A Comparative Study of Machine Learning Approaches for Handwriter Identification

Amal Durou; Somaya Al-Maadeed; Ibrahim Aref; Ahmed Bouridane; Mosa Elbendak

doi:10.1109/ICGS3.2019.8688032

A Comparative Study of Machine Learning Approaches for Handwriter Identification

Amal Durou, Somaya Al-Maadeed, Ibrahim Aref, Ahmed Bouridane, Mosa Elbendak

Computer and Information Sciences Department

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

5 Citations (Scopus)

Abstract

During the past few years, writer identification has attracted significant interest due to its real-life applications including document analysis, forensics etc. Machine learning algorithms have played an important role in the development of writer identification systems demonstrating very effective performance results. Recently, the emergence of deep learning has led to various system in computer vision and pattern recognition applications. Therefore, this work aims to assess and compare the performance between one of the deep learning algorithms, AlexNet model, with two of the most effective machine learning classification approaches: Support Vector Machine (SVM) and K-Nearest-Neighbour (KNN). The evaluation has been conducted using both IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting.

Original language	English
Title of host publication	Proceedings of 12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	206-212
ISBN (Electronic)	9781538670019
ISBN (Print)	9781538670026
DOIs	https://doi.org/10.1109/ICGS3.2019.8688032
Publication status	Published - 11 Apr 2019
Event	12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019 - London, United Kingdom Duration: 16 Jan 2019 → 18 Jan 2019

Conference

Conference	12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019
Country/Territory	United Kingdom
City	London
Period	16/01/19 → 18/01/19

Keywords

convolutional neural network
feature extraction
machine learning
writer identification

Access to Document

10.1109/ICGS3.2019.8688032

Cite this

Durou, A., Al-Maadeed, S., Aref, I., Bouridane, A., & Elbendak, M. (2019). A Comparative Study of Machine Learning Approaches for Handwriter Identification. In Proceedings of 12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019 (pp. 206-212). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICGS3.2019.8688032

@inproceedings{a66daa508a36417399f46e399ef99944,

title = "A Comparative Study of Machine Learning Approaches for Handwriter Identification",

abstract = "During the past few years, writer identification has attracted significant interest due to its real-life applications including document analysis, forensics etc. Machine learning algorithms have played an important role in the development of writer identification systems demonstrating very effective performance results. Recently, the emergence of deep learning has led to various system in computer vision and pattern recognition applications. Therefore, this work aims to assess and compare the performance between one of the deep learning algorithms, AlexNet model, with two of the most effective machine learning classification approaches: Support Vector Machine (SVM) and K-Nearest-Neighbour (KNN). The evaluation has been conducted using both IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting.",

keywords = "convolutional neural network, feature extraction, machine learning, writer identification",

author = "Amal Durou and Somaya Al-Maadeed and Ibrahim Aref and Ahmed Bouridane and Mosa Elbendak",

year = "2019",

month = apr,

day = "11",

doi = "10.1109/ICGS3.2019.8688032",

language = "English",

isbn = "9781538670026",

pages = "206--212",

booktitle = "Proceedings of 12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019 ; Conference date: 16-01-2019 Through 18-01-2019",

}

Durou, A, Al-Maadeed, S, Aref, I, Bouridane, A & Elbendak, M 2019, A Comparative Study of Machine Learning Approaches for Handwriter Identification. in Proceedings of 12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019. Institute of Electrical and Electronics Engineers Inc., pp. 206-212, 12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019, London, United Kingdom, 16/01/19. https://doi.org/10.1109/ICGS3.2019.8688032

A Comparative Study of Machine Learning Approaches for Handwriter Identification. / Durou, Amal; Al-Maadeed, Somaya; Aref, Ibrahim et al.
Proceedings of 12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 206-212.

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

TY - GEN

T1 - A Comparative Study of Machine Learning Approaches for Handwriter Identification

AU - Durou, Amal

AU - Al-Maadeed, Somaya

AU - Aref, Ibrahim

AU - Bouridane, Ahmed

AU - Elbendak, Mosa

PY - 2019/4/11

Y1 - 2019/4/11

N2 - During the past few years, writer identification has attracted significant interest due to its real-life applications including document analysis, forensics etc. Machine learning algorithms have played an important role in the development of writer identification systems demonstrating very effective performance results. Recently, the emergence of deep learning has led to various system in computer vision and pattern recognition applications. Therefore, this work aims to assess and compare the performance between one of the deep learning algorithms, AlexNet model, with two of the most effective machine learning classification approaches: Support Vector Machine (SVM) and K-Nearest-Neighbour (KNN). The evaluation has been conducted using both IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting.

AB - During the past few years, writer identification has attracted significant interest due to its real-life applications including document analysis, forensics etc. Machine learning algorithms have played an important role in the development of writer identification systems demonstrating very effective performance results. Recently, the emergence of deep learning has led to various system in computer vision and pattern recognition applications. Therefore, this work aims to assess and compare the performance between one of the deep learning algorithms, AlexNet model, with two of the most effective machine learning classification approaches: Support Vector Machine (SVM) and K-Nearest-Neighbour (KNN). The evaluation has been conducted using both IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting.

KW - convolutional neural network

KW - feature extraction

KW - machine learning

KW - writer identification

U2 - 10.1109/ICGS3.2019.8688032

DO - 10.1109/ICGS3.2019.8688032

M3 - Conference contribution

AN - SCOPUS:85065039946

SN - 9781538670026

SP - 206

EP - 212

BT - Proceedings of 12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Conference on Global Security, Safety and Sustainability, ICGS3 2019

Y2 - 16 January 2019 through 18 January 2019

ER -

A Comparative Study of Machine Learning Approaches for Handwriter Identification

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this