Cover Image

C-SAR: Class-Specific and Adaptive Recognition for Arabic Handwritten Cheques

We propose C-SAR, a Class-specific and Adaptive Recognition algorithm for Arabic handwritten Cheques. Existing methods suffer from low accuracy due to the complex structure of Arabic script and high-dimensional datasets. In this paper, we present an adaptive algorithm that implements a class-specifi...

Full description

Saved in:
Bibliographic Details
Main Authors: Hamdi, Ali, Al-Nuzaili, Qais, Ghaleb, Fuad A., Shaban, Khaled
Format: Conference or Workshop Item
Published: 2022
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://eprints.utm.my/id/eprint/100310/
http://dx.doi.org/10.1007/978-3-030-98741-1_17
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.100310
record_format eprints
spelling my.utm.1003102023-03-29T07:47:35Z http://eprints.utm.my/id/eprint/100310/ C-SAR: Class-Specific and Adaptive Recognition for Arabic Handwritten Cheques Hamdi, Ali Al-Nuzaili, Qais Ghaleb, Fuad A. Shaban, Khaled QA75 Electronic computers. Computer science We propose C-SAR, a Class-specific and Adaptive Recognition algorithm for Arabic handwritten Cheques. Existing methods suffer from low accuracy due to the complex structure of Arabic script and high-dimensional datasets. In this paper, we present an adaptive algorithm that implements a class-specific classification to address these challenging issues. C-SAR trains a set of class-specific machine learning models of Support Vector Machines and Artificial Neural Networks features extracted using angular pixel distribution approach. Furthermore, we propose a class-specific taxonomy of Arabic cheque handwritten words. The proposed taxonomy divides the Arabic words into groups over three layers based on their structural characteristics. Accordingly, C-SAR performs classification on three phases, i.e., 1) similar and non-similar structures, for binary classification, 2) classes with similar structures into another two categories, and 3) class-specific models to recognize the Arabic word from the given image. We introduce benchmark experimental results of our method against previous methods on the Arabic Handwriting Database for Text Recognition. Our method outperforms the baseline methods with at least 5% accuracy having 90% average classification accuracy. 2022 Conference or Workshop Item PeerReviewed Hamdi, Ali and Al-Nuzaili, Qais and Ghaleb, Fuad A. and Shaban, Khaled (2022) C-SAR: Class-Specific and Adaptive Recognition for Arabic Handwritten Cheques. In: 6th International Conference of Reliable Information and Communication Technology 2021 (IRICT 2021), 22 - 23 December 2021, Virtual, Online. http://dx.doi.org/10.1007/978-3-030-98741-1_17
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Hamdi, Ali
Al-Nuzaili, Qais
Ghaleb, Fuad A.
Shaban, Khaled
C-SAR: Class-Specific and Adaptive Recognition for Arabic Handwritten Cheques
description We propose C-SAR, a Class-specific and Adaptive Recognition algorithm for Arabic handwritten Cheques. Existing methods suffer from low accuracy due to the complex structure of Arabic script and high-dimensional datasets. In this paper, we present an adaptive algorithm that implements a class-specific classification to address these challenging issues. C-SAR trains a set of class-specific machine learning models of Support Vector Machines and Artificial Neural Networks features extracted using angular pixel distribution approach. Furthermore, we propose a class-specific taxonomy of Arabic cheque handwritten words. The proposed taxonomy divides the Arabic words into groups over three layers based on their structural characteristics. Accordingly, C-SAR performs classification on three phases, i.e., 1) similar and non-similar structures, for binary classification, 2) classes with similar structures into another two categories, and 3) class-specific models to recognize the Arabic word from the given image. We introduce benchmark experimental results of our method against previous methods on the Arabic Handwriting Database for Text Recognition. Our method outperforms the baseline methods with at least 5% accuracy having 90% average classification accuracy.
format Conference or Workshop Item
author Hamdi, Ali
Al-Nuzaili, Qais
Ghaleb, Fuad A.
Shaban, Khaled
author_facet Hamdi, Ali
Al-Nuzaili, Qais
Ghaleb, Fuad A.
Shaban, Khaled
author_sort Hamdi, Ali
title C-SAR: Class-Specific and Adaptive Recognition for Arabic Handwritten Cheques
title_short C-SAR: Class-Specific and Adaptive Recognition for Arabic Handwritten Cheques
title_full C-SAR: Class-Specific and Adaptive Recognition for Arabic Handwritten Cheques
title_fullStr C-SAR: Class-Specific and Adaptive Recognition for Arabic Handwritten Cheques
title_full_unstemmed C-SAR: Class-Specific and Adaptive Recognition for Arabic Handwritten Cheques
title_sort c-sar: class-specific and adaptive recognition for arabic handwritten cheques
publishDate 2022
url http://eprints.utm.my/id/eprint/100310/
http://dx.doi.org/10.1007/978-3-030-98741-1_17
_version_ 1762392188514205696
score 13.222552

Similar Items