Please use this identifier to cite or link to this item: https://hdl.handle.net/1959.11/19179
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChatbri, Houssemen
dc.contributor.authorKameyama, Keisukeen
dc.contributor.authorKwan, Paul Hen
dc.date.accessioned2016-06-21T16:57:00Z-
dc.date.issued2015-
dc.identifier.citationProceedings of the Third IAPR Asian Conference on Pattern Recognition (ACPR 2015), p. 146-150en
dc.identifier.isbn9781479961009en
dc.identifier.urihttps://hdl.handle.net/1959.11/19179-
dc.description.abstractWe introduce a method for content-based document image retrieval (CBDIR) of handwritten queries that is both segmentation and recognition-free. We first demonstrate that our method is underpinned by a theoretical model that exploits the Bayes' rule. Next, we present an algorithmic implementation that takes into account real world retrieval challenges caused by handwriting fluctuations and style variations. Our algorithm operates as follows: First, a number of connected components of the query are matched against the connected components of the document image using shape features. A similarity threshold is used to select the connected components of the document image that are most similar to the query components. Then, the selected components are used to detect candidate occurrences of the query in the document image by using size-adaptive bounding boxes. Finally, a score is calculated for each candidate occurrence and used for ranking. We conduct a comparative evaluation of our method on a dataset of 200 printed document images, by executing 40 printed and 200 handwritten queries of mathematical expressions. Experimental results demonstrate competitive performances expressed by P-Recall = 100%, A-Recall = 99.95% for printed queries, and P-Recall = 73.5%, A-Recall = 57.92% for handwritten queries, outperforming a state-of-the-art CBDIR algorithm.en
dc.languageenen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.ispartofProceedings of the Third IAPR Asian Conference on Pattern Recognition (ACPR 2015)en
dc.titleTowards a segmentation and recognition-free approach for content-based document image retrieval of handwritten queriesen
dc.typeConference Publicationen
dc.relation.conferenceACPR 2015: 3rd Asian Conference on Pattern Recognitionen
dc.identifier.doi10.1109/ACPR.2015.7486483en
dc.subject.keywordsPattern Recognition and Data Miningen
dc.subject.keywordsComputer Visionen
dc.subject.keywordsImage Processingen
local.contributor.firstnameHoussemen
local.contributor.firstnameKeisukeen
local.contributor.firstnamePaul Hen
local.subject.for2008080106 Image Processingen
local.subject.for2008080109 Pattern Recognition and Data Miningen
local.subject.for2008080104 Computer Visionen
local.subject.seo2008890404 Publishing and Print Services (incl. Internet Publishing)en
local.subject.seo2008970108 Expanding Knowledge in the Information and Computing Sciencesen
local.subject.seo2008890201 Application Software Packages (excl. Computer Games)en
local.profile.schoolSchool of Science and Technologyen
local.profile.emailwkwan2@une.edu.auen
local.output.categoryE1en
local.record.placeauen
local.record.institutionUniversity of New Englanden
local.identifier.epublicationsrecordune-20151118-09137en
local.date.conference3rd - 6th November, 2015en
local.conference.placeKuala Lumpur, Malaysiaen
local.publisher.placeLos Alamitos, United States of Americaen
local.format.startpage146en
local.format.endpage150en
local.peerreviewedYesen
local.contributor.lastnameChatbrien
local.contributor.lastnameKameyamaen
local.contributor.lastnameKwanen
dc.identifier.staffune-id:wkwan2en
local.profile.roleauthoren
local.profile.roleauthoren
local.profile.roleauthoren
local.identifier.unepublicationidune:19375en
dc.identifier.academiclevelAcademicen
local.title.maintitleTowards a segmentation and recognition-free approach for content-based document image retrieval of handwritten queriesen
local.output.categorydescriptionE1 Refereed Scholarly Conference Publicationen
local.conference.detailsACPR 2015: 3rd Asian Conference on Pattern Recognition, Kuala Lumpur, Malaysia, 3rd - 6th November, 2015en
local.search.authorChatbri, Houssemen
local.search.authorKameyama, Keisukeen
local.search.authorKwan, Paul Hen
local.uneassociationUnknownen
local.year.published2015en
local.subject.for2020460306 Image processingen
local.subject.for2020461199 Machine learning not elsewhere classifieden
local.subject.for2020460301 Active sensingen
local.subject.seo2020220503 Publishing and print servicesen
local.subject.seo2020280115 Expanding knowledge in the information and computing sciencesen
local.subject.seo2020220401 Application software packagesen
local.date.start2015-11-03-
local.date.end2015-11-06-
Appears in Collections:Conference Publication
Files in This Item:
3 files
File Description SizeFormat 
Show simple item record

SCOPUSTM   
Citations

7
checked on Mar 23, 2024

Page view(s)

1,344
checked on Mar 24, 2024
Google Media

Google ScholarTM

Check

Altmetric


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