Detail of the student project

Topic:Učení odhadování věku z částečně anotovaných obrázků
Department:Katedra kybernetiky
Supervisor:Ing. Vojtěch Franc, Ph.D.
Announce as:Diplomová práce, Bakalářská práce, Semestrální projekt
Description:The state-of-the-art methods for visual age prediction use Convolutional Neural Networks learned from examples. Commonly used supervised learning algorithms require a large number of example faces each being annotated by age. Creating annotated examples manually is laborious and imprecise. The goal of this project will be to develop an algorithm learning CNNs for age prediction from cheap, weakly annotated example images. The weak annotation will involve images partitioned into subsets each containing one dominant identity and having a creation time for each image. The algorithm will find faces of the dominant identity, estimate his/her birth date and use it to deduce the actual age that will be consequently used to learn the age predictor.
Bibliography:- V. Franc, J. Cech. Learning CNNs from Weakly Annotated Facial Images. Image and Vision Computing, 2018.
- V. Franc, J. Cech. Face attribute learning from weakly annotated examples. In Proc. of International Conference on Automatic Face and Gesture Recognition Workshops, Biometrics in the Wild (BWILD), 2017
Responsible person: Petr Pošík