Close
Metadata

Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPBW34M/3JLG56S
Repositorysid.inpe.br/sibgrapi/2015/06.12.04.07
Last Update2015:06.12.04.07.28 (UTC) pmiranda@vision.ime.usp.br
Metadatasid.inpe.br/sibgrapi/2015/06.12.04.07.28
Metadata Last Update2020:02.19.02.14.02 (UTC) administrator
Citation KeyAlexandreChowFalcMira:2015:GeFrSu
TitleIFT-SLIC: A general framework for superpixel generation based on simple linear iterative clustering and image foresting transform
FormatOn-line
Year2015
Access Date2021, Nov. 30
Number of Files1
Size3728 KiB
Context area
Author1 Alexandre, Eduardo Barreto
2 Chowdhury, Ananda Shankar
3 Falcão, Alexandre Xavier
4 Miranda, Paulo A. Vechiatto
Affiliation1 Institute of Mathematics and Statistics (IME), Dept. of Computer Science, University of São Paulo (USP)
2 Dept. of Electronics and Telecommunication Engineering, Jadavpur University, Kolkata, India
3 Institute of Computing, Dept. of Information Systems, University of Campinas
4 Institute of Mathematics and Statistics (IME), Dept. of Computer Science, University of São Paulo (USP)
EditorPapa, João Paulo
Sander, Pedro Vieira
Marroquim, Ricardo Guerra
Farrell, Ryan
e-Mail Addresspmiranda@vision.ime.usp.br
Conference NameConference on Graphics, Patterns and Images, 28 (SIBGRAPI)
Conference LocationSalvador
DateAug. 26-29, 2015
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2015-06-12 04:07:28 :: pmiranda@vision.ime.usp.br -> administrator ::
2020-02-19 02:14:02 :: administrator -> :: 2015
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
KeywordsSimple Linear Iterative Clustering
Image Foresting Transform
Superpixel
unsupervised segmentation
AbstractImage representation based on superpixels has become indispensable for improving efficiency in Computer Vision systems. Object recognition, segmentation, depth estimation, and body model estimation are some important problems where superpixels can be applied. However, superpixels can influence the efficacy of the system in positive or negative manner, depending on how well they respect the object boundaries in the image. In this paper, we improve superpixel generation by extending a popular algorithm - Simple Linear Iterative Clustering (SLIC) - to consider minimum path costs between pixel and cluster centers rather than their direct distances. This creates a new Image Foresting Transform (IFT) operator that naturally defines superpixels as regions of strongly connected pixels by choice of the most suitable path-cost function for a given application. Non-smooth connectivity functions are also explored in our IFT-SLIC approach leading to improved performance. Experimental results indicate better superpixel extraction using the proposed approach as compared to that of SLIC.
Arrangementurlib.net > SDLA > SIBGRAPI 2015 > IFT-SLIC: A general...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 12/06/2015 01:07 0.7 KiB 
Conditions of access and use area
data URLhttp://urlib.net/ibi/8JMKD3MGPBW34M/3JLG56S
zipped data URLhttp://urlib.net/zip/8JMKD3MGPBW34M/3JLG56S
Languageen
Target File00078.pdf
User Grouppmiranda@vision.ime.usp.br
Visibilityshown
Update Permissionnot transferred
Allied materials area
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPBW34M/3K24PF8
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition 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