Multiband curvelet-based technique for audio visual recognition over internet protocol

Sue Inn Ch'ng; Kah Phooi Seng; Fong Tien Ong; Li-Minn Ang

doi:10.1007/978-3-642-32573-1

Multiband curvelet-based technique for audio visual recognition over internet protocol

Sue Inn Ch'ng, Kah Phooi Seng, Fong Tien Ong, Li-Minn Ang

Research output: Book chapter/Published conference paper › Conference paper › peer-review

Abstract

The transmission of the entire video and audio sequences over an internal or external network during the implementation of audio-visual recognition over internet protocol is inefficient especially when only selected data out of the entire video and audio sequences are actually used for the recognition process. Hence, in this paper, we propose an efficient method of implementing audio-visual recognition over internet protocol whereby only the extracted audio-visual features are transmitted over internet protocol. To extract the robust features from the video sequence, a multiband curvelet-based technique is employed at the client whereas a late multi-modal fusion scheme using RBF neural network is employed at the server to perform the recognition across both modalities. The proposed audio-visual recognition system is implemented on several standard audio-visual databases to showcase the efficiency of the system.

Original language	English
Title of host publication	Signal Processing and Information Technology
Subtitle of host publication	First International Joint Conference, SPIT 2011
Editors	Vinu V. Das, Ezendu Ariwa, Syarifah Bahiyah Rahayu
Place of Publication	Berlin, Germany
Publisher	Springer
Pages	132-138
Number of pages	7
Volume	62
ISBN (Electronic)	9783642325731
ISBN (Print)	9783642325724
DOIs	https://doi.org/10.1007/978-3-642-32573-1
Publication status	Published - 2012
Event	Signal Processing and Information Technology (SPIT) - Amsterdam, the Netherlands, Amsterdam, Netherlands Duration: 01 Dec 2011 → 02 Dec 2011 Conference number: 1

Conference

Conference	Signal Processing and Information Technology (SPIT)
Country/Territory	Netherlands
City	Amsterdam
Period	01/12/11 → 02/12/11

Access to Document

10.1007/978-3-642-32573-1

Cite this

@inproceedings{9c03c190b83f4106b78179f6a3c1aecf,

title = "Multiband curvelet-based technique for audio visual recognition over internet protocol",

abstract = "The transmission of the entire video and audio sequences over an internal or external network during the implementation of audio-visual recognition over internet protocol is inefficient especially when only selected data out of the entire video and audio sequences are actually used for the recognition process. Hence, in this paper, we propose an efficient method of implementing audio-visual recognition over internet protocol whereby only the extracted audio-visual features are transmitted over internet protocol. To extract the robust features from the video sequence, a multiband curvelet-based technique is employed at the client whereas a late multi-modal fusion scheme using RBF neural network is employed at the server to perform the recognition across both modalities. The proposed audio-visual recognition system is implemented on several standard audio-visual databases to showcase the efficiency of the system.",

keywords = "curvelet transform, multiband technique, internet protocol, windows sockets",

author = "Ch'ng, {Sue Inn} and Seng, {Kah Phooi} and Ong, {Fong Tien} and Li-Minn Ang",

year = "2012",

doi = "10.1007/978-3-642-32573-1",

language = "English",

isbn = "9783642325724",

volume = "62",

pages = "132--138",

editor = "Das, {Vinu V.} and Ezendu Ariwa and Rahayu, {Syarifah Bahiyah}",

booktitle = "Signal Processing and Information Technology",

publisher = "Springer",

address = "United States",

note = "Signal Processing and Information Technology (SPIT) ; Conference date: 01-12-2011 Through 02-12-2011",

}

Ch'ng, SI, Seng, KP, Ong, FT & Ang, L-M 2012, Multiband curvelet-based technique for audio visual recognition over internet protocol. in VV Das, E Ariwa & SB Rahayu (eds), Signal Processing and Information Technology: First International Joint Conference, SPIT 2011. vol. 62, Springer, Berlin, Germany, pp. 132-138, Signal Processing and Information Technology (SPIT), Amsterdam, Netherlands, 01/12/11. https://doi.org/10.1007/978-3-642-32573-1

Multiband curvelet-based technique for audio visual recognition over internet protocol. / Ch'ng, Sue Inn; Seng, Kah Phooi; Ong, Fong Tien et al.
Signal Processing and Information Technology: First International Joint Conference, SPIT 2011. ed. / Vinu V. Das; Ezendu Ariwa; Syarifah Bahiyah Rahayu. Vol. 62 Berlin, Germany: Springer, 2012. p. 132-138.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Multiband curvelet-based technique for audio visual recognition over internet protocol

AU - Ch'ng, Sue Inn

AU - Seng, Kah Phooi

AU - Ong, Fong Tien

AU - Ang, Li-Minn

N1 - Conference code: 1

PY - 2012

Y1 - 2012

N2 - The transmission of the entire video and audio sequences over an internal or external network during the implementation of audio-visual recognition over internet protocol is inefficient especially when only selected data out of the entire video and audio sequences are actually used for the recognition process. Hence, in this paper, we propose an efficient method of implementing audio-visual recognition over internet protocol whereby only the extracted audio-visual features are transmitted over internet protocol. To extract the robust features from the video sequence, a multiband curvelet-based technique is employed at the client whereas a late multi-modal fusion scheme using RBF neural network is employed at the server to perform the recognition across both modalities. The proposed audio-visual recognition system is implemented on several standard audio-visual databases to showcase the efficiency of the system.

AB - The transmission of the entire video and audio sequences over an internal or external network during the implementation of audio-visual recognition over internet protocol is inefficient especially when only selected data out of the entire video and audio sequences are actually used for the recognition process. Hence, in this paper, we propose an efficient method of implementing audio-visual recognition over internet protocol whereby only the extracted audio-visual features are transmitted over internet protocol. To extract the robust features from the video sequence, a multiband curvelet-based technique is employed at the client whereas a late multi-modal fusion scheme using RBF neural network is employed at the server to perform the recognition across both modalities. The proposed audio-visual recognition system is implemented on several standard audio-visual databases to showcase the efficiency of the system.

KW - curvelet transform

KW - multiband technique

KW - internet protocol

KW - windows sockets

U2 - 10.1007/978-3-642-32573-1

DO - 10.1007/978-3-642-32573-1

M3 - Conference paper

SN - 9783642325724

VL - 62

SP - 132

EP - 138

BT - Signal Processing and Information Technology

A2 - Das, Vinu V.

A2 - Ariwa, Ezendu

A2 - Rahayu, Syarifah Bahiyah

PB - Springer

CY - Berlin, Germany

T2 - Signal Processing and Information Technology (SPIT)

Y2 - 1 December 2011 through 2 December 2011

ER -

Multiband curvelet-based technique for audio visual recognition over internet protocol

Abstract

Conference

Access to Document

Fingerprint

Cite this