Improving Face Age Prediction by Using Multiple-Angle Photos.

Face photo-based age provides a cost-effective and readily accessible tool for biological age studies. However, artificial intelligence-based face photo age models were usually trained on a single front-view photo per subject. Here, we hypothesized that face photo-based age prediction performance might be improved by using multiple photos of the same subject at the same time, captured from different angles. To test this hypothesis, we used an available dataset containing mugshots and developed age prediction models trained on (a) only front-view images, (b) only the side-view images, and (c) both front and side images. We found that accurate age prediction is possible using side photos despite the smaller facial area compared to front-facing photos [mean absolute error (MAE) = 3.1 years for the front-view and MAE = 3.7 years for the side-view images]. The age prediction performance further improved by using 2 images from one person at the same time, captured from 2 different angles, front and side (MAE = 2.88 years). We found that subjects who age faster based on front-view face photos generally age faster based on side-view face photos. We also found that side-view models handle the rotation of the face better compared to the front-view model. In summary, we showed that 2 photos of the face at different angles can slightly improve age prediction and may provide a more robust and better approximation of biological age compared to single photos, serving as a useful tool for personalized medicine, aging intervention, and rejuvenation studies. The models are available for academic research purposes at https://photoage.sztaki.hu/.