Segmentation of touching characters in printed document recognition

Deep Blue Home

Show simple item record

dc.contributor.author Liang, Su en_US
dc.contributor.author Shridhar, M. en_US
dc.contributor.author Ahmadi, M. en_US
dc.date.accessioned 2006-04-10T18:07:43Z
dc.date.available 2006-04-10T18:07:43Z
dc.date.issued 1994-06 en_US
dc.identifier.citation Liang, Su, Shridhar, M., Ahmadi, M. (1994/06)."Segmentation of touching characters in printed document recognition." Pattern Recognition 27(6): 825-840. <http://hdl.handle.net/2027.42/31557> en_US
dc.identifier.uri http://www.sciencedirect.com/science/article/B6V14-48MPPYC-205/2/24e3419952a5a766c1c0a93e9e16efca en_US
dc.identifier.uri http://hdl.handle.net/2027.42/31557
dc.description.abstract A new discrimination function is presented for segmenting touching characters based on both pixel and profile projections. A dynamic recursive segmentation algorithm is developed for effectively segmenting touching characters. Contextual information and spell checking are used to correct errors caused by incorrect recognition and segmentation. Based on 12 real documents, a maximum 99.85% and a minimum 99.4% recognition accuracy is achieved. en_US
dc.format.extent 1131760 bytes
dc.format.extent 3118 bytes
dc.format.mimetype application/pdf
dc.format.mimetype text/plain
dc.language.iso en_US
dc.publisher Elsevier en_US
dc.title Segmentation of touching characters in printed document recognition en_US
dc.type Article en_US
dc.rights.robots IndexNoFollow en_US
dc.subject.hlbsecondlevel Science (General) en_US
dc.subject.hlbsecondlevel Computer Science en_US
dc.subject.hlbtoplevel Science en_US
dc.subject.hlbtoplevel Engineering en_US
dc.description.peerreviewed Peer Reviewed en_US
dc.contributor.affiliationum Department of Electrical and Computer Engineering, University of Michigan-Dearborn, Dearborn, MI 48128, U.S.A. en_US
dc.contributor.affiliationother Department of Electrical Engineering, University of Windsor, Windsor, Ontario, Canada N9B 3P4 en_US
dc.contributor.affiliationother Department of Electrical Engineering, University of Windsor, Windsor, Ontario, Canada N9B 3P4 en_US
dc.description.bitstreamurl http://deepblue.lib.umich.edu/bitstream/2027.42/31557/1/0000484.pdf en_US
dc.identifier.doi http://dx.doi.org/10.1016/0031-3203(94)90167-8 en_US
dc.identifier.source Pattern Recognition en_US
dc.owningcollname Interdisciplinary and Peer-Reviewed
 Show simple item record

This item appears in the following Collection(s)


Search Deep Blue

Browse by

My Account

Information

Coming Soon


MLibrary logo