Age estimation via unsupervised neural networks

Abstract

In this work, we investigate an unsupervised neural network framework for the problem of facial image age estimation. Unlike previous approaches in age estimation where a predefined feature extraction framework is used, the features used in this work are directly learned from the data. A single-layer convolutional neural network and recursive convolutional neural networks are used to extract features from an image. Manifold learning scheme is incorporated in the framework, which maps the features into the discriminative subspace. Furthermore, several popular regression and classification methods are evaluated using this scheme. As far as we know, this is the first work where an unsupervised neural network has been introduced to the age estimation problem. We evaluate the proposed scheme on two widely used datasets. The experimental results show that there is a significant improvement compared to the state-of-the-art.