Biometric Authentication and Applications.
Unlike traditional authentication techniques, e.g., PIN code or password, biometrics provides an alternative yet natural way for personal identity authentication. Biometrics handles authentication of individuals on the basis of biological and/or behavioural characteristics (measurements of the human body). As a primary advantage, biometric features are typically unique and, therefore, cannot be misplaced and forgotten since these are always inherently associated with human beings. The major biometric features include voice, face, fingerprint, irises, retinas, palmprint, signature, and so on. In general, there are two types of biometric systems: identification for identifying an unknown biometric token as belonging to one of people (registered in the system) and verification for accepting or rejecting the identity claim of a person based on an input biometric token. Due to the tragedy of 11th September 2001 in New York City and 7th July 2005 in London, automatic biometric authentication systems are highly demanded for security. Therefore, the development of such systems of high performance is of great significance and huge potential applications. In this project, the selected biometrics will be researched in order to develop biometric authentication systems of high performance and explore other novel applications, e.g., the use of biometric information in multimedia information retrieval. The main issues to be studied include silent feature discovery/extraction, biometric user modelling, decision-making strategies and multi-modal biometric information fusion. In addition, there are numerous engineering issues, e.g., trade-off between performance and acceptability and robustness on miscellaneous mismatch conditions, to be investigated.
Component-based Software Development.
In Software Engineering, component-based development...