Please use this identifier to cite or link to this item:
Title: Arabic handwriting recognition using baseline dependant features and hidden Markov modeling
Authors: Hajj Mohamad, Ramy Al
Likforman-Sulem, Laurence
Mokbel, Chafic 
Affiliations: Department of Electrical Engineering 
Keywords: Handwriting recognition
Hidden Markov models
Feature extraction
Visual databases
Natural languages
Subjects: Image segmentation
Issue Date: 2005
Part of: Eighth International Conference on Document Analysis and Recognition (ICDAR'05)
Start page: 1
End page: 5
Conference: International Conference on Document Analysis and Recognition (ICDAR) (8th : 31 Aug- 1 Sep 2005 : Seoul, South Korea) 
In this paper, we describe a 1D HMM offline handwriting recognition system employing an analytical approach. The system is supported by a set of robust language independent features extracted on binary images. Parameters such as lower and upper baselines are used to derive a subset of baseline dependent features. Thus, word variability due to lower and upper parts of words is better taken into account. In addition, the proposed system learns character models without character pre-segmentation. Experiments that have been conducted on the benchmark IFN/ENIT database of Tunisian handwritten country/village names, show the advantage of the proposed approach and of the baseline-dependant features.
Ezproxy URL: Link to full text
Type: Conference Paper
Appears in Collections:Department of Electrical Engineering

Show full item record

Record view(s)

checked on Jul 24, 2021

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.