Price, Anna
(2013)
Longitudinal study of facial growth.
MSc(R) thesis, University of Glasgow.
Full text available as:
Abstract
The statistical analysis of shape is an area with wide applications. The field of facial shape analysis is particularly interesting because the human face has such a complex shape. This thesis investigates the change in the facial shape of a cohort of children, whose faces were photographed 6 times between the ages of 3 months and 12 years providing a normative control group for potential future comparisons.
Chapter 1 provides an introduction to the data, detailing the background and motivation for the longitudinal study. The aims of this thesis are outlines.
Chapter 2 describes the study design and data in detail. The process of data collection, both in the original study and the 12-year follow-up, is explained and the resulting data is explained. Issues that arose with data collection and the resulting data are introduced and discussed.
In Chapter 3 the theory of various statistical shape analysis methods is described in detail, including Procrustes Analysis and Principal Component Analysis.
Chapter 4 develops and discusses methods of automatic curve identification, as well as providing the theory of the shape index and methods of fitting curves such as p-splines and principal curves.
Chapter 5 details the longitudinal analysis of the control data. Statistical methods such as Procrustes Matching and Linear Mixed Effect models are implemented to discover change in facial shape over time.
In Chapter 6 the findings of the thesis are discussed, as well as the limitations of the data and the statistical methods used. Further work which would be of interest in the future is proposed.
Actions (login required)
 |
View Item |