A Method of Combing Multiple Experts for Face Detection from Cluttered Images
スポンサーリンク
概要
- 論文の詳細を見る
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.
- 社団法人電子情報通信学会の論文
- 2003-11-13
著者
-
Kobatake H
Tokyo Univ. Agriculture & Technol. Tokyo Jpn
-
SHIMIZU Akinobu
Graduate School of Bio-Applications and Systems Engineering, Tokyo University of Agriculture and Tec
-
Shimizu A
Tokyo University Of Agriculture And Technology
-
Shimizu Akinobu
Graduate School Of Base Tokyo University Of Agri. & Tech.
-
HUANGT Linlin
Graduate school of BASE, Tokyo university of Agri. & Tech.
-
KOBATAKE Hidefiimi
Graduate school of BASE, Tokyo university of Agri. & Tech.
-
Kobatake Hidefumi
Graduate School Of Bio-applications And Systems Engineering Tokyo Univ. Of Agriculture & Technol
-
Huang Linlin
Graduate School Of Base Tokyo University Of Agri. & Tech.
-
Huangt Linlin
Graduate School Of Base Tokyo University Of Agri. & Tech.
関連論文
- ICA Mixture Analysis of Four-Phase Abdominal CT Images(Biological Engineering)
- Trials of Independent Component Analysis on Multi-phase Abdominal CT Images (関連学会との共催によるバイオメディカルイメージング連合フォーラム) -- (領域抽出及び関連技術)
- Blind source separation using recursive TDD : Introduction of a threshold on separation performance
- A New Method for Solving the Permutation Problem of Frequency-Domain Blind Source Separation(Engineering Acoustics)
- Eigen-structure based near-field wideband sources localization
- Proposal of Atlas-guided Eigen-organ Method for Location Detection of Multi-Organs in Three Dimensional Medical Images(Joint Session 2)
- A Method of Combing Multiple Experts for Face Detection from Cluttered Images
- A Method of Combing Multiple Experts for Face Detection from Cluttered Images
- A Method of Combing Multiple Experts for Face Detection from Cluttered Images
- A Modified Exoskeleton for 3D Shape Description and Recognition
- LI-7 Face detection based on gradient features and polynomial neural network
- A Modified Exoskeleton and Its Application to Object Representation and Recognition
- Face Detection Using Principal Component Analysis and Polynomial Neural Network
- Robust Face Detection Using a Modified Radial Basis Function Network
- Technological Trends of CAD System for Mammography