TY - GEN
T1 - Real-Time Reservoir Computing Network-Based Systems for Detection Tasks on Visual Contents
AU - Jalalvand, Azarakhsh
AU - Wallendael, Glenn Van
AU - Walle, Rik Van De
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/10/28
Y1 - 2015/10/28
N2 - 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.
AB - 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.
KW - image processing
KW - Reservoir computing networks
KW - robust video processing
KW - surveillance camera
UR - http://www.scopus.com/inward/record.url?scp=84962073286&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84962073286&partnerID=8YFLogxK
U2 - 10.1109/CICSyN.2015.35
DO - 10.1109/CICSyN.2015.35
M3 - Conference contribution
AN - SCOPUS:84962073286
T3 - Proceedings - 7th International Conference on Computational Intelligence, Communication Systems and Networks, CICSyN 2015
SP - 146
EP - 151
BT - Proceedings - 7th International Conference on Computational Intelligence, Communication Systems and Networks, CICSyN 2015
A2 - Romanovs, Andrejs
A2 - Merkuryeva, Galina
A2 - Merkuryev, Yuri
A2 - Al-Dabass, David
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Conference on Computational Intelligence, Communication Systems and Networks, CICSyN 2015
Y2 - 3 June 2015 through 5 June 2015
ER -