Advanced search
1 file | 1.10 MB Add to list

Real-time reservoir computing network-based systems for detection tasks on visual contents

Author
Organization
Abstract
Among the various types of artificial neural networks used for event detection in visual contents, those with the ability of processing temporal information, such as recurrent neural networks, have been proved to be more effective. However, training of such networks is often difficult and time consuming. In this work, we show how Reservoir Computing Networks (RCNs) can be used for detecting purposes on raw images. The applicability of RCNs is illustrated using two example challenges, namely isolated digit handwriting recognition on the MNIST dataset as well as detection of the status of a door using self-developed moving pictures from a surveillance camera. Achieving an error rate of 0.92 percent on MNIST, we show that RCN can be a serious competitor to the state-of-the-art. Moreover, we show how RCNs with their simple and yet robust training procedure can be practically used for real surveillance tasks using very low resolution camera sensors.
Keywords
robust video processing, Reservoir computing networks, surveillance camera, image processing, RECOGNITION

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.10 MB

Citation

Please use this url to cite or link to this publication:

MLA
Jalalvand, Azarakhsh, Glenn Van Wallendael, and Rik Van de Walle. “Real-time Reservoir Computing Network-based Systems for Detection Tasks on Visual Contents.” PROCEEDINGS 7TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, COMMUNICATION SYSTEMS AND NETWORKS CICSYN 2015 . International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN): IEEE Conference Publishing Service (CPS), 2015. 146–151. Print.
APA
Jalalvand, A., Van Wallendael, G., & Van de Walle, R. (2015). Real-time reservoir computing network-based systems for detection tasks on visual contents. PROCEEDINGS 7TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, COMMUNICATION SYSTEMS AND NETWORKS CICSYN 2015 (pp. 146–151). Presented at the 7th International Conference on Computational Intelligence, Communication Systems and Networks , International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN): IEEE Conference Publishing Service (CPS).
Chicago author-date
Jalalvand, Azarakhsh, Glenn Van Wallendael, and Rik Van de Walle. 2015. “Real-time Reservoir Computing Network-based Systems for Detection Tasks on Visual Contents.” In PROCEEDINGS 7TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, COMMUNICATION SYSTEMS AND NETWORKS CICSYN 2015 , 146–151. International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN): IEEE Conference Publishing Service (CPS).
Chicago author-date (all authors)
Jalalvand, Azarakhsh, Glenn Van Wallendael, and Rik Van de Walle. 2015. “Real-time Reservoir Computing Network-based Systems for Detection Tasks on Visual Contents.” In PROCEEDINGS 7TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, COMMUNICATION SYSTEMS AND NETWORKS CICSYN 2015 , 146–151. International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN): IEEE Conference Publishing Service (CPS).
Vancouver
1.
Jalalvand A, Van Wallendael G, Van de Walle R. Real-time reservoir computing network-based systems for detection tasks on visual contents. PROCEEDINGS 7TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, COMMUNICATION SYSTEMS AND NETWORKS CICSYN 2015 . International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN): IEEE Conference Publishing Service (CPS); 2015. p. 146–51.
IEEE
[1]
A. Jalalvand, G. Van Wallendael, and R. Van de Walle, “Real-time reservoir computing network-based systems for detection tasks on visual contents,” in PROCEEDINGS 7TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, COMMUNICATION SYSTEMS AND NETWORKS CICSYN 2015 , Riga, Latvia, 2015, pp. 146–151.
@inproceedings{7033396,
  abstract     = {Among the various types of artificial neural networks used for event detection in visual contents, those with the ability of processing temporal information, such as recurrent neural networks, have been proved to be more effective. However, training of such networks is often difficult and time consuming. In this work, we show how Reservoir Computing Networks (RCNs) can be used for detecting purposes on raw images. The applicability of RCNs is illustrated using two example challenges, namely isolated digit handwriting recognition on the MNIST dataset as well as detection of the status of a door using self-developed moving pictures from a surveillance camera. Achieving an error rate of 0.92 percent on MNIST, we show that RCN can be a serious competitor to the state-of-the-art. Moreover, we show how RCNs with their simple and yet robust training procedure can be practically used for real surveillance tasks using very low resolution camera sensors.},
  author       = {Jalalvand, Azarakhsh and Van Wallendael, Glenn and Van de Walle, Rik},
  booktitle    = {PROCEEDINGS 7TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, COMMUNICATION SYSTEMS AND NETWORKS CICSYN 2015 },
  isbn         = {978-1-4673-7016-5},
  keywords     = {robust video processing,Reservoir computing networks,surveillance camera,image processing,RECOGNITION},
  language     = {eng},
  location     = {Riga, Latvia},
  pages        = {146--151},
  publisher    = {IEEE Conference Publishing Service (CPS)},
  title        = {Real-time reservoir computing network-based systems for detection tasks on visual contents},
  url          = {http://dx.doi.org/10.1109/CICSyN.2015.35},
  year         = {2015},
}

Altmetric
View in Altmetric
Web of Science
Times cited: