Please use this identifier to cite or link to this item:
https://scholarhub.balamand.edu.lb/handle/uob/1346
Title: | The UOB-Telecom paristech arabic handwriting recognition and translation systems for the openHart 2013 competition | Authors: | Morillot , Olivier Oprean, Cristina Likforman-Sulem, Laurence Mokbel, Chafic Chammas, Edgar Grosick, Emmanuèle |
Affiliations: | Department of Electrical Engineering | Keywords: | Arabic handwriting recognition Textline recognition Preprocessing HMM BLSTM |
Subjects: | Translation | Issue Date: | 2013 | Conference: | International Conference on Document Analysis and Recognition (ICDAR) (12th : 25-28 Aug 2013 : Washington DC, United States) | Abstract: | This article is a description of the two systems proposed for the recognition of Arabic handwritten text lines and for the automatic translation of text-line and sentence images into English text. The recognition systems are based on HMMs (Hidden Markov Models) and BLSTMs (bi-directional long short term memory) recurrent networks. Two SMT (Statistical Machine Translation) systems based on MOSES [1] were built for the evaluation system: one on text-line translation and one for sentence translation. |
URI: | https://scholarhub.balamand.edu.lb/handle/uob/1346 | Open URL: | Link to full text | Type: | Conference Presentation |
Appears in Collections: | Department of Electrical Engineering |
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.