Multi-View Face Detection with FloatBoost

Authors:
ZhenQiu Zhang1;MingJing Li;Stan Z. Li;HongJiang Zhang
Affiliations:
-;-;-;-
Venue:
WACV '02 Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision
Year:
2002

Citing 0
Cited 4

An adaptive real-time skin detector based on Hue thresholding: A comparison on two motion tracking methods

Pattern Recognition Letters
Audio-video biometric recognition for non-collaborative access granting

Journal of Visual Languages and Computing
A boosted classifier tree for hand shape detection

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Evaluation of Three Vision Based Object Perception Methods for a Mobile Robot

Journal of Intelligent and Robotic Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, a new boosting algorithm, calledFloatBoost, is proposed to construct a strong face-nonfaceclassifier. FloatBoost incorporates the idea ofFloating Search into AdaBoost, and yields similar orhigher classification accuracy than AdaBoost with asmaller number of weak classifiers. We also present anovel framework for fast multi-view face detection. Adetector-pyramid architecture is designed to quicklydiscard a vast number of non-face sub-windows andhence perform multi-view face detection efficiently. Thisresults in the first real-time multi-view face detectionsystem which runs at 5 frames per second for 320x240image sequence.