Irdeto protects digital platforms and applications for media & entertainment, automotive, and IoT connected industries. Irdeto solutions and services enable its customers to protect their brand and revenues, create new offerings and fight cybercrime. Irdeto is a part of Naspers. Founded in 1915, Naspers is a global internet and entertainment group and one of the largest technology investors in the world. Operating in more than 120 countries and markets with long-term growth potential, Naspers builds leading companies that empower people and enrich communities. It runs some of the world’s leading platforms in internet, video entertainment, and media.
The goal of the project is to develop a solution for face clustering using face representation by a state-of-the-art convolutional neural network. Given a set containing a number of unlabeled face images, the solution shall cluster them into the individual identities. The constraints/assumptions are
- number of images in a set, N, vary between 100 and 500;
- number of identities in an image set can vary from 1 to 0.9*N (where N is the size of the set);
- the number of images per individual in a set is differs between identities.
Three datasets are suggested for the assignment: IMDB-WIKI (20284 celebrities, 523051 images), LFW dataset (13233 images, 5749 people), and an internal set (50 rugby players, 4-20 images per player)