Our research group has published a new paper on face recognition on Raspberry Pi in International Conference on Information Processing and Control Engineering (ICIPCE 2015) in Moscow, Russia.

Abstract
An  embedded  face  recognition  system  based  on  the  Raspberry  Pi  single-board
computer  is  proposed  in  this  paper.  Face  recognition  system  consists  of  face
detection and face localization using Haar feature-based cascade classifier. Face
features are extracted using weighted Local Binary Pattern algorithm. Developed
system performs one full face analysis in 110 ms. Comparison of two biometric
samples is performed in 2 ms. The proposed embedded face recognition system
was  tested  on  FERET  database  and  achieves  accuracy  of  CMC:  99.33%  and
EER: 1%.

Full paper is available here [pdf]