Age Estimation System Using Deep Residual Network Classification Method

Abstract

The human face has biometric properties that are important for providing age information because of the aging process of the face. Automatic Age estimation is a difficult problem because the relationship between facial images and age is not very linear. Deep residual network (Resnet) is a neural network convolution architecture that was easier to optimize and can gain accuracy results from a considerably increasing depth. In this paper, we propose a new approach age estimation on convolution neural network (CNN) using the deep residual network (Resnet) model. Through the literature, Resnet achieves superior results when compared with other state-of-the-art image classifications. We compare a new generation of deep residual network called ResNeXt with Resnet and a basic linier regression model architecture.We user UTKFace dataset to evaluate the performance of residual network for age estimation of the range 1-100 years old. The result shows that the ResNeXt-50 (32×4d) architecture achieves a better age estimation results than Resnet-50 and linier regression.