Evolutionary generation of faces
Inhaltsverzeichnis
Reference
Peter J. B. Hancock, Charlie D. Frowd: Evolutionary generation of faces. In: Bentley, Peter J.; Corne, David W.: Creative Evolutionary Systems. Academic Press, 2001. 409 - 423
DOI
http://dx.doi.org/10.1016/B978-155860673-9/50055-0
Abstract
This chapter describes a system that allows the evolutionary generation of near-photographic quality face images. The major anticipated use for such a system would be, allowing eyewitnesses to a crime to construct a likeness of the suspect. Current methods for doing this center on photofit-like composite systems. The user is presented with a large range of possible alternatives for major features, such as nose, mouth, and eyes and attempts to reconstruct a face piecemeal. The original photofit does not work very well, probably because it breaks the face into components in a way that we do not usually do when viewing a face. More recent systems, such as CD-fit, are far more flexible, allowing the position, size, and shape of individual features to be altered interactively on a computer. However, the essential problem of being a composite system remains. If you change, for example, the nose, our perception of the eyes and mouth may well change: we perceive faces holistically. The resultant images also look rather synthetic. The system described here produces face images by recombining principal components (eigenfaces), which are inherently global in nature and produce more photographic-like images.
We describe a system that allows the generation of near-photographic quality images of faces, by random recombination of the principal components of faces. Users navigate the available face space through an evolutionary front-end. Each face is rated for likeness to the desired target and an underlying evolutionary algorithm uses these ratings to produce a new set of faces, through recombination and mutation of the underlying parameters. An initial version of the system, using faces of fixed shape, is shown to be successful in allowing users to produce a good likeness of a displayed target
Extended Abstract
Bibtex
@incollection{Hancock2002409,
title = "Chapter 16 - Evolutionary Generation of Faces ",
editor = "Corne, Peter J BentleyDavid W. ",
booktitle = "Creative Evolutionary Systems ",
publisher = "Morgan Kaufmann",
edition = "",
address = "San Francisco",
year = "2002",
pages = "409 - 423",
series = "The Morgan Kaufmann Series in Artificial Intelligence",
isbn = "978-1-55860-673-9",
doi = "http://dx.doi.org/10.1016/B978-155860673-9/50055-0",
url = "http://www.sciencedirect.com/science/article/pii/B9781558606739500550 http://de.evo-art.org/index.php?title=Evolutionary_generation_of_faces ",
author = "Peter J.B. Hancock and Charlie D. Frowd"
}
Used References
Caldwell, C., and V. S. Johnston (1991). Tracking a Criminal Suspect through "Face Space" with a Genetic Algorithm. In R. K. Belew and L. B. Booker (eds.), Proc. Fourth Int. Conf on Genetic Algorithms, Morgan Kaufmann, pp. 416-421.
Craw, I., and P. Cameron (1991). Parameterising Images for Recognition and Reconstruction. In P. Mowforth (ed.), Proc. British Machine Vision Conference, Springer-Verlag, pp. 367-370.
Ellis, H. D., G. M. Davies, and J. W. Shepherd (1978). A Critical Examination of the Photofit System for Recalling Faces. Ergonomics 21:297-307.
Hancock, P. J. B. (1997). A Comparison of Selection Mechanisms. In T. Bck, D. Fogel, and Z. Michalewicz (eds.), Handbook of Evolutionary Computation, Oxford University Press.
Hancock, P. J. B., A. M. Burton, and V. Bruce (1996). Face Processing: Human Perception and Principal Components Analysis. Memory and Cognition 24:26-40.
Johnston, V. S., and M. Franklin (1993). Is Beauty in the Eye of the Beholder? Ethology and Sociobiology 14:183-199.
O'Toole, A. J., and J. L. Thompson (1993). An X Windows Tool for Synthesizing Face Images from Eigenvectors. Behavior Research Methods, Instruments and Computers 25:41-47.
Turk, M., and A. Pentland (1991). Eigenfaces for Recognition. Journal of Cognitive Neuroscience 3:71-86.
