More Web Proxy on the site http://driver.im/

research-article

Face recognition on smartphones via optimised sparse representation classification

Authors:

Chun Tung ChouAuthors Info & Claims

IPSN '14: Proceedings of the 13th international symposium on Information processing in sensor networks

Pages 237 - 248

Published: 15 April 2014 Publication History

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.

References

[1]

M. A. Turk and A. P. Pentland, "Face recognition using eigenfaces," in CVPR'91. IEEE, 1991, pp. 586--591.

[2]

P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, "Eigenfaces vs. fisherfaces: Recognition using class specific linear projection," PAMI, vol. 19, no. 7, pp. 711--720, 1997.

Digital Library

[3]

T. Ahonen, A. Hadid, and M. Pietikainen, "Face description with local binary patterns: Application to face recognition," PAMI, vol. 28, no. 12, pp. 2037--2041, 2006.

Digital Library

[4]

J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry, and Y. Ma, "Robust face recognition via sparse representation," PAMI, vol. 31, no. 2, pp. 210--227, 2009.

Digital Library

[5]

B. Wei, M. Yang, Y. Shen, R. Rana, C. T. Chou, and H. Wen, "Real-time classification via sparse representation in acoustic sensor networks," in Sensys'13. ACM, 2013.

Digital Library

[6]

E. Candes, J. Romberg, and T. Tao, "Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information," TIT, pp. 489--509, 2006.

Digital Library

[7]

D. Donoho, "Compressed sensing," TIT, pp. 1289--1306, 2006.

Digital Library

[8]

J. Duarte-Carvajalino and G. Sapiro, "Learning to Sense Sparse Signals: Simultaneous Sensing Matrix and Sparsifying Dictionary Optimization," ITIP, pp. 1395--1408, 2009.

Digital Library

[9]

M. Elad, "Optimized projections for compressed sensing," IEEE Transactions on Signal Processing, vol. 55, no. 12, pp. 5695--5702, 2007.

Digital Library

[10]

A. Krause and C. Guestrin, "Optimizing Sensing: From Water to the Web," Computer, vol. 42, pp. 38--45, 2009.

Digital Library

[11]

E. Candes and J. Romberg, "Sparsity and incoherence in compressive sampling," Inverse problems, vol. 23, no. 3, p. 969, 2007.

[12]

D. Donoho, M. Elad, and V. Temlyakov, "Stable recovery of sparse overcomplete representations in the presence of noise," TIIT, pp. 6--18, 2006.

Digital Library

[13]

J. A. Tropp, "The sparsity gap: Uncertainty principles proportional to dimension," in CISS'10.IEEE, 2010, pp. 1--6.

[14]

R. Calderbank, S. Howard, and S. Jafarpour, "Construction of a large class of deterministic sensing matrices that satisfy a statistical isometry property," IEEE Journal of Selected Topics in Signal Processing, vol. 4, no. 2, pp. 358--374, 2010.

[15]

R. Baraniuk, M. Davenport, R. DeVore, and M. Wakin, "A simple proof of the restricted isometry property for random matrices," Constructive Approximation, pp. 253--263, 2008.

[16]

F. Glover and M. Laguna, Tabu Search. Norwell, MA, USA: Kluwer Academic Publishers, 1997.

Digital Library

[17]

G. Paul, "An efficient implementation of the robust tabu search heuristic for sparse quadratic assignment problems," European Journal of Operational Research, vol. 209, no. 3, pp. 215--218, 2011.

[18]

W. B. Johnson and J. Lindenstrauss, "Extensions of lipschitz mappings into a hilbert space," Conference in modern analysis and probability, 1984.

[19]

A. Georghiades, P. Belhumeur, and D. Kriegman, "From few to many: Illumination cone models for face recognition under variable lighting and pose," PAMI, vol. 23, no. 6, pp. 643--660, 2001.

Digital Library

[20]

AT&T Laboratories Cambridge, The AT&T Database of Faces, 2002. {Online}. Available: http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html.

[21]

D. Cai, X. He, Y. Hu, J. Han, and T. Huang, "Learning a spatially smooth subspace for face recognition," in CVPR '07. IEEE, 2007, pp. 1--7.

[22]

B. Boom, G. Beumer, L. J. Spreeuwers, and R. N. Veldhuis, "The effect of image resolution on the performance of a face recognition system," in ICARCV'06. IEEE, 2006, pp. 1--6.

[23]

M. A. Davenport, M. B. Wakin, and R. G. Baraniuk, "The compressive matched filter," Tech. Rep. TREE 0610, Rice University, Tech. Rep., 2006.

