• Jul 03, 2017 News!JACN Vol.4, No.2 has been indexed by EI (inspec)!   [Click]
  • Jul 12, 2017 News!JACN Vol.5, No.1 has been published with online version.
  • Jul 03, 2017 News!Welcome to join in the 2017 8th International Conference on Networking and Information Technology (ICNIT 2017), which will be held in Penang, Malaysia during November 24-26, 2017.
General Information
    • ISSN: 1793-8244
    • Frequency: Semiyearly
    • DOI: 10.18178/JACN
    • Editor-in-Chief: Dr. Ka Wai Gary Wong
    • Executive Editor: Ms. Nina Lee
    • Abstracting/ Indexing: EI (INSPEC, IET), Engineering & Technology Digital Library, DOAJ, Electronic Journals Library, Ulrich's Periodicals Directory, International Computer Science Digital Library (ICSDL), ProQuest, and Google Scholar.
    • E-mail: jacn@ejournal.net
Editor-in-chief
Dr. Ka Wai Gary Wong
Division of Information and Technology Studies, Faculty of Education, The University of Hong Kong.
It's a honor to serve as the editor-in-chief of JACN. I'll work together with the editors and reviewers to help the journal progress
JACN 2014 Vol.2(1): 58-62 ISSN: 1793-8244
DOI: 10.7763/JACN.2014.V2.82

Automatic Classification of Human Body Postures Based on the Truncated SVD

N. Zerrouki and A. Houacine
Abstract—In this experimental study, we propose the use of Singular Value Decomposition (SVD) coefficients as features to automatically classify human body postures. The classification process uses images extracted from a fixed camera video. A background subtraction technique is applied for human body segmentation. A truncated SVD is performed by selecting significant magnitude coefficients. And the height-width ratio of the human body is also included in the set of features. The classification is then performed using an Artificial Neural Network (ANN). Four body postures are considered in our experiments, namely: standing, bending, sitting, and lying. Evaluation results show that the proposed method achieved 90.46% classification accuracy. Truncated SVD coefficients and height-width ratio as body posture features are thus appropriate descriptors to achieve high classification accuracy. Also, the proposed method yields the best classification accuracy compared to well-known classification methods.

Index Terms—Human body postures, classification, SVD coefficients, neural network.

The authors are with LCPTS laboratory, University of Sciences and Technology Houari Boumédienne, Algeria (e-mail: nzerrouki@usthb.dz, ahouacine@usthb.dz).

[PDF]

Cite:N. Zerrouki and A. Houacine, "Automatic Classification of Human Body Postures Based on the Truncated SVD," Journal of Advances in Computer Networks vol. 2, no. 1, pp. 58-62, 2014.

Copyright © 2008-2017. Journal of Advances in Computer Networks.  All rights reserved.
E-mail: jacn@ejournal.net