Open AccessDeep Face Recognition
Author(s) -
Omkar Parkhi,
Andrea Vedaldi,
Andrew Zisserman
Publication year - 2015
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5244/c.29.41
Subject(s) - computer science , facial recognition system , convolutional neural network , artificial intelligence , traverse , deep learning , automation , face (sociological concept) , task (project management) , scale (ratio) , pattern recognition (psychology) , training set , feature extraction , set (abstract data type) , data set , computer vision , machine learning , engineering , social science , geodesy , systems engineering , quantum mechanics , sociology , programming language , geography , mechanical engineering , physics
The goal of this paper is face recognition – from either a single photograph or from a set of faces tracked in a video. Recent progress in this area has been due to two factors: (i) end to end learning for the task using a convolutional neural network (CNN), and (ii) the availability of very large scale training datasets. We make two contributions: first, we show how a very large scale dataset (2.6M images, over 2.6K people) can be assembled by a combination of automation and human in the loop, and discuss the trade off between data purity and time; second, we traverse through the complexities of deep network training and face recognition to present methods and procedures to achieve comparable state of the art results on the standard LFW and YTF face benchmarks.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom