Matching unfamiliar faces is known to be a very difficult task. Yet, despite this, we frequently rely on this method to verify people's identity in high security situations, such as at the airport. Because of such security implications, recent research has focussed on investigating methods to improve our ability to match unfamiliar faces. This has involved methods for improving the document itself, such that photographic-ID presents a better representation of an individual, or training matchers to be better at the task. However, to date, no method has demonstrated significant improvements that would allow the technique to be put into practice in the real world. The experiments in this thesis therefore further explore methods to improve unfamiliar face matching. In the first two chapters both variability and feedback are examined to determine if these previously used techniques do produce reliable improvements. Results show that variability is only of use when training to learn a specific identity, and feedback only leads to improvements when the task is difficult. In the final chapter, collaboration is explored as a new method for improving unfamiliar face matching in general. Asking two people to perform the task together did produce consistent accuracy improvements, and importantly, also demonstrated individual training benefits. Overall, the results further demonstrate that unfamiliar face matching is difficult, and although finding methods to improve this is not straightforward, collaboration does appear to be successful and worth exploring further. The findings are discussed in relation to previous attempts at improving unfamiliar face matching, and the effect these may have on real world applications.
|Creators||Dowsett, Andrew James|
|Publisher||University of Aberdeen|
|Source Sets||Ethos UK|
|Type||Electronic Thesis or Dissertation|
Page generated in 0.0026 seconds