Robust Face Detection Using a Modified Radial Basis Function Network

LinLin HUANG; Akinobu SHIMIZU; Yoshihiro HAGIHARA; Hidefumi KOBATAKE

Robust Face Detection Using a Modified Radial Basis Function Network

LinLin HUANG, Akinobu SHIMIZU, Yoshihiro HAGIHARA, Hidefumi KOBATAKE

Full Text Views

0

Cite this

Summary :

Face detection from cluttered images is very challenging due to the wide variety of faces and the complexity of image backgrounds. In this paper, we propose a neural network based approach for locating frontal views of human faces in cluttered images. We use a radial basis function network (RBFN) for separation of face and non-face patterns, and the complexity of RBFN is reduced by principal component analysis (PCA). The influence of the number of hidden units and the configuration of basis functions on the detection performance was investigated. To further improve the performance, we integrate the distance from feature subspace into the RBFN. The proposed method has achieved high detection rate and low false positive rate on testing a large number of images.

Publication: IEICE TRANSACTIONS on Information Vol.E85-D No.10 pp.1654-1662

Publication Date: 2002/10/01

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Image Processing, Image Pattern Recognition

Cite this

Copy

LinLin HUANG, Akinobu SHIMIZU, Yoshihiro HAGIHARA, Hidefumi KOBATAKE, "Robust Face Detection Using a Modified Radial Basis Function Network" in IEICE TRANSACTIONS on Information, vol. E85-D, no. 10, pp. 1654-1662, October 2002, doi: .
Abstract: Face detection from cluttered images is very challenging due to the wide variety of faces and the complexity of image backgrounds. In this paper, we propose a neural network based approach for locating frontal views of human faces in cluttered images. We use a radial basis function network (RBFN) for separation of face and non-face patterns, and the complexity of RBFN is reduced by principal component analysis (PCA). The influence of the number of hidden units and the configuration of basis functions on the detection performance was investigated. To further improve the performance, we integrate the distance from feature subspace into the RBFN. The proposed method has achieved high detection rate and low false positive rate on testing a large number of images.
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_10_1654/_p

Copy

@ARTICLE{e85-d_10_1654,
author={LinLin HUANG, Akinobu SHIMIZU, Yoshihiro HAGIHARA, Hidefumi KOBATAKE, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Face Detection Using a Modified Radial Basis Function Network},
year={2002},
volume={E85-D},
number={10},
pages={1654-1662},
abstract={Face detection from cluttered images is very challenging due to the wide variety of faces and the complexity of image backgrounds. In this paper, we propose a neural network based approach for locating frontal views of human faces in cluttered images. We use a radial basis function network (RBFN) for separation of face and non-face patterns, and the complexity of RBFN is reduced by principal component analysis (PCA). The influence of the number of hidden units and the configuration of basis functions on the detection performance was investigated. To further improve the performance, we integrate the distance from feature subspace into the RBFN. The proposed method has achieved high detection rate and low false positive rate on testing a large number of images.},
keywords={},
doi={},
ISSN={},
month={October},}

Copy

TY - JOUR
TI - Robust Face Detection Using a Modified Radial Basis Function Network
T2 - IEICE TRANSACTIONS on Information
SP - 1654
EP - 1662
AU - LinLin HUANG
AU - Akinobu SHIMIZU
AU - Yoshihiro HAGIHARA
AU - Hidefumi KOBATAKE
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2002
AB - Face detection from cluttered images is very challenging due to the wide variety of faces and the complexity of image backgrounds. In this paper, we propose a neural network based approach for locating frontal views of human faces in cluttered images. We use a radial basis function network (RBFN) for separation of face and non-face patterns, and the complexity of RBFN is reduced by principal component analysis (PCA). The influence of the number of hidden units and the configuration of basis functions on the detection performance was investigated. To further improve the performance, we integrate the distance from feature subspace into the RBFN. The proposed method has achieved high detection rate and low false positive rate on testing a large number of images.
ER -