Gender Classification Using Deep Learning Techniques

Abstract

Gender classification from face images is a challenging task due to presence of complex background, object occlusion, and variations in illumination conditions. Face images can be exploited for various applications such as expression analysis, recognition and tracking. In this paper, two deep learning-based methods are investigated for gender classification using face images. These methods include: convolutional neural network (CNN) and Alex Net. Experiments were performed to evaluate the performance of both models for identification of male and female classes from face images. Results show that both methods were effective for gender classification. Moreover, a comparative analysis was also performed between these two models and some of the popular methods for gender classification.