Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Last Update1998: (UTC) administrator
Metadata Last Update2013: (UTC) administrator
Citation KeyMoreiraCost:1996:NeCoIm
TitleNeural-based color image segmentation and classification using self-organizing maps
FormatImpresso, On-line.
Access Date2021, Dec. 02
Number of Files1
Size77 KiB
Context area
Author1 Moreira, Jander
2 Costa, Luciano da Fontoura
EditorVelho, Luiz
Albuquerque, Arnaldo de
Lotufo, Roberto A.
Conference NameSimpósio Brasileiro de Computação Gráfica e Processamento de Imagens, 9 (SIBGRAPI)
Conference LocationCaxambu
Date29 out. - 1 nov. 1996
PublisherSociedade Brasileira de Computação
Publisher CityPorto Alegre
Book TitleAnais
Tertiary TypeArtigo
OrganizationSBC - Sociedade Brasileira de Computação; UFMG - Universidade Federal de Minas Gerais
History (UTC)2008-07-17 14:17:55 :: administrator -> banon ::
2010-08-28 20:04:48 :: banon -> administrator ::
2013-04-05 16:31:17 :: administrator -> banon :: 1996
2013-04-05 16:47:49 :: banon -> administrator :: 1996
2013-04-19 14:14:55 :: administrator -> banon :: 1996
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Keywordscolor segmentation
neural networks
self-organizing maps
k-means segmentation
nearest-neighbor classification
AbstractThis paper presents a method for color image segmentation which uses classification to group pixels into regions. The chromaticity is used as data source for the method because it is normalized and considers only hue and saturation, excluding the luminance component. The classification is carried out by means of a self-organizing map (SOM), which is employed to obtain the main chromaticities present in the image. Then, each pixel is classified according to the identified classes. The number of classes is a priori unknown and the artificial neural network that implements the SOM is used to determine the main classes. The detection of the classes in the SOM is done by using a K-means segmentation. The obtained results substantiate the feasibility of the method, whose performance is compared, for evaluation, to human-assisted segmentation. A comparison of the method with a segmentation based on the k-nearest-neighbor classification is also presented.
TypeReconhecimento de Padrões
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Contentthere are no files
Conditions of access and use area
data URL
zipped data URL
Target Filea19.pdf
User Groupadministrator
Allied materials area
Notes area
Empty Fieldsaccessionnumber affiliation archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi e-mailaddress edition electronicmailaddress group holdercode issn label lineage mark nextedition nexthigherunit notes numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark url versiontype volume
Description control area
e-Mail (login)banon