Semmler, CarolynHeyer, RebeccaMichalski, Dana Jaclyn2018-03-222018-03-222018http://hdl.handle.net/2440/111184Determining the identity of children is critical for many national security agencies for example, to aid in the fight against child exploitation, trafficking, and radicalised minors, as well as for passport control and visa issuance purposes. Facial comparison is one method that may be used to achieve this. Facial comparison can be conducted using an algorithm (within a facial recognition system), manually by a facial comparison practitioner, or by a combination of the two. Much of the previous research examining facial comparison performance of both algorithms and practitioners has been conducted using images of adults. Due to the substantial amount of age-related facial growth that occurs in childhood, compared to adulthood, it is likely that performance will be poorer with images of children. The overarching aim of the research therefore, was to determine the impact of age-related variables, namely chronological age and age variation (the age difference between images) on facial comparison performance of algorithms and practitioners with images of children. Study 1 involved consultation with national security agencies and algorithm vendors to identify the key requirements to examine in this thesis. After reviewing the literature to identify research gaps, five empirical studies were conducted. To ensure the studies were as operationally relevant as possible, a large database containing several million controlled images of children and adults was sourced, and five state-of-the-art facial recognition algorithms were employed. In addition, facial comparison practitioners from a government agency participated in the practitioner studies. Study 2A compared algorithm performance with images of children to performance with images of adults. Study 2B compared practitioner performance with images of children to performance with images of adults. Study 3A examined algorithm performance with images of children at each chronological age in childhood (0–17 years) and age variations ranging from 0–10 years apart. Study 3B examined practitioner performance on the same age-related variables examined in Study 3A. Study 4 demonstrated how the data collected in Study 3A and 3B could be used to answer agency specific questions. This thesis concludes with a series of recommendations for both the algorithm and practitioner domains, as well as future research directions designed to improve knowledge and performance regarding facial comparisons with images of children.enfacial comparison practitionersfacial recognition algorithmschild identificationoperational imagesTheses10.4225/55/5ab4385633544