Age and Gender Prediction From Face Images Using Attentional Convolutional Network

Automatic prediction of age and gender from a photo is a task useful in different domains: biometrics, identity verification, video surveillance, crowd behavior analysis, online advertisement, and others. Most often, this task is performed using deep neural networks.

Elderly man. Image credit: Pixnio, CC0 Public Domain

Elderly man. Image credit: Pixnio, CC0 Public Domain

A recent paper on proposes a novel age and gender recognition method which combines the attentional network with the residual network. The former lets to attend the most salient and informative parts of the face, e. g. the outline, eyes, and wrinkles. As the results show, the joint model outperforms both individual models.

Also, knowing that information about the person’s gender can lead to better age prediction, the authors of the study use predicted gender as an input for the age prediction. The accuracy of gender detection was 0.965 and the accuracy of age range detection 0.913.

Automatic prediction of age and gender from face images has drawn a lot of attention recently, due it is wide applications in various facial analysis problems. However, due to the large intra-class variation of face images (such as variation in lighting, pose, scale, occlusion), the existing models are still behind the desired accuracy level, which is necessary for the use of these models in real-world applications. In this work, we propose a deep learning framework, based on the ensemble of attentional and residual convolutional networks, to predict gender and age group of facial images with high accuracy rate. Using attention mechanism enables our model to focus on the important and informative parts of the face, which can help it to make a more accurate prediction. We train our model in a multi-task learning fashion, and augment the feature embedding of the age classifier, with the predicted gender, and show that doing so can further increase the accuracy of age prediction. Our model is trained on a popular face age and gender dataset, and achieved promising results. Through visualization of the attention maps of the train model, we show that our model has learned to become sensitive to the right regions of the face.


Leave a Reply

Your email address will not be published. Required fields are marked *