<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<holdercode>{ibi 8JMKD3MGPEW34M/46T9EHH}</holdercode>
		<identifier>8JMKD3MGPAW/3PJ6MCH</identifier>
		<repository>sid.inpe.br/sibgrapi/2017/09.05.02.31</repository>
		<lastupdate>2017:09.11.23.33.15 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2017/09.05.02.31.10</metadatarepository>
		<metadatalastupdate>2022:05.18.22.18.24 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2017}</metadatalastupdate>
		<citationkey>PereiraSant:2017:ImReLe</citationkey>
		<title>Image representation learning by color quantization optimization</title>
		<format>On-line</format>
		<year>2017</year>
		<numberoffiles>1</numberoffiles>
		<size>3513 KiB</size>
		<author>Pereira, Érico Marco Dias Alves,</author>
		<author>dos Santos, Jefersson Alex,</author>
		<affiliation>Universidade Federal de Minas Gerais</affiliation>
		<affiliation>Universidade Federal de Minas Gerais</affiliation>
		<editor>Torchelsen, Rafael Piccin,</editor>
		<editor>Nascimento, Erickson Rangel do,</editor>
		<editor>Panozzo, Daniele,</editor>
		<editor>Liu, Zicheng,</editor>
		<editor>Farias, Mylène,</editor>
		<editor>Viera, Thales,</editor>
		<editor>Sacht, Leonardo,</editor>
		<editor>Ferreira, Nivan,</editor>
		<editor>Comba, João Luiz Dihl,</editor>
		<editor>Hirata, Nina,</editor>
		<editor>Schiavon Porto, Marcelo,</editor>
		<editor>Vital, Creto,</editor>
		<editor>Pagot, Christian Azambuja,</editor>
		<editor>Petronetto, Fabiano,</editor>
		<editor>Clua, Esteban,</editor>
		<editor>Cardeal, Flávio,</editor>
		<e-mailaddress>emarco.pereira@dcc.ufmg.br</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 30 (SIBGRAPI)</conferencename>
		<conferencelocation>Niterói, RJ, Brazil</conferencelocation>
		<date>17-20 Oct. 2017</date>
		<publisher>Sociedade Brasileira de Computação</publisher>
		<publisheraddress>Porto Alegre</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Undergraduate Work</tertiarytype>
		<transferableflag>1</transferableflag>
		<keywords>representation learning, color quantization, CBIR, genetic algorithm, feature extraction.</keywords>
		<abstract>The 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.</abstract>
		<language>en</language>
		<targetfile>Pereira_DosSantos_2017.pdf</targetfile>
		<usergroup>emarco.pereira@dcc.ufmg.br</usergroup>
		<visibility>shown</visibility>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<nexthigherunit>8JMKD3MGPAW/3PKCC58</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2017/09.12.13.04 7</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2017/09.05.02.31</url>
	</metadata>
</metadatalist>