[24]

M. Salman Asif and J. Romberg, "Dynamic updating for l1 minimization," IEEE Journal of Selected Topics in Signal Processing, vol. 4, no. 2, pp. 421--434, 2010.

[25]

S. Nirjon, R. F. Dickerson, Q. Li, P. Asare, J. A. Stankovic, D. Hong, B. Zhang, X. Jiang, G. Shen, and F. Zhao, "Musicalheart: A hearty way of listening to music," in Sensys'12. ACM, 2012, pp. 43--56.

Digital Library

[26]

A. Zhan, M. Chang, Y. Chen, and A. Terzis, "Accurate caloric expenditure of bicyclists using cellphones," in Sensys'12. ACM, 2012, pp. 71--84.

Digital Library

[27]

U. Park and J. Heidemann, "Data muling with mobile phones for sensornets," in Sensys'11. ACM, 2011, pp. 162--175.

Digital Library

[28]

D. Chu, N. D. Lane, T. T.-T. Lai, C. Pang, X. Meng, Q. Guo, F. Li, and F. Zhao, "Balancing energy, latency and accuracy for mobile sensor data classification," in Sensys'11. ACM, 2011, pp. 54--67.

Digital Library

[29]

R. LiKamWa, B. Priyantha, M. Philipose, L. Zhong, and P. Bahl, "Energy characterization and optimization of image sensing toward continuous mobile vision," in Mobisys'13. ACM, 2013.

Digital Library

[30]

B. Liu, Y. Jiang, F. Sha, and R. Govindan, "Cloud-enabled privacy-preserving collaborative learning for mobile sensing," in Sensys'12. ACM, 2012, pp. 57--70.

Digital Library

[31]

P. Gilbert, J. Jung, K. Lee, H. Qin, D. Sharkey, A. Sheth, and L. P. Cox, "Youprove: authenticity and fidelity in mobile sensing," in Sensys'11. ACM, 2011, pp. 176--189.

Digital Library

[32]

C.-W. You, N. D. Lane, F. Chen, R. Wang, Z. Chen, T. J. Bao, M. Montes-de Oca, Y. Cheng, M. Lin, L. Torresani et al., "Carsafe app: Alerting drowsy and distracted drivers using dual cameras on smartphones," Mobisys'13, 2013.

Digital Library

[33]

J. Qiu, D. Chu, X. Meng, and T. Moscibroda, "On the feasibility of real-time phone-to-phone 3d localization," in Sensys'11. ACM, 2011, pp. 190--203.

Digital Library

[34]

Y. Shen, W. Hu, J. Liu, M. Yang, B. Wei, and C. T. Chou, "Efficient background subtraction for real-time tracking in embedded camera networks," in Sensys'12. ACM, 2012, pp. 295--308.

Digital Library

[35]

P. Misra, W. Hu, M. Yang, and S. Jha, "Efficient cross-correlation via sparse representation in sensor networks," in IPSN'12. ACM, 2012, pp. 13--24.

Digital Library

[36]

X. Wu and M. Liu, "In-situ soil moisture sensing: measurement scheduling and estimation using compressive sensing," in IPSN'12. ACM, 2012, pp. 1--12.

Digital Library

Cited By

Marsico MMecca A(2019)A Survey on Gait Recognition via Wearable SensorsACM Computing Surveys10.1145/334029352:4(1-39)Online publication date: 30-Aug-2019
https://dl.acm.org/doi/10.1145/3340293
Wei BHu WYang MChou C(2019)From Real to ComplexACM Transactions on Sensor Networks10.1145/333802615:3(1-32)Online publication date: 9-Aug-2019
https://dl.acm.org/doi/10.1145/3338026
Ma DLan GXu WHassan MHu WGu TKotagiri RLiu H(2017)Unobtrusive User Verification using Piezoelectric Energy HarvestingProceedings of the 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services10.1145/3144457.3144510(541-542)Online publication date: 7-Nov-2017
https://dl.acm.org/doi/10.1145/3144457.3144510
Show More Cited By

Index Terms

Face recognition on smartphones via optimised sparse representation classification
1. Computer systems organization
  1. Embedded and cyber-physical systems
  2. Real-time systems

Recommendations

Pose and illumination variable face recognition via sparse representation and illumination dictionary

This paper addresses the problem of face recognition under pose and illumination variations, and proposes a novel algorithm inspired by the idea of sparse representation (SR). In order to make the SR early designed for the pose-invariant face ...
Approximately symmetrical face images for image preprocessing in face recognition and sparse representation based classification

