Multimodal Biometric System
for Contactless Persons Identification

Scientific goal of the project

The scientific goal of the project is to develop a multimodal biometric system for contactless persons identification working based on the following physical and behavioral features (biometric traits):

  1. Iris pattern
  2. Face geometry
  3. Hand geometry

In the constructed system iris pattern features unique for each individual are derived from analysis of the iris structure image taken under NIR (Near Infrared) light. Unique face features are computed by analyzing 3D face scan acquired using two structured light scanning heads. Unique hand features are extracted by analyzing the 3D hand scan.

The essence of the problem

The main scientific problem to be solved is to work out suit of algorithms necessary for building the multimodal biometric persons identification system. The algorithms can be divided into two groups – algorithms that analyze each biometric trait independently and algorithms that perform fusion of data derived from analysis of each biometric trait solely.

Detailed characteristic of final result

First result of the project is building a measurement station for researches on biometric persons identification. The station allows to acquire the following biometric data from the individual:

  • iris pattern image taken under NIR light
  • 3D face scan
  • 3D hand scan

Second result of the project is acquisition of multimodal database for further researches. The database was acquired using the built measurement station. Subset of the collected database which contains the 3D face and hand scans, known as the DMCSv1 database, is publicly available for research and educational institutions. The collected iris patterns, due to privacy issues, are not publicly available.

Third result of the project is development and implementation of suit of algorithms for the needs of the build multimodal biometric system for persons identification. The team constructed the system according to the block diagram depicted in Fig. 1.

Fourth result of the project is development of software dedicated for the constructed measurement station. The software extends the station capabilities and makes it a fully functional multimodal biometric system for persons identification. The software - as specified in the block diagram depicted in Fig. 1 - allows cooperation between software modules implementing each component algorithm of the system. As a result there is build a fully functional system allowing enrolment of individuals in database and their later recognition.

mbs1


Fig. 1. Block diagram of constructed multimodal biometric system for contactless persons identification.