Close
Metadata

Reference TypeConference Proceedings
Repositorysid.inpe.br/sibgrapi@80/2007/08.02.10.54
Metadatasid.inpe.br/sibgrapi@80/2007/08.02.10.54.45
Sitesibgrapi.sid.inpe.br
Citation KeyLeitePeGoVeSaNaCa:2007:LeEyDe
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
TitleA learning-based eye detector coupled with eye candidate filtering and PCA features
Conference NameBrazilian Symposium on Computer Graphics and Image Processing, 20 (SIBGRAPI)
Year2007
EditorFalcão, Alexandre Xavier
Lopes, Hélio Côrtes Vieira
Book TitleProceedings
DateOct. 7-10, 2007
Publisher CityLos Alamitos
PublisherIEEE Computer Society
Conference LocationBelo Horizonte
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%. .
Languageen
Tertiary TypeFull Paper
FormatPrinted, On-line.
Size181 KiB
Number of Files1
Target Filegomes-EyeDetection.pdf
Last Update2007:08.02.10.54.44 sid.inpe.br/banon/2001/03.30.15.38 administrator
Metadata Last Update2020:02.19.03.06.19 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2007}
Document Stagecompleted
Is the master or a copy?is the master
Mirrordpi.inpe.br/banon-pc2@80/2006/08.30.19.27
User Grouphmg@dsc.ufcg.edu.br administrator
Visibilityshown
Transferable1
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Content TypeExternal Contribution
source Directory Contentthere are no files
agreement Directory Contentthere are no files
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
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
Access Date2020, Oct. 26

Close