Face recognition and visual processing

This research area is concerned with the understanding and synthesis of face images by both machines and humans.

A core component of the work of the group is in developing statistical models of the appearance and behaviour of human faces in image sequences.

Such models can be matched to new image sequences, and the resulting model parameters further analysed to estimate the identity, expression and facial behaviour of the individual in the sequence.

Summary of current active research


Professor Tim Cootes

  • Development of statistical models of facial appearance and behaviour
  • Development of efficient algorithms to match such models to images and image sequences
  • Development of face recognition algorithms using such models

Professor Cootes heads the Faces group within Imaging Sciences, and has a long history of developing and applying statistical models of appearance to many different problems.

Professor Chris Taylor

  • Development of statistical models of facial appearance and behaviour
  • Development of efficient algorithms to match such models to images and image sequences