Difference between revisions of "Publications:Offline handwritten Amharic word recognition"
From ISLAB/CAISR
(Created page with "<div style='display: none'> == Do not edit this section == </div> {{PublicationSetupTemplate|Author=Yaregal Assabie, Josef Bigun |PID=408370 |Name=Assabie, Yaregal (Department...") |
|||
| Line 4: | Line 4: | ||
{{PublicationSetupTemplate|Author=Yaregal Assabie, Josef Bigun | {{PublicationSetupTemplate|Author=Yaregal Assabie, Josef Bigun | ||
|PID=408370 | |PID=408370 | ||
| − | |Name=Assabie, Yaregal (Department of Computer Science, Addis Ababa University, Ethiopia);Bigun, Josef | + | |Name=Assabie, Yaregal (yaas) (Department of Computer Science, Addis Ababa University, Ethiopia);Bigun, Josef (josef) (Högskolan i Halmstad (2804), Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) (3905), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), Laboratoriet för intelligenta system (6703)) |
|Title=Offline handwritten Amharic word recognition | |Title=Offline handwritten Amharic word recognition | ||
|PublicationType=Journal Paper | |PublicationType=Journal Paper | ||
| Line 28: | Line 28: | ||
|Urls= | |Urls= | ||
|ISRN= | |ISRN= | ||
| − | |DOI=http://dx.doi.org/ | + | |DOI=http://dx.doi.org/10.1016/j.patrec.2011.02.007 |
|ISI=000290745100002 | |ISI=000290745100002 | ||
|PMID= | |PMID= | ||
| Line 40: | Line 40: | ||
|Projects= | |Projects= | ||
|Notes= | |Notes= | ||
| − | |Abstract=<p>This paper describes two approaches for Amharic word recognition in unconstrained handwritten text using HMMs. The first approach builds word models from concatenated features of constituent characters and in the second method HMMs of constituent characters are concatenated to form word model. In both cases, the features used for training and recognition are a set of primitive strokes and their spatial relationships. The recognition system does not require segmentation of characters but requires text line detection and extraction of structural features, which is done by making use of direction field tensor. The performance of the recognition system is tested by a dataset of unconstrained handwritten documents collected from various sources, and promising results are obtained.</p> | + | |Abstract=<p>This paper describes two approaches for Amharic word recognition in unconstrained handwritten text using HMMs. The first approach builds word models from concatenated features of constituent characters and in the second method HMMs of constituent characters are concatenated to form word model. In both cases, the features used for training and recognition are a set of primitive strokes and their spatial relationships. The recognition system does not require segmentation of characters but requires text line detection and extraction of structural features, which is done by making use of direction field tensor. The performance of the recognition system is tested by a dataset of unconstrained handwritten documents collected from various sources, and promising results are obtained. (C) 2011 Elsevier B.V. All rights reserved.</p> |
|Opponents= | |Opponents= | ||
|Supervisors= | |Supervisors= | ||
| Line 55: | Line 55: | ||
|CreatedDate=2011-04-04 | |CreatedDate=2011-04-04 | ||
|PublicationDate=2011-04-04 | |PublicationDate=2011-04-04 | ||
| − | |LastUpdated= | + | |LastUpdated=2014-06-24 |
|diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:408370}} | |diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:408370}} | ||
<div style='display: none'> | <div style='display: none'> | ||
Latest revision as of 21:41, 30 September 2016
| Title | Offline handwritten Amharic word recognition |
|---|---|
| Author | Yaregal Assabie and Josef Bigun |
| Year | 2011 |
| PublicationType | Journal Paper |
| Journal | Pattern Recognition Letters |
| HostPublication | |
| Conference | |
| DOI | http://dx.doi.org/10.1016/j.patrec.2011.02.007 |
| Diva url | http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:408370 |
| Abstract | This paper describes two approaches for Amharic word recognition in unconstrained handwritten text using HMMs. The first approach builds word models from concatenated features of constituent characters and in the second method HMMs of constituent characters are concatenated to form word model. In both cases, the features used for training and recognition are a set of primitive strokes and their spatial relationships. The recognition system does not require segmentation of characters but requires text line detection and extraction of structural features, which is done by making use of direction field tensor. The performance of the recognition system is tested by a dataset of unconstrained handwritten documents collected from various sources, and promising results are obtained. (C) 2011 Elsevier B.V. All rights reserved. |
