A method for detecting human face region based on generation and selection of kernel features

Junya Arakawa, Kenichi Morooka, Yousun Kang, Hiroshi Nagahashi

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

Abstract

Recent researches for detecting face regions from images have paid attention to high dimensional kernel features(KFs), which are obtained by a non-linear transformation of original features extracted from images. A Support Vector Machine(SVM) is one of the most prominent learning algorithms for KFs. However, SVM is time-consuming because of needing a large number of KFs to improve the accuracy of the classification. This paper proposes a new method that constructs a classifier between face and non-face regions by generating and choosing KFs based on Kullback-Leibler Divergence(KLD). The KLD means a distance between two distributions of face and non-face data under a given KF, and some KFs of large KLDs are selected for the face detection. Moreover, the use of KLD enables us to generate new KFs, and to deal with different kinds of KFs concurrently. Some experiments show that our method can reduce the number of KFs much more than SVM, and achieve almost equal or better detection rate than that of SVM.

Original languageEnglish
Title of host publication2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004
Pages2191-2196
Number of pages6
Volume3
DOIs
Publication statusPublished - 2004
Externally publishedYes
Event2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004 - The Hague, Netherlands
Duration: Oct 10 2004Oct 13 2004

Other

Other2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004
CountryNetherlands
CityThe Hague
Period10/10/0410/13/04

Fingerprint

Support vector machines
Face recognition
Learning algorithms
Classifiers
Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Arakawa, J., Morooka, K., Kang, Y., & Nagahashi, H. (2004). A method for detecting human face region based on generation and selection of kernel features. In 2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004 (Vol. 3, pp. 2191-2196) https://doi.org/10.1109/ICSMC.2004.1400653

A method for detecting human face region based on generation and selection of kernel features. / Arakawa, Junya; Morooka, Kenichi; Kang, Yousun; Nagahashi, Hiroshi.

2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004. Vol. 3 2004. p. 2191-2196.

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

Arakawa, J, Morooka, K, Kang, Y & Nagahashi, H 2004, A method for detecting human face region based on generation and selection of kernel features. in 2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004. vol. 3, pp. 2191-2196, 2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004, The Hague, Netherlands, 10/10/04. https://doi.org/10.1109/ICSMC.2004.1400653
Arakawa J, Morooka K, Kang Y, Nagahashi H. A method for detecting human face region based on generation and selection of kernel features. In 2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004. Vol. 3. 2004. p. 2191-2196 https://doi.org/10.1109/ICSMC.2004.1400653
Arakawa, Junya ; Morooka, Kenichi ; Kang, Yousun ; Nagahashi, Hiroshi. / A method for detecting human face region based on generation and selection of kernel features. 2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004. Vol. 3 2004. pp. 2191-2196
@inproceedings{a17db407f8b74d1b877587eecc2994e1,
title = "A method for detecting human face region based on generation and selection of kernel features",
abstract = "Recent researches for detecting face regions from images have paid attention to high dimensional kernel features(KFs), which are obtained by a non-linear transformation of original features extracted from images. A Support Vector Machine(SVM) is one of the most prominent learning algorithms for KFs. However, SVM is time-consuming because of needing a large number of KFs to improve the accuracy of the classification. This paper proposes a new method that constructs a classifier between face and non-face regions by generating and choosing KFs based on Kullback-Leibler Divergence(KLD). The KLD means a distance between two distributions of face and non-face data under a given KF, and some KFs of large KLDs are selected for the face detection. Moreover, the use of KLD enables us to generate new KFs, and to deal with different kinds of KFs concurrently. Some experiments show that our method can reduce the number of KFs much more than SVM, and achieve almost equal or better detection rate than that of SVM.",
author = "Junya Arakawa and Kenichi Morooka and Yousun Kang and Hiroshi Nagahashi",
year = "2004",
doi = "10.1109/ICSMC.2004.1400653",
language = "English",
isbn = "0780385667",
volume = "3",
pages = "2191--2196",
booktitle = "2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004",

}

TY - GEN

T1 - A method for detecting human face region based on generation and selection of kernel features

AU - Arakawa, Junya

AU - Morooka, Kenichi

AU - Kang, Yousun

AU - Nagahashi, Hiroshi

PY - 2004

Y1 - 2004

N2 - Recent researches for detecting face regions from images have paid attention to high dimensional kernel features(KFs), which are obtained by a non-linear transformation of original features extracted from images. A Support Vector Machine(SVM) is one of the most prominent learning algorithms for KFs. However, SVM is time-consuming because of needing a large number of KFs to improve the accuracy of the classification. This paper proposes a new method that constructs a classifier between face and non-face regions by generating and choosing KFs based on Kullback-Leibler Divergence(KLD). The KLD means a distance between two distributions of face and non-face data under a given KF, and some KFs of large KLDs are selected for the face detection. Moreover, the use of KLD enables us to generate new KFs, and to deal with different kinds of KFs concurrently. Some experiments show that our method can reduce the number of KFs much more than SVM, and achieve almost equal or better detection rate than that of SVM.

AB - Recent researches for detecting face regions from images have paid attention to high dimensional kernel features(KFs), which are obtained by a non-linear transformation of original features extracted from images. A Support Vector Machine(SVM) is one of the most prominent learning algorithms for KFs. However, SVM is time-consuming because of needing a large number of KFs to improve the accuracy of the classification. This paper proposes a new method that constructs a classifier between face and non-face regions by generating and choosing KFs based on Kullback-Leibler Divergence(KLD). The KLD means a distance between two distributions of face and non-face data under a given KF, and some KFs of large KLDs are selected for the face detection. Moreover, the use of KLD enables us to generate new KFs, and to deal with different kinds of KFs concurrently. Some experiments show that our method can reduce the number of KFs much more than SVM, and achieve almost equal or better detection rate than that of SVM.

UR - http://www.scopus.com/inward/record.url?scp=15744389913&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=15744389913&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2004.1400653

DO - 10.1109/ICSMC.2004.1400653

M3 - Conference contribution

SN - 0780385667

VL - 3

SP - 2191

EP - 2196

BT - 2004 IEEE International Conference on Systems, Man and Cybernetics, SMC 2004

ER -