Cargando…
ASM Based Synthesis of Handwritten Arabic Text Pages
Document analysis tasks, as text recognition, word spotting, or segmentation, are highly dependent on comprehensive and suitable databases for training and validation. However their generation is expensive in sense of labor and time. As a matter of fact, there is a lack of such databases, which comp...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi Publishing Corporation
2015
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4534626/ https://www.ncbi.nlm.nih.gov/pubmed/26295059 http://dx.doi.org/10.1155/2015/323575 |
_version_ | 1782385484485361664 |
---|---|
author | Dinges, Laslo Al-Hamadi, Ayoub Elzobi, Moftah El-etriby, Sherif Ghoneim, Ahmed |
author_facet | Dinges, Laslo Al-Hamadi, Ayoub Elzobi, Moftah El-etriby, Sherif Ghoneim, Ahmed |
author_sort | Dinges, Laslo |
collection | PubMed |
description | Document analysis tasks, as text recognition, word spotting, or segmentation, are highly dependent on comprehensive and suitable databases for training and validation. However their generation is expensive in sense of labor and time. As a matter of fact, there is a lack of such databases, which complicates research and development. This is especially true for the case of Arabic handwriting recognition, that involves different preprocessing, segmentation, and recognition methods, which have individual demands on samples and ground truth. To bypass this problem, we present an efficient system that automatically turns Arabic Unicode text into synthetic images of handwritten documents and detailed ground truth. Active Shape Models (ASMs) based on 28046 online samples were used for character synthesis and statistical properties were extracted from the IESK-arDB database to simulate baselines and word slant or skew. In the synthesis step ASM based representations are composed to words and text pages, smoothed by B-Spline interpolation and rendered considering writing speed and pen characteristics. Finally, we use the synthetic data to validate a segmentation method. An experimental comparison with the IESK-arDB database encourages to train and test document analysis related methods on synthetic samples, whenever no sufficient natural ground truthed data is available. |
format | Online Article Text |
id | pubmed-4534626 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2015 |
publisher | Hindawi Publishing Corporation |
record_format | MEDLINE/PubMed |
spelling | pubmed-45346262015-08-20 ASM Based Synthesis of Handwritten Arabic Text Pages Dinges, Laslo Al-Hamadi, Ayoub Elzobi, Moftah El-etriby, Sherif Ghoneim, Ahmed ScientificWorldJournal Research Article Document analysis tasks, as text recognition, word spotting, or segmentation, are highly dependent on comprehensive and suitable databases for training and validation. However their generation is expensive in sense of labor and time. As a matter of fact, there is a lack of such databases, which complicates research and development. This is especially true for the case of Arabic handwriting recognition, that involves different preprocessing, segmentation, and recognition methods, which have individual demands on samples and ground truth. To bypass this problem, we present an efficient system that automatically turns Arabic Unicode text into synthetic images of handwritten documents and detailed ground truth. Active Shape Models (ASMs) based on 28046 online samples were used for character synthesis and statistical properties were extracted from the IESK-arDB database to simulate baselines and word slant or skew. In the synthesis step ASM based representations are composed to words and text pages, smoothed by B-Spline interpolation and rendered considering writing speed and pen characteristics. Finally, we use the synthetic data to validate a segmentation method. An experimental comparison with the IESK-arDB database encourages to train and test document analysis related methods on synthetic samples, whenever no sufficient natural ground truthed data is available. Hindawi Publishing Corporation 2015 2015-07-30 /pmc/articles/PMC4534626/ /pubmed/26295059 http://dx.doi.org/10.1155/2015/323575 Text en Copyright © 2015 Laslo Dinges et al. https://creativecommons.org/licenses/by/3.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Dinges, Laslo Al-Hamadi, Ayoub Elzobi, Moftah El-etriby, Sherif Ghoneim, Ahmed ASM Based Synthesis of Handwritten Arabic Text Pages |
title | ASM Based Synthesis of Handwritten Arabic Text Pages |
title_full | ASM Based Synthesis of Handwritten Arabic Text Pages |
title_fullStr | ASM Based Synthesis of Handwritten Arabic Text Pages |
title_full_unstemmed | ASM Based Synthesis of Handwritten Arabic Text Pages |
title_short | ASM Based Synthesis of Handwritten Arabic Text Pages |
title_sort | asm based synthesis of handwritten arabic text pages |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4534626/ https://www.ncbi.nlm.nih.gov/pubmed/26295059 http://dx.doi.org/10.1155/2015/323575 |
work_keys_str_mv | AT dingeslaslo asmbasedsynthesisofhandwrittenarabictextpages AT alhamadiayoub asmbasedsynthesisofhandwrittenarabictextpages AT elzobimoftah asmbasedsynthesisofhandwrittenarabictextpages AT eletribysherif asmbasedsynthesisofhandwrittenarabictextpages AT ghoneimahmed asmbasedsynthesisofhandwrittenarabictextpages |