Age Estimation with Synthetic Mask Generation Based on MobileNet and Facial Keypoint Detection

Facial age estimation is one of the most important tasks in the field of face recognition and recommendation system. Since the COVID-19 pandemic, people have been required to wear masks, which can be a challenge for traditional recognition methods. In this paper, an improved convolutional neural network architecture based on MobileNet is proposed to perform age estimation. For the challenge of masked faces, an innovative mask generation method using face keypoint detection is adopted, extracting the key points of the faces in order to add synthetic masks to simulate the real situations. Then we compare the estimation results of the original images and the synthetic images. Our method is applied to the WIKI Face dataset containing more than 150,000 images, and achieves MAE of 3.79 and 6.54 on unmasked and masked faces, respectively, which demonstrates the effectiveness of the proposed model.