Gender Classification of Facial Images Based on Multiple Facial Regions

In this paper, we describe an experimental investigation to evaluate the significance of different facial regions of a person in the task of gender classification. For this purpose we use a support vector machine (SVM) classifier on face images for gender classification. We perform experiments using different facial regions of varying resolution so that the significance of facial regions in this application can be assessed. According to the results obtained, the upper region of the face proved to be the most significant for the task of gender classification. Moreover, the changes in the resolution of the facial region images do not produce significant changes in the result. Based on the significance of different facial regions, we propose a gender classification method based on fusion of multiple facial regions and show that this method is able to compensate for facial expressions and lead to better overall performance.