<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<identifier>8JMKD3MGPBW34M/387LT3L</identifier>
		<repository>sid.inpe.br/sibgrapi/2010/09.06.13.15</repository>
		<lastupdate>2010:09.06.13.15.10 sid.inpe.br/banon/2001/03.30.15.38 crjung@inf.ufrgs.br</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2010/09.06.13.15.11</metadatarepository>
		<metadatalastupdate>2010:10.01.04.19.38 sid.inpe.br/banon/2001/03.30.15.38 crjung@inf.ufrgs.br {D 2010}</metadatalastupdate>
		<citationkey>ParolinHerzJung:2010:SeDiMe</citationkey>
		<title>Semi-Automated Diagnosis of Melanoma Through the Analysis of Dermatological Images</title>
		<format>Printed, On-line.</format>
		<year>2010</year>
		<date>Aug. 30 - Sep. 3, 2010</date>
		<numberoffiles>1</numberoffiles>
		<size>256 Kbytes</size>
		<author>Parolin, Alessandro,</author>
		<author>Herzer, Eduardo,</author>
		<author>Jung, Claudio R.,</author>
		<affiliation>Unisinos</affiliation>
		<affiliation>Unisinos</affiliation>
		<affiliation>UFRGS</affiliation>
		<editor>Bellon, Olga,</editor>
		<editor>Esperanša, Claudio,</editor>
		<e-mailaddress>crjung@inf.ufrgs.br</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 23 (SIBGRAPI)</conferencename>
		<conferencelocation>Gramado</conferencelocation>
		<booktitle>Proceedings</booktitle>
		<publisher>IEEE Computer Society</publisher>
		<publisheraddress>Los Alamitos</publisheraddress>
		<transferableflag>1</transferableflag>
		<contenttype>External Contribution</contenttype>
		<tertiarytype>Full Paper</tertiarytype>
		<keywords>image processing, medical imaging, classification, MDA-FKT.</keywords>
		<abstract>Melanoma is the deadliest kind of skin cancer, but it can be 100% cured if recognized early in advance. This paper proposes a non-invasive automated skin lesion classifier based on digitized dermatological images. In the proposed approach, the lesion is initially segmented using snakes guided by an edge map based on the Wavelet Transform (WT) computed at different resolutions. A set of features is extracted from lesion pixels, and a probabilistic classifier is used to identify melanoma lesions. The detection rate of the proposed system can be adjusted to control the tradeoff between false positives and false negatives, and experimental results indicated that a false negative rate of 1.89% can be achieved, in a total accuracy rate of 82.55%.</abstract>
		<language>en</language>
		<targetfile>sib10_dermato_camera_ready.pdf</targetfile>
		<usergroup>crjung@inf.ufrgs.br</usergroup>
		<visibility>shown</visibility>
		<mirrorrepository>dpi.inpe.br/banon-pc2@80/2006/08.30.19.27</mirrorrepository>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2010/09.06.13.15</url>
	</metadata>
</metadatalist>