After completing a degree in Maths and Physics at Exeter University, and a PhD in Civil Engineering (studying a storm sewer overflow) at Sheffield City Polytechnic, I joined the University of Manchester in 1991.
I began as an RA, working with Prof Chris Taylor on modelling industrial components.
I was awarded an SERC Postgraduate fellowship in 1993, and an EPSRC Advanced Fellowship in 1995.
I became a Lecturer in ISBE in June 2001, and was promoted to Senior Lecturer in October 2002.
I became a Reader in Computer Vision in August 2005, and was appointed as a Professorial Research Fellow in August 2006.

My research has concentrated on constructing statistical models of the shape and appearance of objects in images, and in developing algorithms to match such models to new images.  We have applied these models to many problems in the industrial and medical domains, and to the interpretation of facial images.

Collaborators and affiliated staff


  • Dr Paul Bromiley
  • Dr Claudia Linder
  • Dr Georgia Rajamanoharan
  • Dr Xinghui Dong

Affiliated staff

Methodological knowledge

Computer Vision

Medical Image Analysis

Statistical Models of Appearance

Groupwise Image Registration

Facial Image Interpretation

Research interests

Medical Image Analysis using Statistical Models

Using statistical shape and appearance models, and machine learning methods, to locate and measure structures in medical images.

Musculoskeletal Applications

Analysing the shape and appearance of bones and joints in medical images in order to diagnose and monitor diseases such as osteoporosis and osteoarthritis.

Facial Image Analysis

Using statistical models to locate and track facial features in images and videos, and to estimate the identity or activity of the person.

Groupwise Image Registration

Methods of finding corresponding points and structures in large groups of images, so that we can automatically construct statistical models to learn about the common structures and variation inherent in the data.


I run an MSc Module on Mathematical Methods

ID: 252100