activities to apply 3-D biometric facial recognition technology to individual identification initiatives. ZN's facial recognition technology is widely regarded as one of the most promising and best performing methods worldwide.
The objective of the government project is to improve the performance of facial recognition technologies when comparing 2-D to 3-D images. This process is the basis for the automatic comparison of photos and life individuals. The application, following the latest recommendations of the ICAO (International Civil Aviation Organization) on biometric passports and border control scenarios, appears to be the biometric application of the future. In a recently published global harmonized blueprint the ICAO clearly underscores that facial recognition is the biometric technology of choice for ID documents. The face captured in the form of a photograph is already regarded as a standardized element of ID documents worldwide and has long been used by border control authorities and in access control scenarios to confirm an individual's identity by a "photo ID".
But the great advantages of facial recognition technology also entail a number of specific challenges: Portraits or passport photographs may vary greatly with regard to illumination and the pose of the head. By deploying a new generation of 3-D facial recognition technology, these variations of illumination and pose no longer would hinder a reliable identification of faces on the basis of photographs. The research project now initiated by the U.S. government is conceived to realize 3-D facial recognition applications and to make available for deployment a highly effective tool that performs a reliable and efficient identity confirmation.
One of the technologies to be evaluated is ZN's facial recognition method, the "Hierarchical Graph Matching" (HGM), which originally was developed in cooperation with Prof. Dr. Christoph von der Malsburg and his colleagues at the Ruhr-Universitat Bochum (Germany) and the University of Southern California, Los Angeles (USA). ZN's algorithms represent an organic approach that imitates the human vision process. The face is represented by an "elastic" grid, which is adjusted to the specific facial pose and expression by adapting the size, position and internal distortion. Within this grid, approximately 2,000 characteristics are used for the facial analysis. The flexibility of the technology and the complexity of analyzed features account not only for superior performance, but also provide an optimal basis for 3-D facial recognition. The combination of ZN's facial recognition technology with the products of Viisage Technology, Inc. (NASDAQ: VISG) enables further technological developments. Both companies announced to merge in March, the closing is expected to be completed in the third quarter. Viisage Technology is the leading provider of advanced technology for identity verification solutions for the government and various US agencies.
According to Dr. Stefan Gehlen, CTO of ZN Vision Technologies, the success of the project will support the U.S. government's activities in 3-D facial recognition research. "We are very pleased to work with Unisys on this advanced project. First evaluations have been very promising and we hope to present first results by the end of this year."