Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICME.2010.5582544
DC FieldValue
dc.titleAutomated assembly of shredded pieces from multiple photos
dc.contributor.authorCao, S.
dc.contributor.authorLiu, H.
dc.contributor.authorYan, S.
dc.date.accessioned2014-06-19T03:01:03Z
dc.date.available2014-06-19T03:01:03Z
dc.date.issued2010
dc.identifier.citationCao, S., Liu, H., Yan, S. (2010). Automated assembly of shredded pieces from multiple photos. 2010 IEEE International Conference on Multimedia and Expo, ICME 2010 : 358-363. ScholarBank@NUS Repository. https://doi.org/10.1109/ICME.2010.5582544
dc.identifier.isbn9781424474912
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/69467
dc.description.abstractIn this paper, we investigate the problem of automated assembly of shredded pieces from multiple photos. We first establish candidate matchings between fragments by using both shape and appearance information. A weighted graph whose vertices represent shredded pieces and edges represent candidate matchings is then constructed, and divided into separate subgraphs, with each subgraph corresponding to a desired photo. The assembly results are finally obtained by searching for a spanning tree of each subgraph. This proposed framework can deal with casesin which materials are lost and/or fragments belonging to multiple photos coexist. The experimental results on both computershredded and human-shredded photos well demonstrate the effectiveness and efficiency of our proposed framework. © 2010 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/ICME.2010.5582544
dc.sourceScopus
dc.subjectAutomated assembly
dc.subjectGraph partition
dc.subjectShredded photos
dc.subjectSpanning tree
dc.typeConference Paper
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1109/ICME.2010.5582544
dc.description.sourcetitle2010 IEEE International Conference on Multimedia and Expo, ICME 2010
dc.description.page358-363
dc.identifier.isiut000287977700063
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

20
checked on Apr 15, 2021

WEB OF SCIENCETM
Citations

15
checked on Apr 15, 2021

Page view(s)

72
checked on Apr 12, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.