Presentation 2003/11/13
A Method of Combing Multiple Experts for Face Detection from Cluttered Images
Linlin HUANGT, Akinobu SHIMIZU, Hidefiimi KOBATAKE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we present a face detection approach by combining multiple experts. We use four detection experts differing in feature representation of local image: intensities, Gabor, gradient and 2D Harr wavelet. The four experts employ the same classification model, namely, a polynomial neural network (PNN) on reduced feature subspace learned by principal component analysis (PCA). The outputs of the four PNNs are fused to make the final decision of face detection. The experiments on a large number of images have resulted in significant improvements compared to the best individual expert and the state-of-art methods proposed in the literature.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face detection / multiple expert / feature representation / polynomial neural network / principal component analysis
Paper # PRMU2003-147,HIP2003-53
Date of Issue

Conference Information
Committee HIP
Conference Date 2003/11/13(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Human Information Processing (HIP)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Method of Combing Multiple Experts for Face Detection from Cluttered Images
Sub Title (in English)
Keyword(1) Face detection
Keyword(2) multiple expert
Keyword(3) feature representation
Keyword(4) polynomial neural network
Keyword(5) principal component analysis
1st Author's Name Linlin HUANGT
1st Author's Affiliation Graduate school of BASE, Tokyo university of Agri. & Tech.()
2nd Author's Name Akinobu SHIMIZU
2nd Author's Affiliation Graduate school of BASE, Tokyo university of Agri. & Tech.
3rd Author's Name Hidefiimi KOBATAKE
3rd Author's Affiliation Graduate school of BASE, Tokyo university of Agri. & Tech.
Date 2003/11/13
Paper # PRMU2003-147,HIP2003-53
Volume (vol) vol.103
Number (no) 454
Page pp.pp.-
#Pages 6
Date of Issue