Facial Image Analysis

Tim Cootes

We have a long-standing interest in detecting faces, locating facial features, tracking faces and interpretting facial images.
Recently we have focused on accurate facial feature detection and tracking, and have achieved excellent results using Random Forest Voting in the Constrained Local Model framework [Cootes:ECCV2012].

Current challenges include improving the accuracy, efficiency and robustness of the system, dealing with larger pose variations and analysing the behaviour of the face from the model match results.

Example of face tracking

Tracking with 23 points (1Mb, mpg)

Related projects

Monitoring the faces of drivers
(Funded by Toyota Motor Europe)
Tools for Understanding Facial Behaviour

References

T.F.Cootes, M.Ionita, C.Lindner and P.Sauer, "Robust and Accurate Shape Model Fitting using Random Forest Regression Voting", ECCV 2012 (PDF)

G.J.Edwards, C.J.Taylor and T.F. Cootes. Learning to Identify and Track Faces in Image Sequences. Proc 8th BMVC (Vol.1) (Ed. A.F.Clark) BMVA Press, pp.130-139. 1997. HTML

A.Lanitis, C.J.Taylor and T.F.Cootes, "Towards Automatic Simulation of Ageing Effects on Face Images", IEEE PAMI Vol.24, No.4, pp.442-455

F. Bettinger, T.F. Cootes and C.J. Taylor, "Modelling Facial Behaviours", Proc.BMVC2002, Vol.2, pp.797-806. (PDF)

D. Cristinacce and T.F.Cootes, "Feature Detection and Tracking with Constrained Local Models", Proc. British Machine Vision Conference, Vol. 3, pp.929-938, 2006 (PDF)

A.Caunce, T.F.Cootes and C.J.Taylor, "Improved 3D Model Search for Facial Feature Location and Pose Estimation in 2D images", Proc. British Machine Vision Conference 2010 (PDF)

P. A. Tresadern, M. C. Ionita and T. F. Cootes, "Real-Time Facial Feature Tracking on a Mobile Device", International Journal of Computer Vision, 96(3), pp.280-289, 2012