Close
Metadata

Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Repositorysid.inpe.br/sibgrapi@80/2007/08.02.10.54
Last Update2007:08.02.10.54.44 administrator
Metadatasid.inpe.br/sibgrapi@80/2007/08.02.10.54.45
Metadata Last Update2020:02.19.03.06.19 administrator
Citation KeyLeitePeGoVeSaNaCa:2007:LeEyDe
TitleA learning-based eye detector coupled with eye candidate filtering and PCA features
FormatPrinted, On-line.
Year2007
DateOct. 7-10, 2007
Access Date2021, Jan. 16
Number of Files1
Size181 KiB
Context area
Author1 Leite, Bruno de Brito
2 Pereira, Eanes Torres
3 Gomes, Herman Martins
4 Veloso, Luciana Ribeiro
5 Santos, C´ı
6 Nascimento, cero Einstein do
7 de Carvalho, João Marques
Affiliation1 Departamento de Sistemas e Computação, Universidade Federal de Campina Grande
2 Departamento de Sistemas e Computação, Universidade Federal de Campina Grande
3 Departamento de Sistemas e Computação, Universidade Federal de Campina Grande
4 Departamento de Engenharia Elétrica, Universidade Federal de Campina Grande
5 Departamento de Engenharia Elétrica, Universidade Federal de Campina Grande
6 Departamento de Engenharia Elétrica, Universidade Federal de Campina Grande
EditorFalcão, Alexandre Xavier
Lopes, Hélio Côrtes Vieira
Conference NameBrazilian Symposium on Computer Graphics and Image Processing, 20 (SIBGRAPI)
Conference LocationBelo Horizonte
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Tertiary TypeFull Paper
History2007-08-02 10:54:45 :: hmg@dsc.ufcg.edu.br -> administrator ::
2007-08-02 21:17:52 :: administrator -> hmg@dsc.ufcg.edu.br ::
2008-07-17 14:09:43 :: hmg@dsc.ufcg.edu.br -> administrator ::
2009-08-13 20:38:30 :: administrator -> banon ::
2010-08-28 20:02:29 :: banon -> administrator ::
2020-02-19 03:06:19 :: administrator -> :: 2007
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Keywordseye detection, neural networks, principal component analysis, integral image.
AbstractIn this work, we present a system based on a Neural Network classifier for eye detection in human face images. This classifier works on eye candidate regions extracted from a face image and represented by a reduced number of features, selected by Principal Component Analysis. The regions are determined considering that in an image window containing the eye, the gray level distribution will generally assume a pattern of adjacent light-dark-light horizontal and vertical stripes, corresponding to the eyelid, pupil and eyelid, respectively. For training, validation and testing, a database was built with a total of 4,400 images. Experimental results have shown that the proposed approach correctly detects more eyes than any of two existing systems (Rowley-Baluja-Kanade and Machine Perception Toolbox), for eye location error tolerances from 0 to 5 pixels. Considering an error tolerance of 9 pixels, the correct detection rate achieved was above 90%. .
source Directory Contentthere are no files
agreement Directory Contentthere are no files
Conditions of access and use area
data URLhttp://urlib.net/rep/sid.inpe.br/sibgrapi@80/2007/08.02.10.54
zipped data URLhttp://urlib.net/zip/sid.inpe.br/sibgrapi@80/2007/08.02.10.54
Languageen
Target Filegomes-EyeDetection.pdf
User Grouphmg@dsc.ufcg.edu.br
administrator
Visibilityshown
Allied materials area
Mirror Repositorydpi.inpe.br/banon-pc2@80/2006/08.30.19.27
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi e-mailaddress edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition nexthigherunit notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume

Close