A feature extraction method for Arabic Offline Handwritten Recognition System using Naïve Bayes classifier

Ahmed Subhi Abdalkafor; Khattab M. Ali Alheeti; Laith Al-Jobouri

doi:10.1109/I3CAT53310.2021.9629408

A feature extraction method for Arabic Offline Handwritten Recognition System using Naïve Bayes classifier

Ahmed Subhi Abdalkafor, Khattab M. Ali Alheeti, Laith Al-Jobouri

Division of Games Technology and Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

59 Downloads (Pure)

Abstract

Handwriting recognition in the Arabic language is considered one of the most challenging problems and the accuracies in recognizing still need more enhancements due to the Arabic character’s nature, cursive writing, style, and size of writing in contrast to working with other languages. In this paper, we propose a system for Arabic Offline Handwritten Character Recognition based on Naïve Bayes classifier (NB). Extraction features preceded by divided the image of character into three horizontal and vertical zones and 3x3 zones in one and two dimensions respectively, then classified by Naïve Bayes. The performance of the system proposes evaluated by using the benchmark CENPARMI database reached up to 97.05% accuracy rate. Experimental results confirm a high enhancement inaccuracy rate in comparison with other Arabic Optical Character Recognition systems.

Original language	English
Title of host publication	2021 International Conference on Computing and Communications Applications and Technologies (I3CAT)
Subtitle of host publication	conference proceedings
Publisher	IEEE
Pages	82-87
Number of pages	6
ISBN (Electronic)	9781665424417
ISBN (Print)	9781665424424
DOIs	https://doi.org/10.1109/I3CAT53310.2021.9629408
Publication status	Published - 7 Dec 2021
Event	2021 International Conference on Computing and Communications Applications and Technologies - virtual conference, Ipswich, United Kingdom Duration: 15 Sep 2021 → 15 Sep 2021 https://i3cat.org/

Conference

Conference	2021 International Conference on Computing and Communications Applications and Technologies
Abbreviated title	I3CAT
Country/Territory	United Kingdom
City	Ipswich
Period	15/09/21 → 15/09/21
Internet address	https://i3cat.org/

Keywords

Arabic handwritten character
Starters and intersections
Minor-starters
Naïve Bayes classifier

Access to Document

10.1109/I3CAT53310.2021.9629408

Al-Jobouri_AFeatureExtractionMethod_Accepted_2021Accepted author manuscript, 617 KB

Cite this

Abdalkafor, A. S., Alheeti, K. M. A., & Al-Jobouri, L. (2021). A feature extraction method for Arabic Offline Handwritten Recognition System using Naïve Bayes classifier. In 2021 International Conference on Computing and Communications Applications and Technologies (I3CAT): conference proceedings (pp. 82-87). [9629408] IEEE . https://doi.org/10.1109/I3CAT53310.2021.9629408

@inproceedings{5891f8410f44453d838a0ade0600ca15,

title = "A feature extraction method for Arabic Offline Handwritten Recognition System using Na{\"i}ve Bayes classifier",

abstract = "Handwriting recognition in the Arabic language is considered one of the most challenging problems and the accuracies in recognizing still need more enhancements due to the Arabic character{\textquoteright}s nature, cursive writing, style, and size of writing in contrast to working with other languages. In this paper, we propose a system for Arabic Offline Handwritten Character Recognition based on Na{\"i}ve Bayes classifier (NB). Extraction features preceded by divided the image of character into three horizontal and vertical zones and 3x3 zones in one and two dimensions respectively, then classified by Na{\"i}ve Bayes. The performance of the system proposes evaluated by using the benchmark CENPARMI database reached up to 97.05% accuracy rate. Experimental results confirm a high enhancement inaccuracy rate in comparison with other Arabic Optical Character Recognition systems.",

author = "Abdalkafor, {Ahmed Subhi} and Alheeti, {Khattab M. Ali} and Laith Al-Jobouri",

year = "2021",

month = dec,

day = "7",

doi = "10.1109/I3CAT53310.2021.9629408",

language = "English",

isbn = "9781665424424",

pages = "82--87",

booktitle = "2021 International Conference on Computing and Communications Applications and Technologies (I3CAT)",

publisher = "IEEE ",

note = "2021 International Conference on Computing and Communications Applications and Technologies, I3CAT ; Conference date: 15-09-2021 Through 15-09-2021",

url = "https://i3cat.org/",

}

Abdalkafor, AS, Alheeti, KMA & Al-Jobouri, L 2021, A feature extraction method for Arabic Offline Handwritten Recognition System using Naïve Bayes classifier. in 2021 International Conference on Computing and Communications Applications and Technologies (I3CAT): conference proceedings., 9629408, IEEE , pp. 82-87, 2021 International Conference on Computing and Communications Applications and Technologies, Ipswich, United Kingdom, 15/09/21. https://doi.org/10.1109/I3CAT53310.2021.9629408

A feature extraction method for Arabic Offline Handwritten Recognition System using Naïve Bayes classifier. / Abdalkafor, Ahmed Subhi; Alheeti, Khattab M. Ali; Al-Jobouri, Laith.

2021 International Conference on Computing and Communications Applications and Technologies (I3CAT): conference proceedings. IEEE , 2021. p. 82-87 9629408.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A feature extraction method for Arabic Offline Handwritten Recognition System using Naïve Bayes classifier

AU - Abdalkafor, Ahmed Subhi

AU - Alheeti, Khattab M. Ali

AU - Al-Jobouri, Laith

PY - 2021/12/7

Y1 - 2021/12/7

N2 - Handwriting recognition in the Arabic language is considered one of the most challenging problems and the accuracies in recognizing still need more enhancements due to the Arabic character’s nature, cursive writing, style, and size of writing in contrast to working with other languages. In this paper, we propose a system for Arabic Offline Handwritten Character Recognition based on Naïve Bayes classifier (NB). Extraction features preceded by divided the image of character into three horizontal and vertical zones and 3x3 zones in one and two dimensions respectively, then classified by Naïve Bayes. The performance of the system proposes evaluated by using the benchmark CENPARMI database reached up to 97.05% accuracy rate. Experimental results confirm a high enhancement inaccuracy rate in comparison with other Arabic Optical Character Recognition systems.

AB - Handwriting recognition in the Arabic language is considered one of the most challenging problems and the accuracies in recognizing still need more enhancements due to the Arabic character’s nature, cursive writing, style, and size of writing in contrast to working with other languages. In this paper, we propose a system for Arabic Offline Handwritten Character Recognition based on Naïve Bayes classifier (NB). Extraction features preceded by divided the image of character into three horizontal and vertical zones and 3x3 zones in one and two dimensions respectively, then classified by Naïve Bayes. The performance of the system proposes evaluated by using the benchmark CENPARMI database reached up to 97.05% accuracy rate. Experimental results confirm a high enhancement inaccuracy rate in comparison with other Arabic Optical Character Recognition systems.

U2 - 10.1109/I3CAT53310.2021.9629408

DO - 10.1109/I3CAT53310.2021.9629408

M3 - Conference contribution

SN - 9781665424424

SP - 82

EP - 87

BT - 2021 International Conference on Computing and Communications Applications and Technologies (I3CAT)

PB - IEEE

T2 - 2021 International Conference on Computing and Communications Applications and Technologies

Y2 - 15 September 2021 through 15 September 2021

ER -

A feature extraction method for Arabic Offline Handwritten Recognition System using Naïve Bayes classifier

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this