Advanced stroke labelling technique based on directions features for Arabic character segmentation

Offline Character segmentation of text images is an important step in many document image analysis and recognition (DIAR) applications. However, the character segmentation of both writing styles (printed and handwritten) remains an open problem. Moreover, the manual segmentation is time-consuming an...

Full description

Bibliographic Details
Main Authors:	Abu-Ain, Tarik Abdel-Kareem, Siti Norul Huda Sheikh Abdullah, Khairuddin Omar, Siti Zaharah Abd Rahman
Format:	Article
Language:	English
Published:	Penerbit Universiti Kebangsaan Malaysia 2019
Online Access:	http://journalarticle.ukm.my/14154/ http://journalarticle.ukm.my/14154/ http://journalarticle.ukm.my/14154/1/26483-111116-1-PB.pdf

id	ukm-14154
recordtype	eprints
spelling	ukm-141542020-02-07T11:10:28Z http://journalarticle.ukm.my/14154/ Advanced stroke labelling technique based on directions features for Arabic character segmentation Abu-Ain, Tarik Abdel-Kareem Siti Norul Huda Sheikh Abdullah, Khairuddin Omar, Siti Zaharah Abd Rahman, Offline Character segmentation of text images is an important step in many document image analysis and recognition (DIAR) applications. However, the character segmentation of both writing styles (printed and handwritten) remains an open problem. Moreover, the manual segmentation is time-consuming and impractical for large numbers of documents. Based on the unconstraint-cursive handwritten perspective, the auto character segmentation is more challenging and complex. The Arabic script writing style suffers from many common problems, such as sub-words overlapping, characters overlapping, and missed characters. These challenging issues have attracted the attention of researchers in the field of DIAR for Arabic character segmentation. The proposed method combines a new advanced Stroke Labelling based on Direction Features (SLDF2) technique and a modified vertical projection histogram (MVPH) technique. This technique extracts the relationship between each text stroke pixel and its 8 neighboring foreground pixels and labels it with the proper value before identify the possible segmentation points. The text preparation for the segmentation process was achieved using multiple preprocessing steps and developing an advanced stroke labelling technique based on direction features. Several Arabic language structural-rules were made to detect the candidate segmentation points (CSP), detect many character overlapping cases, solve the missed characters problem that appears as a result of using the text skeleton in VPH, and validate the CSP. All techniques and methods are tested on the ACDAR benchmark database. The validation method used to measure segmentation accuracy was a quantitative analysis that includes Recall, Precision, and F-measurement tests. The average accuracy of the proposed segmentation method was 92.44%, which outperforms the state-of-the-art method. Penerbit Universiti Kebangsaan Malaysia 2019-06 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/14154/1/26483-111116-1-PB.pdf Abu-Ain, Tarik Abdel-Kareem and Siti Norul Huda Sheikh Abdullah, and Khairuddin Omar, and Siti Zaharah Abd Rahman, (2019) Advanced stroke labelling technique based on directions features for Arabic character segmentation. Asia-Pacific Journal of Information Technology and Multimedia, 8 (1). pp. 97-127. ISSN 2289-2192 http://ejournals.ukm.my/apjitm/issue/view/1179
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Kebangasaan Malaysia
building	UKM Institutional Repository
collection	Online Access
language	English
description	Offline Character segmentation of text images is an important step in many document image analysis and recognition (DIAR) applications. However, the character segmentation of both writing styles (printed and handwritten) remains an open problem. Moreover, the manual segmentation is time-consuming and impractical for large numbers of documents. Based on the unconstraint-cursive handwritten perspective, the auto character segmentation is more challenging and complex. The Arabic script writing style suffers from many common problems, such as sub-words overlapping, characters overlapping, and missed characters. These challenging issues have attracted the attention of researchers in the field of DIAR for Arabic character segmentation. The proposed method combines a new advanced Stroke Labelling based on Direction Features (SLDF2) technique and a modified vertical projection histogram (MVPH) technique. This technique extracts the relationship between each text stroke pixel and its 8 neighboring foreground pixels and labels it with the proper value before identify the possible segmentation points. The text preparation for the segmentation process was achieved using multiple preprocessing steps and developing an advanced stroke labelling technique based on direction features. Several Arabic language structural-rules were made to detect the candidate segmentation points (CSP), detect many character overlapping cases, solve the missed characters problem that appears as a result of using the text skeleton in VPH, and validate the CSP. All techniques and methods are tested on the ACDAR benchmark database. The validation method used to measure segmentation accuracy was a quantitative analysis that includes Recall, Precision, and F-measurement tests. The average accuracy of the proposed segmentation method was 92.44%, which outperforms the state-of-the-art method.
format	Article
author	Abu-Ain, Tarik Abdel-Kareem Siti Norul Huda Sheikh Abdullah, Khairuddin Omar, Siti Zaharah Abd Rahman,
spellingShingle	Abu-Ain, Tarik Abdel-Kareem Siti Norul Huda Sheikh Abdullah, Khairuddin Omar, Siti Zaharah Abd Rahman, Advanced stroke labelling technique based on directions features for Arabic character segmentation
author_facet	Abu-Ain, Tarik Abdel-Kareem Siti Norul Huda Sheikh Abdullah, Khairuddin Omar, Siti Zaharah Abd Rahman,
author_sort	Abu-Ain, Tarik Abdel-Kareem
title	Advanced stroke labelling technique based on directions features for Arabic character segmentation
title_short	Advanced stroke labelling technique based on directions features for Arabic character segmentation
title_full	Advanced stroke labelling technique based on directions features for Arabic character segmentation
title_fullStr	Advanced stroke labelling technique based on directions features for Arabic character segmentation
title_full_unstemmed	Advanced stroke labelling technique based on directions features for Arabic character segmentation
title_sort	advanced stroke labelling technique based on directions features for arabic character segmentation
publisher	Penerbit Universiti Kebangsaan Malaysia
publishDate	2019
url	http://journalarticle.ukm.my/14154/ http://journalarticle.ukm.my/14154/ http://journalarticle.ukm.my/14154/1/26483-111116-1-PB.pdf
first_indexed	2023-09-18T20:06:28Z
last_indexed	2023-09-18T20:06:28Z
_version_	1777407191282614272

Advanced stroke labelling technique based on directions features for Arabic character segmentation

Similar Items