Show simple item record

dc.contributor.authorXu, Jiamin
dc.contributor.authorShivakumara, Palaiahnakote
dc.contributor.authorLu, Tong
dc.contributor.authorTan, Chew Lim
dc.contributor.authorBlumenstein, Michael
dc.date.accessioned2018-03-16T01:52:19Z
dc.date.available2018-03-16T01:52:19Z
dc.date.issued2015
dc.identifier.doi10.1109/ACPR.2015.7486591
dc.identifier.urihttp://hdl.handle.net/10072/123854
dc.description.abstractThere is a need for effective web-document understanding due to the explosive progress of internet and network technologies. In this paper, we propose a new method for text detection in born-digital images by introducing a mass estimation concept. We propose to explore super-pixel information of different color channels to identify text atoms in images. The proposed method uses similarity graphs and spectral clustering to identify candidate text regions. We propose a new idea of mapping Gabor responses of a candidate text region to a spatial circle to study the spatial coherency of pixels. We introduce a mass estimation concept to identify text candidates from the pixel distribution in a spatial circle. The linear linkage graphs help in grouping text candidates to obtain full text lines. The same Gabor responses are used as features to eliminate false positives with an SVM classifier. We evaluate the proposed method for the testing on standard datasets, such as ICDAR 2013 (challenge-1) and the Situ et al. dataset. Experimental results on both the datasets show that the proposed method outperforms the existing methods.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.publisher.placeUnited States
dc.relation.ispartofconferencenameACPR 2015
dc.relation.ispartofconferencetitleProceedings of the 2015 Third IAPR Asian Conference on Pattern Recognition
dc.relation.ispartofdatefrom2015-11-03
dc.relation.ispartofdateto2015-11-06
dc.relation.ispartoflocationKuala Lumpur, Malaysia
dc.subject.fieldofresearchOther information and computing sciences not elsewhere classified
dc.subject.fieldofresearchcode469999
dc.titleText Detection in Born-Digital Images by Mass Estimation
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
gro.hasfulltextNo Full Text
gro.griffith.authorBlumenstein, Michael M.


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record