Learn More
The corpus callosum is the largest white matter tract, important for interhemispheric communication. The aim of this study was to investigate and compare corpus callosum size, shape and diffusion characteristics in 106 very preterm infants and 22 full-term infants. Structural and diffusion magnetic resonance images were obtained at term equivalent. The(More)
The aim of this study was to relate altered corpus callosum (CC) integrity in 106 very preterm (VPT) infants (<30 weeks' gestational age or <1250 g birth weight) at term equivalent to perinatal predictors and neurodevelopmental outcomes at two years. T1 and diffusion magnetic resonance images were obtained. The CC was traced, and divided into six(More)
This paper presents a method to fit a 3D Morphable Model to a sequence of extracted facial features. The approach is a direct extension of a single view method. The novelty is presented as a new mathematical derivation of the same method but for multiple views where identity and pose are known. The new fitting method exploits point-to-model correspondences(More)
The neurobiological processes resulting in epilepsy, known as epileptogenesis, are incompletely understood. Manganese-enhanced MRI (MEMRI) can potentially aide in this quest as it provides superior tissue contrast, particularly of the hippocampal subregions. This longitudinal study aims to characterise the changes in the hippocampus of the post kainic(More)
The hippocampus undergoes rapid growth and development in the perinatal months. Infants born very preterm (VPT) are vulnerable to hippocampal alterations, and can provide a model of disturbed early hippocampal development. Hippocampal shape alterations have previously been associated with memory impairment, but have never been investigated in infants. The(More)
Active Appearance Models (or AAMs) are fast linear models for appearance variation in images. A key disadvantage of AAMs is the requirement for hand-labeled correspondence points. We use Morphable Model (or MM) data to avoid hand-labeling error and test the convergence performance of a well known fitting method, Inverse Compo-sitional Image Alignment (or(More)
Face recognition from video can be improved if good face segmentation of the subject under test is achieved. Many video based face recognition rely on simple background modeling and coarse alignment strategies for seg-mentation. This work presents a face recognition from video framework based on using Active Appearance Models (AAM) to achieve accurate face(More)
This paper presents a fast fitting method for 3D Mor-phable Models (3DMMs). In most cases fitting a Mor-phable Model to an image is done using slow non-linear optimization processes. We avoid this by introducing a relationship to Active Appearance Models (AAMs) that can be used to linearize the non-linear optimization problem of 3DMM fitting. Using the(More)