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