Age and gender classification has received more attention recently owing to its important role in user-friendly intelligent systems. In this paper, we propose a convolutional neural network (CNN) based architecture for joint age-gender classification, where we use the Gabor filter responses as the input. The weighting of Gabor-filter responses is learned through back-propagation in an end-to-end architecture. The architecture is trained to label the input images into 8 ranges of age and 2 types of gender. Our approach shows improved accuracy in both age and gender classification compared to the state-of-the-art methodologies. We also observe that increasing the width of neural network would increase the accuracy of the overall system.
