Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/42867
Title: Face and facial feature detection evaluation. Performance evaluation of public domain haar detectors for face and facial feature detection
Authors: Castrillón-Santana, M. 
Déniz-Suárez, O.
Antón-Canalís, L.
Lorenzo-Navarro, J. 
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: Face and facial feature detection
Haar wavelets
Human computer interaction
Issue Date: 2008
Project: Tecnicas Para El Robustecimiento de Procesos en Vision Artificial Para la Interaccion 
Conference: 3rd International Conference on Computer Vision Theory and Applications 
Abstract: Fast and reliable face and facial feature detection are required abilities for any Human Computer Interaction approach based on Computer Vision. Since the publication of the Viola-Jones object detection framework and the more recent open source implementation, an increasing number of applications have appeared, particularly in the context of facial processing. In this respect, the OpenCV community shares a collection of public domain classifiers for this scenario. However, as far as we know these classifiers have never been evaluated and/or compared. In this paper we analyze the individual performance of all those public classifiers getting the best performance for each target. These results are valid to define a baseline for future approaches. Additionally we propose a simple hierarchical combination of those classifiers to increase the facial feature detection rate while reducing the face false detection rate.
URI: http://hdl.handle.net/10553/42867
ISBN: 978-989-8111-21-0
DOI: 10.5220/0001073101670172
Source: Visapp 2008: Proceedings Of The Third International Conference On Computer Vision Theory And Applications, Vol 2, p. 167-172, (2008)
Appears in Collections:Actas de congresos
Thumbnail
pdf
Adobe PDF (457,97 kB)
Show full item record

SCOPUSTM   
Citations

38
checked on Dec 8, 2024

WEB OF SCIENCETM
Citations

14
checked on Feb 25, 2024

Page view(s)

248
checked on Oct 19, 2024

Download(s)

398
checked on Oct 19, 2024

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.