Difference between revisions of "Publications:Offline Handwritten Amharic Word Recognition Using HMMs"
(Created page with "<div style='display: none'> == Do not edit this section == </div> {{PublicationSetupTemplate|Author=Yaregal Assabie, Josef Bigun |PID=728445 |Name=Assabie, Yaregal [yaas] (Hö...") |
|||
| Line 4: | Line 4: | ||
{{PublicationSetupTemplate|Author=Yaregal Assabie, Josef Bigun | {{PublicationSetupTemplate|Author=Yaregal Assabie, Josef Bigun | ||
|PID=728445 | |PID=728445 | ||
| − | |Name=Assabie, Yaregal | + | |Name=Assabie, Yaregal (yaas) (Högskolan i Halmstad (2804), Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) (3905), Halmstad Embedded and Intelligent Systems Research (EIS) (3938));Bigun, Josef (josef) (Högskolan i Halmstad (2804), Sektionen för Informationsvetenskap, Data– och Elektroteknik (IDE) (3905), Halmstad Embedded and Intelligent Systems Research (EIS) (3938)) |
|Title=Offline Handwritten Amharic Word Recognition Using HMMs | |Title=Offline Handwritten Amharic Word Recognition Using HMMs | ||
|PublicationType=Book Chapter | |PublicationType=Book Chapter | ||
Latest revision as of 21:38, 30 September 2016
Property "Publisher" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user. Property "Author" has a restricted application area and cannot be used as annotation property by a user.
| Title | Offline Handwritten Amharic Word Recognition Using HMMs |
|---|---|
| Author | |
| Year | 2009 |
| PublicationType | Book Chapter |
| Journal | |
| HostPublication | Proceedings SSBA '09 : Symposium on Image Analysis, Halmstad University, Halmstad, March 18-20, 2009 |
| Conference | |
| DOI | |
| Diva url | http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:728445 |
| Abstract | This paper describes two appraches 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 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 DEHR dataset of unconstrained handwritten documents collected from various sources. |
