Postgraduate research project

Generative AI for synthetic biometric and age estimation testing

Funding
Fully funded (UK only)
Type of degree
Doctor of Philosophy
Entry requirements
2:1 honours degree View full entry requirements
Faculty graduate school
Faculty of Engineering and Physical Sciences
Closing date

About the project

The development and offline testing of biometric systems (such as face and voice) relies on the presentation of a large collection of population unbiased-data. Assembling these data is often time consuming and, to be ethically valid, requires the agreement of test participants for their data to be used for research purposes.

Likewise robust testing of age estimation systems, increasingly being deployed for age restricted products and services, is of increasing importance. The generation of representative data of subjects between the ages of 12-24 will enable an assessment of systems which traditionally have suffered from a lack of accurate ground-truthed data. Generative AI (GAI) tools are rapidly advancing, enabling the creation of media tuned to descriptive parameters.

Working alongside Professor Richard Guest and Dr Jennifer Williams in the School of Electronics and Computer Science, this project will assess the utility of GAI techniques in producing media for synthetic biometric purposes with the following research questions:

  • can Generative AI media (GAIM) be used for biometric matching?
  • can GAIM be used to augment real-world data?
  • what is the performance of GAIM tuned to demographic parameters?
  • can we develop a feedback framework for enhancing the utility of GAIM?
  • can we metricise performance of individual GAI systems?

Funding for this project is offered by the Centre for Doctoral Training in Complex Integrated Systems for Defence & Security (CISDnS), which will recruit motivated and inquisitive candidates across the themes of digital, physical and biological systems to provide a diverse and interconnected cohort training environment.

As well as carrying out research training in a world-leading research group, membership of CISDnS will provide the opportunity for you to be exposed and trained to handle the interdisciplinary challenges faced in the real-world via a Systems Thinking approach.

You will learn about the wider challenges of research and innovation within the Defence & Security sector from both your peers and the numerous industry partners supporting the Centre.