Though most of the faces are axis-symmetrical objects, few real-world face images are axis-symmetrical images. In the past years, there are many studies on face recognition, but only little attention is paid to this issue and few studies to explore and ...
Pose-robust face recognition via sparse representation

We propose a pose-robust face recognition method to handle the challenging task of face recognition in the presence of large pose difference between gallery and probe faces. The proposed method exploits the sparse property of the representation ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

IPSN '14: Proceedings of the 13th international symposium on Information processing in sensor networks

April 2014

368 pages

ISBN:9781479931460

General Chair:
Adam Wolisz
TU Berlin, Germany
,
Program Chairs:
Jie Liu
Microsoft Research, USA
,
Lin Zhong
Rice University, USA

Sponsors

IEEE
SIGBED: ACM Special Interest Group on Embedded Systems
IEEE-CS\DATC: IEEE Computer Society

Publisher

IEEE Press

Publication History

Published: 15 April 2014

Check for updates

Author Tags

Qualifiers

Research-article

Acceptance Rates

IPSN '14 Paper Acceptance Rate 23 of 111 submissions, 21%;

Overall Acceptance Rate 143 of 593 submissions, 24%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

15
Total Citations
View Citations
516
Total Downloads

Downloads (Last 12 months)4
Downloads (Last 6 weeks)0

Reflects downloads up to 20 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Marsico MMecca A(2019)A Survey on Gait Recognition via Wearable SensorsACM Computing Surveys10.1145/334029352:4(1-39)Online publication date: 30-Aug-2019
https://dl.acm.org/doi/10.1145/3340293
Wei BHu WYang MChou C(2019)From Real to ComplexACM Transactions on Sensor Networks10.1145/333802615:3(1-32)Online publication date: 9-Aug-2019
https://dl.acm.org/doi/10.1145/3338026
Ma DLan GXu WHassan MHu WGu TKotagiri RLiu H(2017)Unobtrusive User Verification using Piezoelectric Energy HarvestingProceedings of the 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services10.1145/3144457.3144510(541-542)Online publication date: 7-Nov-2017
https://dl.acm.org/doi/10.1145/3144457.3144510
Yao SZhao YZhang ASu LAbdelzaher T(2017)DeepIoTProceedings of the 15th ACM Conference on Embedded Network Sensor Systems10.1145/3131672.3131675(1-14)Online publication date: 6-Nov-2017
https://dl.acm.org/doi/10.1145/3131672.3131675
Wang LZhang DYang DPathak AChen CHan XXiong HWang Y(2017)SPACE-TAACM Transactions on Intelligent Systems and Technology10.1145/31316719:2(1-28)Online publication date: 23-Oct-2017
https://dl.acm.org/doi/10.1145/3131671
Luo CCheng LHong HSankaran KChan MLi JMing Z(2017)From mapping to indoor semantic queriesJournal of Network and Computer Applications10.1016/j.jnca.2016.11.02180:C(141-151)Online publication date: 15-Feb-2017
https://dl.acm.org/doi/10.1016/j.jnca.2016.11.021
Xu WShen YBergmann NHu WXing G(2016)Sensor-assisted face recognition system on smart glass via multi-view sparse representation classificationProceedings of the 15th International Conference on Information Processing in Sensor Networks10.5555/2959355.2959357(1-12)Online publication date: 11-Apr-2016
https://dl.acm.org/doi/10.5555/2959355.2959357
Wang YTan RXing GWang JTan XLiu X(2016)Energy-Efficient Aquatic Environment Monitoring Using Smartphone-Based RobotsACM Transactions on Sensor Networks10.1145/293219012:3(1-28)Online publication date: 26-Jul-2016
https://dl.acm.org/doi/10.1145/2932190
Westhoven MPlegge CHenrich TAlexander T(2016)Posture Based Recognition of the Visual Focus of Attention for Adaptive Mobile Information SystemsProceedings, Part I, 10th International Conference on Foundations of Augmented Cognition: Neuroergonomics and Operational Neuroscience - Volume 974310.1007/978-3-319-39955-3_39(416-427)Online publication date: 17-Jul-2016
https://dl.acm.org/doi/10.1007/978-3-319-39955-3_39
Xu WSong JAbdelzaher TMascolo C(2015)Mobile Applications Based on Smart Wearable DevicesProceedings of the 13th ACM Conference on Embedded Networked Sensor Systems10.1145/2809695.2822525(505-506)Online publication date: 1-Nov-2015
https://dl.acm.org/doi/10.1145/2809695.2822525
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents