Deep Face Recognition

• DOI: 10.5244/c.29.41
• Publication Date: 2015-12-23T06:54:07Z
• Authors: Omkar M. Parkhi; Andrea Vedaldi; Andrew Zisserman
• Keywords: Traverse; Training set; Data set

The goal of this paper is face recognition – from either a single photograph or set faces tracked in video. Recent progress area has been due to two factors: (i) end learning for the task using convolutional neural network (CNN), and (ii) availability very large scale training datasets. We make contributions: first, we show how dataset (2.6M images, over 2.6K people) can be assembled by combination automation human loop, discuss trade off between data purity time; second, traverse through complexities deep present methods procedures achieve comparable state art results on standard LFW YTF benchmarks.