Close
Metadata

Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPBW34M/3CA22GH
Repositorysid.inpe.br/sibgrapi/2012/07.15.23.58
Last Update2012:07.15.23.58.11 apneto@icmc.usp.br
Metadatasid.inpe.br/sibgrapi/2012/07.15.23.58.11
Metadata Last Update2020:02.19.02.18.29 administrator
Citation KeyCasacaGFTPPNP:2012:CoMuPr
TitleColorization by Multidimensional Projection
FormatDVD, On-line.
Year2012
Access Date2021, Jan. 24
Number of Files1
Size5392 KiB
Context area
Author1 Casaca, Wallace
2 Gomez-Nieto, Erick
3 Ferreira, Cynthia O. L.
4 Tavares, Geovan
5 Pagliosa, Paulo
6 Paulovich, Fernando
7 Nonato, Luis Gustavo
8 Paiva, Afonso
Affiliation1 ICMC-USP
2 ICMC-USP
3 PUC-Rio
4 PUC-Rio
5 UFMS
6 ICMC-USP
7 ICMC-USP
8 ICMC-USP
EditorFreitas, Carla Maria Dal Sasso
Sarkar, Sudeep
Scopigno, Roberto
Silva, Luciano
e-Mail Addressapneto@icmc.usp.br
Conference NameConference on Graphics, Patterns and Images, 25 (SIBGRAPI)
Conference LocationOuro Preto
DateAug. 22-25, 2012
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Tertiary TypeFull Paper
History2012-09-20 16:45:34 :: apneto@icmc.usp.br -> administrator :: 2012
2020-02-19 02:18:29 :: administrator -> :: 2012
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Keywordsimage colorization, image processing, multidimensional projection, high dimensional data.
AbstractMost image colorization techniques assign colors to grayscale images by embedding image pixels into a highdimensional feature space and applying a color pattern to each cluster of high-dimensional data. A main drawback of such an approach is that, depending on texture patterns and image complexity, clusters of similar pixels can hardly be defined automatically, rendering existing methods prone to fail. In this work we present a novel approach to colorize grayscale images that allows for user intervention. Our methodology makes use of multidimensional projection to map high-dimensional data to a visual space. User can manipulate projected data in the visual space so as to further improve clusters and thus the colorization result. Different from other methods, our interactive tool is ease of use while still being flexible enough to enable local color modification. We show the effectiveness of our approach through a set of examples and comparisons against existing colorization methods.
source Directory Contentthere are no files
agreement Directory Content
agreement.html 15/07/2012 20:58 0.7 KiB 
Conditions of access and use area
data URLhttp://urlib.net/rep/8JMKD3MGPBW34M/3CA22GH
zipped data URLhttp://urlib.net/zip/8JMKD3MGPBW34M/3CA22GH
Languageen
Target Fileprojcolor_final.pdf
User Groupapneto@icmc.usp.br
Visibilityshown
Allied materials area
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
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 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