Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Last Update2017:
Metadata Last Update2020: administrator
Citation KeyPereiraSant:2017:ImReLe
TitleImage representation learning by color quantization optimization
DateOct. 17-20, 2017
Access Date2021, Jan. 21
Number of Files1
Size3513 KiB
Context area
Author1 Pereira, Érico Marco Dias Alves
2 dos Santos, Jefersson Alex
Affiliation1 Universidade Federal de Minas Gerais
2 Universidade Federal de Minas Gerais
EditorTorchelsen, Rafael Piccin
Nascimento, Erickson Rangel do
Panozzo, Daniele
Liu, Zicheng
Farias, Mylène
Viera, Thales
Sacht, Leonardo
Ferreira, Nivan
Comba, João Luiz Dihl
Hirata, Nina
Schiavon Porto, Marcelo
Vital, Creto
Pagot, Christian Azambuja
Petronetto, Fabiano
Clua, Esteban
Cardeal, Flávio
Conference NameConference on Graphics, Patterns and Images, 30 (SIBGRAPI)
Conference LocationNiterói, RJ
Book TitleProceedings
PublisherSociedade Brasileira de Computação
Publisher CityPorto Alegre
Tertiary TypeUndergraduate Work
History2017-09-05 02:31:10 :: -> administrator ::
2017-09-09 18:59:05 :: administrator -> :: 2017
2017-09-11 23:33:16 :: -> administrator :: 2017
2020-02-20 22:06:47 :: administrator -> :: 2017
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Keywordsrepresentation learning, color quantization, CBIR, genetic algorithm, feature extraction.
AbstractThe state-of-art methods of representation learning, based on Deep Neural Networks, present serious drawbacks regarding usage complexity and resources consumption, leaving space for simpler alternatives. We proposed two approaches of a Representation Learning method which aims to provide more effective and compact image representations by optimizing the colour quantization for the image domain. Our hypothesis is that changes in the quantization affect the description quality of the features enabling representation improvements. We evaluated the method performing experiments for the task of Content-Based Image Retrieval on eight known datasets. The results showed that the first approach, focused on representation effectiveness, produced representations that outperforms the baseline in all the tested scenarios. And the second, focused on compactness, was able to produce superior results maintaining or even reducing the dimensionality and representations until 25% smaller that presented statistically equivalent performance.
source Directory Content
Pereira_DosSantos_2017.pdf 04/09/2017 23:31 3.4 MiB
agreement Directory Content
agreement.html 04/09/2017 23:31 1.2 KiB 
Conditions of access and use area
data URL
zipped data URL
Target FilePereira_DosSantos_2017.pdf
Update Permissionnot transferred
Allied materials area
Next Higher Units8JMKD3MGPAW/3PJT9LS
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber contenttype 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