Gender determination using a Support Vector Machine Variant
Stefanos P. Zafeiriou, Anastasios Tefas, Ioannis Pitas · 2008
In this paper a modified class of Support Vector Ma-chines (SVMs) inspired from the optimization of Fisher’s discriminant ratio is presented. Moreover, we present a novel class of nonlinear decision surfaces by solving the proposed optimization problem in arbitrary Hilbert spaces defined by Mercer’s kernels. The effectiveness of the proposed approach is demonstrated by compar-ing it with the standard SVMs and other classifiers, like Kernel Fisher Discriminant Analysis (KFDA) in gender determination. 1.