Abdi H, Valentin D, Edelman B, O'Toole A J, 1995, "More about the difference between men and women: evidence from linear neural networks and the principal-component approach" Perception 24(5) 539 – 562
Download citation data in RIS format
More about the difference between men and women: evidence from linear neural networks and the principal-component approach
Hervé Abdi, Dominique Valentin, Betty Edelman, Alice J O'Toole
Received 20 December 1994
Abstract. The ability of a statistical/neural network to classify faces by sex by means of a pixel-based representation has not been fully investigated. Simulations with pixel-based codes have provided sex-classification results that are less impressive than those reported for measurement-based codes. In no case, however, have the reported pixel-based simulations been optimized for the task of classifying faces by sex. A series of simulations is described in which four network models were applied to the same pixel-based face code. These simulations involved either a radial basis function network or a perceptron as a classifier, preceded or not by a preprocessing step of eigendecomposition. It is shown that performance comparable to that of the measurement-based models can be achieved with pixel-based input (90%) when the data are preprocessed. The effect of the eigendecomposition preprocessing of the faces is then compared with spatial-frequency analysis of face images and analyzed in terms of the perceptual information it captures. It is shown that such an examination may offer insight into the facial aspects important to the sex-classification process. Finally, the contribution of hair information to the performance of the model is evaluated. It is shown that, although the hair contributes to the sex-classification process, it is not the only important contributor.
Full-text PDF size: 4489 Kb
Your computer (IP address: 188.8.131.52) has not been recognised as being on a network authorised to view the full text or references of this article. This content is part of our deep back archive. If you are a member of a university library that has a subscription to the journal, please contact your serials librarian (subscriptions information).