Accurate Age Estimation Using Multi-Task Siamese Network-Based Deep Metric Learning for Front Face Images

Recently, there have been many studies on the automatic extraction of facial information using machine learning. Age estimation from front face images is becoming important, with various applications. Our proposed work is based on the binary classifier, which only determines whether two input images are clustered in a similar class, and trains the convolutional neural networks (CNNs) model using the deep metric learning method based on the Siamese network. To converge the results of the training Siamese network, two classes, for which age differences are below a certain level of distance, are considered as the same class, so the ratio of positive database images is increased. The deep metric learning method trains the CNN model to measure similarity based on only age data, but we found that the accumulated gender data can also be used to compare ages. From this experimental fact, we adopted a multi-task learning approach to consider the gender data for more accurate age estimation. In the experiment, we evaluated our approach using MORPH and MegaAge-Asian datasets, and compared gender classification accuracy only using age data from the training images. In addition, from the gender classification, we found that our proposed architecture, which is trained with only age data, performs age comparison by using the self-generated gender feature. The accuracy enhancement by multi-task learning, for the simultaneous consideration of age and gender data, is discussed. Our approach results in the best accuracy among the methods based on deep metric learning on MORPH dataset. Additionally, our method is also the best results compared with the results of the state of art in terms of age estimation on MegaAge Asian and MORPH datasets.