A tracking approach for text line segmentation in handwritten documents

Simple item page
dc.contributor.authorSetitra, Insaf
dc.contributor.authorHadjadj, Zineb
dc.contributor.authorMeziane, Abdelkrim
dc.date.accessioned2016-12-25T16:52:48Z
dc.date.available2016-12-25T16:52:48Z
dc.date.issued2017-02-24
dc.description.abstractTracking of objects in videos consists of giving a label to the same object moving in different frames. This labeling is performed by predicting position of the object given its set of features observed in previous frames. In this work, we apply the same rationale by considering each connected component in the manuscript as a moving object and to track it so that to minimize the distance and angle of the connected component to its nearest neighbor. The approach was applied to images of ICDAR 2013 handwritten segmentation contest and proved to be robust against text orientation, size and writing script.fr_FR
dc.identifier.isrnCERIST- DSISM/PR—16-000000027--dzfr_FR
dc.identifier.urihttp://dl.cerist.dz/handle/CERIST/875
dc.publisherCERIST
dc.relation.ispartofRapports de recherche internes
dc.relation.placeAlger
dc.structureSystèmes d'Information et Image en Santé S2ISfr_FR
dc.subjecttrackingfr_FR
dc.subjectconnected componentsfr_FR
dc.subjectangle minimizationfr_FR
dc.subjectsegmentationfr_FR
dc.subjecthandwrittenfr_FR
dc.subjectpredictionfr_FR
dc.titleA tracking approach for text line segmentation in handwritten documentsfr_FR
dc.typeTechnical Report
Files
Collections
Research Reports