Threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition

Arabic and English handwritten digit recognition is a challenging problem because the writing style differs from one writer to another. In middle east countries, many official forms are prepared to be written using either Arabic or English languages. However, some people fill the form using both...

Full description

Saved in:

Bibliographic Details
Main Author:	Saleh Al-Wajih, Ebrahim Qasem
Format:	Thesis
Language:	English English English
Published:	2022
Subjects:	QA76 Computer software
Online Access:	http://eprints.uthm.edu.my/8412/1/24p%20EBRAHIM%20QASEM%20SALEH%20AL-WAJIH.pdf http://eprints.uthm.edu.my/8412/2/EBRAHIM%20QASEM%20SALEH%20AL-WAJIH%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/8412/3/EBRAHIM%20QASEM%20SALEH%20AL-WAJIH%20WATERMARK.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uthm-ep.8412
record_format	uketd_dc
spelling	my-uthm-ep.84122023-02-26T07:09:06Z Threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition 2022-03 Saleh Al-Wajih, Ebrahim Qasem QA76 Computer software Arabic and English handwritten digit recognition is a challenging problem because the writing style differs from one writer to another. In middle east countries, many official forms are prepared to be written using either Arabic or English languages. However, some people fill the form using both languages (Arabic and English), which adds more challenges to recognize digits. Nowadays, deep learning approaches are considered the hot trend of new research, including Convolutional Neural Networks (CNN). CNN is used in many applications and modified to produce other models such as Local Binary Convolutional Neural Networks (LBCNN). LBCNN was created by fusing Local Binary Pattern (LBP) with CNN by reformulating LBP as a convolution layer called Local Binary Convolution (LBC). However, LBCNN suffers from the random assign 1, 0, or -1 to LBC weights, making LBCNN less robust. Nevertheless, using another LBP-based technique such as Center-Symmetric Local Binary Patterns (CS-LBP) can address such issues. In this thesis, a new model based on CS-LBP is proposed called Center-Symmetric Local Binary Convolutional Neural Networks (CS-LBCNN) that addresses the issues of LBCNN. Further, an enhanced version of CS-LBCNN is proposed called Threshold Center-Symmetric Local Binary Convolutional Neural Networks (TCSLBCNN) that addresses another issue related to the zero-thresholding function. The proposed models are compared against state-of-the-art techniques that used the MNIST and MADBase as a bilingual dataset. The proposed TCS-LBCNN model proves its ability to give a more accurate and significant classification rate than the existing LBCNN models. For the bilingual dataset, the TCS-LBCNN enhances the performance of LBCNN and CS-LBCNN, in terms of accuracy, by 0.15% and 0.03%, respectively. In addition, the comparison shows that the accuracy acquired by TCS-LBCNN is the second-highest using the MNIST and MADBase datasets. 2022-03 Thesis http://eprints.uthm.edu.my/8412/ http://eprints.uthm.edu.my/8412/1/24p%20EBRAHIM%20QASEM%20SALEH%20AL-WAJIH.pdf text en public http://eprints.uthm.edu.my/8412/2/EBRAHIM%20QASEM%20SALEH%20AL-WAJIH%20COPYRIGHT%20DECLARATION.pdf text en staffonly http://eprints.uthm.edu.my/8412/3/EBRAHIM%20QASEM%20SALEH%20AL-WAJIH%20WATERMARK.pdf text en validuser phd doctoral Universiti Tun Hussein Onn Malaysia Fakulti Sains Komputer dan Teknologi Maklumat
institution	Universiti Tun Hussein Onn Malaysia
collection	UTHM Institutional Repository
language	English English English
topic	QA76 Computer software
spellingShingle	QA76 Computer software Saleh Al-Wajih, Ebrahim Qasem Threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition
description	Arabic and English handwritten digit recognition is a challenging problem because the writing style differs from one writer to another. In middle east countries, many official forms are prepared to be written using either Arabic or English languages. However, some people fill the form using both languages (Arabic and English), which adds more challenges to recognize digits. Nowadays, deep learning approaches are considered the hot trend of new research, including Convolutional Neural Networks (CNN). CNN is used in many applications and modified to produce other models such as Local Binary Convolutional Neural Networks (LBCNN). LBCNN was created by fusing Local Binary Pattern (LBP) with CNN by reformulating LBP as a convolution layer called Local Binary Convolution (LBC). However, LBCNN suffers from the random assign 1, 0, or -1 to LBC weights, making LBCNN less robust. Nevertheless, using another LBP-based technique such as Center-Symmetric Local Binary Patterns (CS-LBP) can address such issues. In this thesis, a new model based on CS-LBP is proposed called Center-Symmetric Local Binary Convolutional Neural Networks (CS-LBCNN) that addresses the issues of LBCNN. Further, an enhanced version of CS-LBCNN is proposed called Threshold Center-Symmetric Local Binary Convolutional Neural Networks (TCSLBCNN) that addresses another issue related to the zero-thresholding function. The proposed models are compared against state-of-the-art techniques that used the MNIST and MADBase as a bilingual dataset. The proposed TCS-LBCNN model proves its ability to give a more accurate and significant classification rate than the existing LBCNN models. For the bilingual dataset, the TCS-LBCNN enhances the performance of LBCNN and CS-LBCNN, in terms of accuracy, by 0.15% and 0.03%, respectively. In addition, the comparison shows that the accuracy acquired by TCS-LBCNN is the second-highest using the MNIST and MADBase datasets.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Saleh Al-Wajih, Ebrahim Qasem
author_facet	Saleh Al-Wajih, Ebrahim Qasem
author_sort	Saleh Al-Wajih, Ebrahim Qasem
title	Threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition
title_short	Threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition
title_full	Threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition
title_fullStr	Threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition
title_full_unstemmed	Threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition
title_sort	threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition
granting_institution	Universiti Tun Hussein Onn Malaysia
granting_department	Fakulti Sains Komputer dan Teknologi Maklumat
publishDate	2022
url	http://eprints.uthm.edu.my/8412/1/24p%20EBRAHIM%20QASEM%20SALEH%20AL-WAJIH.pdf http://eprints.uthm.edu.my/8412/2/EBRAHIM%20QASEM%20SALEH%20AL-WAJIH%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/8412/3/EBRAHIM%20QASEM%20SALEH%20AL-WAJIH%20WATERMARK.pdf
_version_	1776103339602214912

Threshold center-symmetric local binary convolutional neural networks for bilingual handwritten digit recognition

Similar Items