Handwritten Arabic Documents Segmentation into Text Lines using Seam Carving
Inspired from human perception and common text documents characteristics based on readability constraints, an Arabic text line segmentation approach is proposed using seam carving. Taking the gray scale of the image as input data, this technique offers better results at extracting handwritten text l...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universidad Internacional de La Rioja (UNIR)
2019-06-01
|
Series: | International Journal of Interactive Multimedia and Artificial Intelligence |
Subjects: | |
Online Access: | http://www.ijimai.org/journal/node/2420 |
id |
doaj-73aae31608904e7590072c533c04f9f0 |
---|---|
record_format |
Article |
spelling |
doaj-73aae31608904e7590072c533c04f9f02020-11-24T21:55:11ZengUniversidad Internacional de La Rioja (UNIR)International Journal of Interactive Multimedia and Artificial Intelligence1989-16601989-16602019-06-0155899610.9781/ijimai.2018.06.002ijimai.2018.06.002Handwritten Arabic Documents Segmentation into Text Lines using Seam CarvingM. DaldaliAbdelghani SouharInspired from human perception and common text documents characteristics based on readability constraints, an Arabic text line segmentation approach is proposed using seam carving. Taking the gray scale of the image as input data, this technique offers better results at extracting handwritten text lines without the need for the binary representation of the document image. In addition to its fast processing time, its versatility permits to process a multitude of document types, especially documents presenting low text-to-background contrast such as degraded historical manuscripts or complex writing styles like cursive handwriting. Even if our focus in this paper was on Arabic text segmentation, this method is language independent. Tests on a public database of 123 handwritten Arabic documents showed a line detection rate of 97.5% for a matching score of 90%.http://www.ijimai.org/journal/node/2420Arabic DocumentsHandwritten Character RecognitionProjection ProfileSeam CarvingText Line Segmentation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
M. Daldali Abdelghani Souhar |
spellingShingle |
M. Daldali Abdelghani Souhar Handwritten Arabic Documents Segmentation into Text Lines using Seam Carving International Journal of Interactive Multimedia and Artificial Intelligence Arabic Documents Handwritten Character Recognition Projection Profile Seam Carving Text Line Segmentation |
author_facet |
M. Daldali Abdelghani Souhar |
author_sort |
M. Daldali |
title |
Handwritten Arabic Documents Segmentation into Text Lines using Seam Carving |
title_short |
Handwritten Arabic Documents Segmentation into Text Lines using Seam Carving |
title_full |
Handwritten Arabic Documents Segmentation into Text Lines using Seam Carving |
title_fullStr |
Handwritten Arabic Documents Segmentation into Text Lines using Seam Carving |
title_full_unstemmed |
Handwritten Arabic Documents Segmentation into Text Lines using Seam Carving |
title_sort |
handwritten arabic documents segmentation into text lines using seam carving |
publisher |
Universidad Internacional de La Rioja (UNIR) |
series |
International Journal of Interactive Multimedia and Artificial Intelligence |
issn |
1989-1660 1989-1660 |
publishDate |
2019-06-01 |
description |
Inspired from human perception and common text documents characteristics based on readability constraints, an Arabic text line segmentation approach is proposed using seam carving. Taking the gray scale of the image as input data, this technique offers better results at extracting handwritten text lines without the need for the binary representation of the document image. In addition to its fast processing time, its versatility permits to process a multitude of document types, especially documents presenting low text-to-background contrast such as degraded historical manuscripts or complex writing styles like cursive handwriting. Even if our focus in this paper was on Arabic text segmentation, this method is language independent. Tests on a public database of 123 handwritten Arabic documents showed a line detection rate of 97.5% for a matching score of 90%. |
topic |
Arabic Documents Handwritten Character Recognition Projection Profile Seam Carving Text Line Segmentation |
url |
http://www.ijimai.org/journal/node/2420 |
work_keys_str_mv |
AT mdaldali handwrittenarabicdocumentssegmentationintotextlinesusingseamcarving AT abdelghanisouhar handwrittenarabicdocumentssegmentationintotextlinesusingseamcarving |
_version_ |
1725864225483522048 |