Face verification is a widely studied research topic, where the goal is to automatically determine whether two images represent the same person. Until recently, the dominating techniques used
facial landmarks
as the features for identity verification. Typical landmarks include the coordinates of eyes, nose, corner of mouth, etc. More recently
deep learning
based techniques have changed the domain by reaching
human level
accuracy (97 % and above) in the verification process [1,2].
The goal of this competition is to develop algorithms for accurate face verification. The goal is to learn to predict whether a pair of images represent the same person (target output = 1) or a different person (target output = 0). In order to help you get started, we've prepared three sets of possible features: two sets of landmark locations and one set of deep features calculated using the AlexNet as described
[here](http://caffe.berkeleyvision.org/gathered/examples/feature_extraction.html)
.
Prizes:
The best teams from TUT and TUGraz will be donated a T-shirt for each team member. Moreover, the winning team will receive shirts as well, if not from the related courses of the organizing universities. We'll try our best to get hold of
[XKCD shirts](http://store-xkcd-com.myshopify.com/products/sudo)
, although they are in high demand. If not possible, we'll find another nerd T-shirt instead.
Organizers:
Gernot Riegler (Graz University of Technology, Austria) and Heikki Huttunen (Tampere University of Technology, Finland).
[1] Taigman, et al. "Deepface: Closing the gap to human-level performance in face verification,"
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
, 2014.
[2] Schroff, et al., "FaceNet: A Unified Embedding for Face Recognition and Clustering,"
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
, 2015.