In recent times, there has been an increase in national security awareness with a focus on improving current practices relating to the identification and verification of individuals and the reduction of identity fraud. One tool that has been found to assist in these areas is biometrics. This thesis examines some biometric technologies that may be potentially suitable for surveillance and access control applications, and shows why facial recognition technology has been the focus of this study. Despite the testing reported in the literature discussing attempts to solve the problems with facial recognition operational performance, facial recognition has not been widely implemented in security applications to date. The reported testing regimes vary in terms of the date of testing, methodology used for the study, evaluation type, test size and the extent to which possible variations of each variable were examined. To summarise what is known about the effect each variable has on performance, a baseline model of variables together with a ranking scheme is defined and utilised to create a starting point for the research. The research described in this thesis focuses on how to improve the operational performance of two dimensional facial recognition systems by building upon the baseline model of variables and by better understanding how the variables affect facial recognition performance. To improve on the baseline model, systems engineering techniques are used to identify the functional components of a generic facial recognition system, the relationships between them, and the variables that affect those relationships. This identifies other variables that may affect performance. In order to determine which variables affect performance, and how, a series of technical, scenario and operational experiments are conducted to test a selection of the variables. It is shown that this results in a greater understanding of how facial recognition systems react to different variables in operational environments. A revised model of ranked variables is produced that can then be used by current and prospective stakeholders of biometric systems, system designers, integrators and testers to ensure that the majority of the variables are considered when designing, installing, commissioning, or testing facial recognition systems. The findings of this research can also be used to critically analyse existing facial recognition system implementations in order to identify areas where performance increases are possible. This is confirmed in part throughout the two year testing phase of this research where data collected from initial experiments were used as a starting point to improve the performance of later operational experiments. Finally, this thesis identifies that the revised model of variables is sufficiently generic to be used as a starting point for analysing a system using any biometric technology. This is supported by using iris recognition technology as a test case. It is anticipated that with an increased knowledge of how some systems are affected by certain variables, and by better controlling those variables, an increase in performance is possible for access control and surveillance security applications that utilise biometric technologies. / thesis (PhDElectronicSystemsEngineering)--University of South Australia, 2005.
| Identifer | oai:union.ndltd.org:ADTP/284119 |
| Date | January 2005 |
| Creators | McLindin, Brett Alan |
| Source Sets | Australiasian Digital Theses Program |
| Language | English |
| Detected Language | English |
| Rights | Copyright 2005 Brett Alan McLindin |
Page generated in 0.0017 seconds