Robust face detection with multi-class boosting

YY Lin*, TL Liu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

35 Scopus citations

Abstract

With the aim to design a general learning framework for detecting faces of various poses or under different lighting conditions, we are motivated to formulate the task as a classification problem over data of multiple classes. Specifically, our approach focuses on a new multi-class boosting algorithm, called MBHboost, and its integration with a cascade structure for effectively performing face detection. There are three main advantages of using MBHboost: 1) each MBH weak learner is derived by sharing a good projection direction such that each class of data has its own decision boundary; 2) the proposed boosting algorithm is established based on an optimal criterion for multi-class classification; and 3) since MBHboost is flexible with respect to the number of classes, it turns out that it is possible to use only one single boosted cascade for the multi-class detection. All these properties give rise to a robust system to detect faces efficiently and accurately.

Original languageEnglish
Title of host publication2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol 1, Proceedings
EditorsC Schmid, S Soatto, C Tomasi
PublisherIEEE COMPUTER SOC
Pages680-687
Number of pages8
ISBN (Print)0-7695-2372-2
DOIs
StatePublished - 2005
EventConference on Computer Vision and Pattern Recognition - San Diego, Canada
Duration: 20 Jun 200525 Jun 2005

Publication series

NamePROCEEDINGS - IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
PublisherIEEE COMPUTER SOC
ISSN (Print)1063-6919

Conference

ConferenceConference on Computer Vision and Pattern Recognition
CountryCanada
CitySan Diego
Period20/06/0525/06/05

Cite this