Recognition of cursive Arabic handwritten text using embedded training based on HMMs

In this paper we present a system for offline recognition cursive Arabic handwritten text based on Hidden Markov Models (HMMs). The system is analytical without explicit segmentation used embedded training to perform and enhance the character models. Extraction features preceded by baseline estimati...

Full description

Bibliographic Details
Main Authors: Rabi Mouhcine, Amrouch Mustapha, Mahani Zouhir
Format: Article
Language:English
Published: SpringerOpen 2018-09-01
Series:Journal of Electrical Systems and Information Technology
Online Access:http://www.sciencedirect.com/science/article/pii/S2314717217300156
_version_ 1819295127549509632
author Rabi Mouhcine
Amrouch Mustapha
Mahani Zouhir
author_facet Rabi Mouhcine
Amrouch Mustapha
Mahani Zouhir
author_sort Rabi Mouhcine
collection DOAJ
description In this paper we present a system for offline recognition cursive Arabic handwritten text based on Hidden Markov Models (HMMs). The system is analytical without explicit segmentation used embedded training to perform and enhance the character models. Extraction features preceded by baseline estimation are statistical and geometric to integrate both the peculiarities of the text and the pixel distribution characteristics in the word image. These features are modelled using hidden Markov models and trained by embedded training. The experiments on images of the benchmark IFN/ENIT database show that the proposed system improves recognition. Keywords: Recognition, Handwriting, Arabic text, HMMs, Embedded training
first_indexed 2024-12-24T04:37:17Z
format Article
id doaj.art-dd727baf651746298e00f2d53c0ae4ca
institution Directory Open Access Journal
issn 2314-7172
language English
last_indexed 2024-12-24T04:37:17Z
publishDate 2018-09-01
publisher SpringerOpen
record_format Article
series Journal of Electrical Systems and Information Technology
spelling doaj.art-dd727baf651746298e00f2d53c0ae4ca2022-12-21T17:15:05ZengSpringerOpenJournal of Electrical Systems and Information Technology2314-71722018-09-0152245251Recognition of cursive Arabic handwritten text using embedded training based on HMMsRabi Mouhcine0Amrouch Mustapha1Mahani Zouhir2Laboratory IRF-SIC, Faculty of Sciences, Ibn Zohr University, Agadir, Morocco; Corresponding author.Laboratory IRF-SIC, Faculty of Sciences, Ibn Zohr University, Agadir, MoroccoHight School of Technology, Ibn Zohr University, Agadir, MoroccoIn this paper we present a system for offline recognition cursive Arabic handwritten text based on Hidden Markov Models (HMMs). The system is analytical without explicit segmentation used embedded training to perform and enhance the character models. Extraction features preceded by baseline estimation are statistical and geometric to integrate both the peculiarities of the text and the pixel distribution characteristics in the word image. These features are modelled using hidden Markov models and trained by embedded training. The experiments on images of the benchmark IFN/ENIT database show that the proposed system improves recognition. Keywords: Recognition, Handwriting, Arabic text, HMMs, Embedded traininghttp://www.sciencedirect.com/science/article/pii/S2314717217300156
spellingShingle Rabi Mouhcine
Amrouch Mustapha
Mahani Zouhir
Recognition of cursive Arabic handwritten text using embedded training based on HMMs
Journal of Electrical Systems and Information Technology
title Recognition of cursive Arabic handwritten text using embedded training based on HMMs
title_full Recognition of cursive Arabic handwritten text using embedded training based on HMMs
title_fullStr Recognition of cursive Arabic handwritten text using embedded training based on HMMs
title_full_unstemmed Recognition of cursive Arabic handwritten text using embedded training based on HMMs
title_short Recognition of cursive Arabic handwritten text using embedded training based on HMMs
title_sort recognition of cursive arabic handwritten text using embedded training based on hmms
url http://www.sciencedirect.com/science/article/pii/S2314717217300156
work_keys_str_mv AT rabimouhcine recognitionofcursivearabichandwrittentextusingembeddedtrainingbasedonhmms
AT amrouchmustapha recognitionofcursivearabichandwrittentextusingembeddedtrainingbasedonhmms
AT mahanizouhir recognitionofcursivearabichandwrittentextusingembeddedtrainingbasedonhmms