Reference TypeConference Proceedings
Citation KeyNomaJr:2010:SpReEf
Author1 Noma, Alexandre
2 Jr, Roberto Marcondes Cesar
Affiliation1 Instituto de Matemática e Estatística - USP
2 Instituto de Matemática e Estatística - USP
TitleSparse Representations for Efficient Shape Matching
Conference NameConference on Graphics, Patterns and Images, 23 (SIBGRAPI)
EditorBellon, Olga
Esperança, Claudio
Book TitleProceedings
DateAug. 30 - Sep. 3, 2010
Publisher CityLos Alamitos
PublisherIEEE Computer Society
Conference LocationGramado
Keywordspoint pattern matching, graph matching, quadratic assignment, Markov random fields, efficient belief propagation, sparse shape representations, shape metric, 3D object recognition, handwritten digits.
AbstractGraph matching is a fundamental problem with many applications in computer vision. Patterns are represented by graphs and pattern recognition corresponds to finding a correspondence between vertices from different graphs. In many cases, the problem can be formulated as a quadratic assignment problem, where the cost function consists of two components: a linear term representing the vertex compatibility and a quadratic term encoding the edge compatibility. The quadratic assignment problem is NP-hard and the present paper extends the approximation technique based on graph matching and efficient belief propagation described in previous work by using sparse representations for efficient shape matching. Successful results of recognition of 3D objects and handwritten digits are illustrated, using COIL and MNIST datasets, respectively. .
Tertiary TypeFull Paper
FormatPrinted, On-line.
Size521 KiB
Number of Files1
Target Filepaper2.pdf
Last Update2010:
Metadata Last Update2010: {D 2010}
Document Stagecompleted
Is the master or a copy?is the master
Content TypeExternal Contribution
source Directory Contentthere are no files
agreement Directory Contentthere are no files
History2010-10-01 04:19:39 :: -> :: 2010
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition nexthigherunit 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
Access Date2020, Nov. 24