Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network

Lee Seng Yeong; Li Minn Ang; Kah Phooi Seng

doi:10.1109/CIS.2007.132

Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network

Lee Seng Yeong, Li Minn Ang, Kah Phooi Seng

Materials and Manufacturing Engineering

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

2 Citations (Scopus)

Abstract

A dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied to face detection in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm and can grow dynamically during training allowing subclasses in the training data to be learnt. The network is trained using the categorized wavelet coefficients of the image as features of the image. The results suggests a 98% correct detection rate can be achieved with 4% false positives by increasing network complexity.

Original language	English
Title of host publication	Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007
Pages	315-319
Number of pages	5
DOIs	https://doi.org/10.1109/CIS.2007.132
Publication status	Published - 2007
Externally published	Yes
Event	2007 International Conference on Computational Intelligence and Security, CIS'07 - Harbin, Heilongjiang, China Duration: 15 Dec 2007 → 19 Dec 2007

Publication series

Name	Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007

Conference

Conference	2007 International Conference on Computational Intelligence and Security, CIS'07
Country/Territory	China
City	Harbin, Heilongjiang
Period	15/12/07 → 19/12/07

Access to Document

10.1109/CIS.2007.132

Cite this

Yeong, L. S., Ang, L. M., & Seng, K. P. (2007). Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network. In Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007 (pp. 315-319). Article 4415355 (Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007). https://doi.org/10.1109/CIS.2007.132

Yeong, Lee Seng ; Ang, Li Minn ; Seng, Kah Phooi. / Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network. Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007. 2007. pp. 315-319 (Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007).

@inproceedings{10208e9e41ce4048a3a8c34162bc905f,

title = "Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network",

abstract = "A dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied to face detection in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm and can grow dynamically during training allowing subclasses in the training data to be learnt. The network is trained using the categorized wavelet coefficients of the image as features of the image. The results suggests a 98% correct detection rate can be achieved with 4% false positives by increasing network complexity.",

author = "Yeong, {Lee Seng} and Ang, {Li Minn} and Seng, {Kah Phooi}",

year = "2007",

doi = "10.1109/CIS.2007.132",

language = "English",

isbn = "0769530729",

series = "Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007",

pages = "315--319",

booktitle = "Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007",

note = "2007 International Conference on Computational Intelligence and Security, CIS'07 ; Conference date: 15-12-2007 Through 19-12-2007",

}

Yeong, LS, Ang, LM & Seng, KP 2007, Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network. in Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007., 4415355, Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007, pp. 315-319, 2007 International Conference on Computational Intelligence and Security, CIS'07, Harbin, Heilongjiang, China, 15/12/07. https://doi.org/10.1109/CIS.2007.132

Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network. / Yeong, Lee Seng; Ang, Li Minn; Seng, Kah Phooi.
Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007. 2007. p. 315-319 4415355 (Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network

AU - Yeong, Lee Seng

AU - Ang, Li Minn

AU - Seng, Kah Phooi

PY - 2007

Y1 - 2007

N2 - A dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied to face detection in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm and can grow dynamically during training allowing subclasses in the training data to be learnt. The network is trained using the categorized wavelet coefficients of the image as features of the image. The results suggests a 98% correct detection rate can be achieved with 4% false positives by increasing network complexity.

AB - A dynamic counterpropagation network based on the forward only counterpropagation network (CPN) is applied to face detection in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN) trains using a supervised algorithm and can grow dynamically during training allowing subclasses in the training data to be learnt. The network is trained using the categorized wavelet coefficients of the image as features of the image. The results suggests a 98% correct detection rate can be achieved with 4% false positives by increasing network complexity.

UR - http://www.scopus.com/inward/record.url?scp=48349111389&partnerID=8YFLogxK

U2 - 10.1109/CIS.2007.132

DO - 10.1109/CIS.2007.132

M3 - Conference Proceeding

AN - SCOPUS:48349111389

SN - 0769530729

SN - 9780769530727

T3 - Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007

SP - 315

EP - 319

BT - Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007

T2 - 2007 International Conference on Computational Intelligence and Security, CIS'07

Y2 - 15 December 2007 through 19 December 2007

ER -

Yeong LS, Ang LM, Seng KP. Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network. In Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007. 2007. p. 315-319. 4415355. (Proceedings - 2007 International Conference on Computational Intelligence and Security, CIS 2007). doi: 10.1109/CIS.2007.132

Face detection from greyscale images using details from categorized wavelet coefficients as features for a dynamic counterpropagation network

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this