Please use this identifier to cite or link to this item:
https://scholarhub.balamand.edu.lb/handle/uob/380
Title: | The A2iA-telecom paristech-UOB system for the ICDAR 2009 handwriting recognition competition | Authors: | Kermorvant, Christopher Menasri, Fares Bianne-Bernard, Anne-Laure Hajj Mohamad, Ramy Al Mokbel, Chafic Likforman-Sulem, Laurence |
Affiliations: | Department of Electrical Engineering | Keywords: | Hidden Markov models Artificial Neural Network (ANN) Handwriting recognition Feature extraction Context modeling |
Subjects: | Training Databases |
Issue Date: | 2011 | Publisher: | IEEE | Part of: | 2010 12th International Conference on Frontiers in Handwriting Recognition | Start page: | 247 | End page: | 252 | Conference: | International Conference on Frontiers in Handwriting Recognition (12th : 16-18 Nov 2010 : Kolkata, India) | Abstract: | This article describes the isolated word recognizer presented by the authors to the ICDAR 2009 French handwriting recognition competition. The system is a combination of three isolated word recognizers based on different features and models. A novel n-best combination method is proposed and compared to standard combination methods. New results on the ICDAR 2009 test database are reported. |
URI: | https://scholarhub.balamand.edu.lb/handle/uob/380 | Ezproxy URL: | Link to full text | Type: | Conference Paper |
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.