Theories of beauty were evaluated by requiring subjects to ''evolve''
a beautiful female face using a Genetic Algorithm. In this procedure,
a computer program generated a small population of faces (first genera
tion of phenotypes) from a set of random binary strings (genotypes). G
enotypes specified the shapes and soft tissue anthropometrics of facia
l features. Each of the first generation of faces was rated by a subje
ct (relative fitness measure) for beauty. The fittest genotypes then b
red in proportion to their fitness, with crossover and mutation of the
binary strings, to produce offspring which were again rated by the su
bject. This process continued until the most beautiful face, for that
subject, was evolved. Forty Caucasian subjects (20 M, 20 F) were requi
red to evolve their idealized beautiful female face using this procedu
re. The features and soft tissue anthropometrics of their final compos
ites were compared to population norms. Also, the final composites, an
d different faces generated from the same data base, were rated for be
auty by independent judges. The results support the conclusion that th
e concept of facial beauty is the result of sexual selection, and a be
autiful female face has features and proportions indicative of high fe
rtility.