Face Recognition on Smartphones via Optimised Sparse Representation Classification

Yiran Shen, Wen Hu, Mingrui Yang, Bo Wei, Simon Lucey, Chun Tung Chou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

42 Citations (Scopus)
21 Downloads (Pure)

Abstract

Face recognition is an element of many smartphone apps, e.g. face unlocking, people tagging and games. Sparse Representation Classification (SRC) is a state-of-the-art face recognition algorithm, which has been shown to outperform many classical face recognition algorithms in OpenCV. The success of SRC is due to its use of l1, which makes SRC robust to noise and occlusions. Since l1 optmisation is computationally intensive, SRC uses random projection matrices to reduce the dimension of the l1 problem. However, random projection matrices do not give consistent classification accuracy. In this paper, we propose a method to optimise the projection matrix for l1-based classification1. Our evaluations, based on publicly available databases and real experiment, show that face recognition based on the optimised projection matrix can be 5-17% more accurate than its random counterpart and OpenCV algorithms. Furthermore, the optimised projection matrix does not have to be re-calculated even if new faces are added to the training set. We implement the SRC with optimised projection matrix on Android smartphones and find that the computation of residuals in SRC is a severe bottleneck, taking up 85-90% of the computation time. To address this problem, we propose a method to compute the residuals approximately, which is 50 times faster but without sacrificing recognition accuracy. Lastly, we demonstrate the feasibility of our new algorithm by the implementation and evaluation of a new face unlocking app and show its robustness to variation to poses, facial expressions, lighting changes and occlusions.
Original languageEnglish
Title of host publicationProceedings of the 13th International Symposium on Information Processing in Sensor Networks
Place of PublicationPiscataway, NJ, USA
PublisherIEEE
Pages237-248
Number of pages12
ISBN (Print)9781479931460
Publication statusPublished - 15 Apr 2014
Event13th International Symposium on Information Processing in Sensor Networks - Berlin, Germany
Duration: 15 Apr 201417 Apr 2014
http://ipsn.acm.org/2014/

Publication series

NameIPSN '14
PublisherIEEE Press

Conference

Conference13th International Symposium on Information Processing in Sensor Networks
Abbreviated titleISPN 2014
CountryGermany
CityBerlin
Period15/04/1417/04/14
Internet address

Fingerprint

Dive into the research topics of 'Face Recognition on Smartphones via Optimised Sparse Representation Classification'. Together they form a unique fingerprint.

Cite this