<?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>83LX3pFwXQZ4BFjAq/jhcjj</identifier>
		<repository>dpi.inpe.br/vagner/1999/11.26.16.59</repository>
		<lastupdate>2000:01.03.02.00.00 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/banon/2001/03.30.15.57.50</metadatarepository>
		<metadatalastupdate>2022:06.14.00.17.04 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 1999}</metadatalastupdate>
		<doi>10.1109/SIBGRA.1999.805717</doi>
		<citationkey>FonsecaKenn:1999:CoPoAs</citationkey>
		<title>Control point assessment for image registration</title>
		<year>1999</year>
		<numberoffiles>3</numberoffiles>
		<size>149 KiB</size>
		<author>Fonseca, L. M. G.,</author>
		<author>Kenney, C. S.,</author>
		<editor>Stolfi, Jorge,</editor>
		<editor>Tozzi, Clésio Luis,</editor>
		<conferencename>Brazilian Symposium on Computer Graphics and Image Processing, 12 (SIBGRAPI)</conferencename>
		<conferencelocation>Campinas, SP, Brazil</conferencelocation>
		<date>17-20 Oct. 1999</date>
		<publisher>IEEE Computer Society</publisher>
		<publisheraddress>Los Alamitos</publisheraddress>
		<pages>125-132</pages>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Full Paper</tertiarytype>
		<organization>SBC - Brazilian Computer Society and UNICAMP - University of Campinas</organization>
		<transferableflag>1</transferableflag>
		<versiontype>finaldraft</versiontype>
		<keywords>cpa algorithm, lloyd algorithm, image.</keywords>
		<abstract>This paper presents several extensions of the basic CPA algorithm. First we compare CPA to standard corner detection algorithms and then turn to the question of selecting control points with adequate dispersion since this is crucial for accurate registration. Two selection methods are proposed. The first consists of clustering the control points via the Lloyd algorithm followed by selecting the dominant control point in each cluster. This 'gold stantard' approach produces excellent dispersion but is costly in terms of computacional effort. The second selection method consists of subdividing the image and then selecting dominant control points in each subdivision. This is extremely fast and produces results comparable to the Lloyd selection method. The paper concludes with a discussion of how LS operator norm information can be coupled with anisotropic diffusion to produce smoothed images without corner degradation.</abstract>
		<targetfile>012-30329670.pdf</targetfile>
		<usergroup>administrator</usergroup>
		<visibility>shown</visibility>
		<nexthigherunit>8JMKD3MGPEW34M/46PDF8P</nexthigherunit>
		<nexthigherunit>8JMKD3MGPEW34M/4742MCS</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2022/04.25.03.44 7</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<notes>The conference was held in Campinas, SP, Brazil, from October 17 to 20.</notes>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/dpi.inpe.br/vagner/1999/11.26.16.59</url>
	</metadata>
</metadatalist>