Home > Research > Publications & Outputs > Writer identification approach based on bag of ...

Links

Text available via DOI:

View graph of relations

Writer identification approach based on bag of words with OBI features

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Writer identification approach based on bag of words with OBI features. / Durou, Amal; Aref, Ibrahim; Al-Maadeed, Somaya et al.
In: Information Processing & Management, Vol. 56, No. 2, 31.03.2019, p. 354-366.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Durou, A, Aref, I, Al-Maadeed, S, Bouridane, A & Benkhelifa, E 2019, 'Writer identification approach based on bag of words with OBI features', Information Processing & Management, vol. 56, no. 2, pp. 354-366. https://doi.org/10.1016/j.ipm.2017.09.005

APA

Durou, A., Aref, I., Al-Maadeed, S., Bouridane, A., & Benkhelifa, E. (2019). Writer identification approach based on bag of words with OBI features. Information Processing & Management, 56(2), 354-366. https://doi.org/10.1016/j.ipm.2017.09.005

Vancouver

Durou A, Aref I, Al-Maadeed S, Bouridane A, Benkhelifa E. Writer identification approach based on bag of words with OBI features. Information Processing & Management. 2019 Mar 31;56(2):354-366. Epub 2019 Jan 7. doi: 10.1016/j.ipm.2017.09.005

Author

Durou, Amal ; Aref, Ibrahim ; Al-Maadeed, Somaya et al. / Writer identification approach based on bag of words with OBI features. In: Information Processing & Management. 2019 ; Vol. 56, No. 2. pp. 354-366.

Bibtex

@article{18a195512ae84073a64768488a9a4405,
title = "Writer identification approach based on bag of words with OBI features",
abstract = "Handwriter identification aims to simplify the task of forensic experts by providing them with semi-automated tools in order to enable them to narrow down the search to determine the final identification of an unknown handwritten sample. An identification algorithm aims to produce a list of predicted writers of the unknown handwritten sample ranked in terms of confidence measure metrics for use by the forensic expert will make the final decision.Most existing handwriter identification systems use either statistical or model-based approaches. To further improve the performances this paper proposes to deploy a combination of both approaches using Oriented Basic Image features and the concept of graphemes codebook. To reduce the resulting high dimensionality of the feature vector a Kernel Principal Component Analysis has been used. To gauge the effectiveness of the proposed method a performance analysis, using IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting, has been carried out. The results obtained achieved an accuracy of 96% thus demonstrating its superiority when compared against similar techniques.",
keywords = "Writer identification, Oriented basic image, Kernel principal component analysis, Graphemes, Text independent classification",
author = "Amal Durou and Ibrahim Aref and Somaya Al-Maadeed and Ahmed Bouridane and Elhadj Benkhelifa",
year = "2019",
month = mar,
day = "31",
doi = "10.1016/j.ipm.2017.09.005",
language = "English",
volume = "56",
pages = "354--366",
journal = "Information Processing & Management",
publisher = "Elsevier",
number = "2",

}

RIS

TY - JOUR

T1 - Writer identification approach based on bag of words with OBI features

AU - Durou, Amal

AU - Aref, Ibrahim

AU - Al-Maadeed, Somaya

AU - Bouridane, Ahmed

AU - Benkhelifa, Elhadj

PY - 2019/3/31

Y1 - 2019/3/31

N2 - Handwriter identification aims to simplify the task of forensic experts by providing them with semi-automated tools in order to enable them to narrow down the search to determine the final identification of an unknown handwritten sample. An identification algorithm aims to produce a list of predicted writers of the unknown handwritten sample ranked in terms of confidence measure metrics for use by the forensic expert will make the final decision.Most existing handwriter identification systems use either statistical or model-based approaches. To further improve the performances this paper proposes to deploy a combination of both approaches using Oriented Basic Image features and the concept of graphemes codebook. To reduce the resulting high dimensionality of the feature vector a Kernel Principal Component Analysis has been used. To gauge the effectiveness of the proposed method a performance analysis, using IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting, has been carried out. The results obtained achieved an accuracy of 96% thus demonstrating its superiority when compared against similar techniques.

AB - Handwriter identification aims to simplify the task of forensic experts by providing them with semi-automated tools in order to enable them to narrow down the search to determine the final identification of an unknown handwritten sample. An identification algorithm aims to produce a list of predicted writers of the unknown handwritten sample ranked in terms of confidence measure metrics for use by the forensic expert will make the final decision.Most existing handwriter identification systems use either statistical or model-based approaches. To further improve the performances this paper proposes to deploy a combination of both approaches using Oriented Basic Image features and the concept of graphemes codebook. To reduce the resulting high dimensionality of the feature vector a Kernel Principal Component Analysis has been used. To gauge the effectiveness of the proposed method a performance analysis, using IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting, has been carried out. The results obtained achieved an accuracy of 96% thus demonstrating its superiority when compared against similar techniques.

KW - Writer identification

KW - Oriented basic image

KW - Kernel principal component analysis

KW - Graphemes

KW - Text independent classification

UR - https://www.researchgate.net/publication/320341379_Writer_identification_approach_based_on_bag_of_words_with_OBI_features

U2 - 10.1016/j.ipm.2017.09.005

DO - 10.1016/j.ipm.2017.09.005

M3 - Journal article

VL - 56

SP - 354

EP - 366

JO - Information Processing & Management

JF - Information Processing & Management

IS - 2

ER -