Synthetic Images of Faces — An Approach to Model-Based Face Recognition
We present a method of generating realistic views of the head of any individual from a single photograph of the individual and a generic model of a human head.
The generic model is distorted so that it projects correctly onto the photograph. This is done by finding the least energy position of a springframe model, some of whose vertices are constrained to lie on particular features in the photograph.
This gives us a model of the individual, which is then texture mapped using the original photograph to generate the final view. This is perceived to be a realistic view of the individual, even if the model is quite crude.
Unable to display preview. Download preview PDF.
- Frederic I. Parke. Parameterized models for facial animation. IEEE CG&A, pages 61-68, November 1982.Google Scholar
- Patel and Willis. Faces: Facial animation, construction and editing system. In EUROGRAPHICS’ 91, Vienna, September 1991.Google Scholar
- Alf D. Linney. The use of 3-D computer graphics for the simulation and prediction of facial surgery. In Vicki Bruce and Mike Burton, editors, Processing Images of Faces. Ablex, Norwood, NJ. To Appear 1991?Google Scholar
- David Tock, Ian Craw, and Roly Lishman. A knowledge based system for measuring faces. In BMVC90 Proceedings of the British Machine Vision Conference, pages 401-407, University of Oxford, 24–27 September 1990. British Machine Vision Association.Google Scholar
- Alan D. Bennett and Ian Craw. Finding facial features using deformable templates and detailed prior statistical knowledge. In this volume.Google Scholar
- P. J. Benson and D. I. Perrett. Perception and recognition of photographic quality facial caricatures: Implications for the recognition of natural images. European Journal of Cognitive Psychology, 3(1), 1991.Google Scholar
- Ian Craw and Peter J. Cameron. Parameterising images for recognition and reconstruction. In this volume.Google Scholar