Adaptive feature selection for real-time face recognition in portable surveillance systems

Wen Chung Kao, Chia Ping Shen, Chin Chung Kao, Ming Chai Hsu, Hung Hsin Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Real-time face recognition is a necessary feature in advanced portable surveillance systems. However, the high complexity of available algorithms to objects segmentation and recognition makes it impossible to include such a feature into a portable device. In this paper, we aim at designing a portable surveillance system which can take MPEG audio/video currently with recognizing human faces based on a digital camera platform. The proposed flow fully utilizes the available intermediate data passing from standard video compression flow in a digital camera. An efficient face recognition approach based on adaptive feature extraction and support vector machines (SVMs) are proposed to address the performance issues. The experimental result shows that the recognition speed running on a commercial digital camera platform can achieve 1.216 seconds/frame.

Original languageEnglish
Title of host publication2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007
Pages1083-1087
Number of pages5
DOIs
Publication statusPublished - 2007 Dec 1
Event2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007 - Montreal, QC, Canada
Duration: 2007 Oct 72007 Oct 10

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
ISSN (Print)1062-922X

Other

Other2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007
CountryCanada
CityMontreal, QC
Period07/10/707/10/10

Fingerprint

Digital cameras
Face recognition
Feature extraction
Image compression
Support vector machines

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Kao, W. C., Shen, C. P., Kao, C. C., Hsu, M. C., & Wu, H. H. (2007). Adaptive feature selection for real-time face recognition in portable surveillance systems. In 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007 (pp. 1083-1087). [4413922] (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). https://doi.org/10.1109/ICSMC.2007.4413922

Adaptive feature selection for real-time face recognition in portable surveillance systems. / Kao, Wen Chung; Shen, Chia Ping; Kao, Chin Chung; Hsu, Ming Chai; Wu, Hung Hsin.

2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007. 2007. p. 1083-1087 4413922 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kao, WC, Shen, CP, Kao, CC, Hsu, MC & Wu, HH 2007, Adaptive feature selection for real-time face recognition in portable surveillance systems. in 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007., 4413922, Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, pp. 1083-1087, 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007, Montreal, QC, Canada, 07/10/7. https://doi.org/10.1109/ICSMC.2007.4413922
Kao WC, Shen CP, Kao CC, Hsu MC, Wu HH. Adaptive feature selection for real-time face recognition in portable surveillance systems. In 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007. 2007. p. 1083-1087. 4413922. (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). https://doi.org/10.1109/ICSMC.2007.4413922
Kao, Wen Chung ; Shen, Chia Ping ; Kao, Chin Chung ; Hsu, Ming Chai ; Wu, Hung Hsin. / Adaptive feature selection for real-time face recognition in portable surveillance systems. 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007. 2007. pp. 1083-1087 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).
@inproceedings{c4b9f81e901048efb9d590f925ba69a8,
title = "Adaptive feature selection for real-time face recognition in portable surveillance systems",
abstract = "Real-time face recognition is a necessary feature in advanced portable surveillance systems. However, the high complexity of available algorithms to objects segmentation and recognition makes it impossible to include such a feature into a portable device. In this paper, we aim at designing a portable surveillance system which can take MPEG audio/video currently with recognizing human faces based on a digital camera platform. The proposed flow fully utilizes the available intermediate data passing from standard video compression flow in a digital camera. An efficient face recognition approach based on adaptive feature extraction and support vector machines (SVMs) are proposed to address the performance issues. The experimental result shows that the recognition speed running on a commercial digital camera platform can achieve 1.216 seconds/frame.",
author = "Kao, {Wen Chung} and Shen, {Chia Ping} and Kao, {Chin Chung} and Hsu, {Ming Chai} and Wu, {Hung Hsin}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICSMC.2007.4413922",
language = "English",
isbn = "1424409918",
series = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",
pages = "1083--1087",
booktitle = "2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007",

}

TY - GEN

T1 - Adaptive feature selection for real-time face recognition in portable surveillance systems

AU - Kao, Wen Chung

AU - Shen, Chia Ping

AU - Kao, Chin Chung

AU - Hsu, Ming Chai

AU - Wu, Hung Hsin

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Real-time face recognition is a necessary feature in advanced portable surveillance systems. However, the high complexity of available algorithms to objects segmentation and recognition makes it impossible to include such a feature into a portable device. In this paper, we aim at designing a portable surveillance system which can take MPEG audio/video currently with recognizing human faces based on a digital camera platform. The proposed flow fully utilizes the available intermediate data passing from standard video compression flow in a digital camera. An efficient face recognition approach based on adaptive feature extraction and support vector machines (SVMs) are proposed to address the performance issues. The experimental result shows that the recognition speed running on a commercial digital camera platform can achieve 1.216 seconds/frame.

AB - Real-time face recognition is a necessary feature in advanced portable surveillance systems. However, the high complexity of available algorithms to objects segmentation and recognition makes it impossible to include such a feature into a portable device. In this paper, we aim at designing a portable surveillance system which can take MPEG audio/video currently with recognizing human faces based on a digital camera platform. The proposed flow fully utilizes the available intermediate data passing from standard video compression flow in a digital camera. An efficient face recognition approach based on adaptive feature extraction and support vector machines (SVMs) are proposed to address the performance issues. The experimental result shows that the recognition speed running on a commercial digital camera platform can achieve 1.216 seconds/frame.

UR - http://www.scopus.com/inward/record.url?scp=40949157975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40949157975&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2007.4413922

DO - 10.1109/ICSMC.2007.4413922

M3 - Conference contribution

AN - SCOPUS:40949157975

SN - 1424409918

SN - 9781424409914

T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

SP - 1083

EP - 1087

BT - 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007

ER -