Writer Identification Using Handwritten Cursive Texts and Single Character Words
One of the biometric methods in authentication systems is the writer verification/identification using password handwriting. The main objective of this paper is to present a robust writer verification system by using cursive texts as well as block letter words. To evaluate the system, two datasets h...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-04-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/8/4/391 |
id |
doaj-4d7620c365294482bc2b3bcf114592b5 |
---|---|
record_format |
Article |
spelling |
doaj-4d7620c365294482bc2b3bcf114592b52020-11-24T21:44:27ZengMDPI AGElectronics2079-92922019-04-018439110.3390/electronics8040391electronics8040391Writer Identification Using Handwritten Cursive Texts and Single Character WordsTobias Kutzner0Carlos F. Pazmiño-Zapatier1Matthias Gebhard2Ingrid Bönninger3Wolf-Dietrich Plath4Carlos M. Travieso5Institute of Medical Technology, Brandenburg University of Technology Cottbus, 01968 Senftenberg, GermanyInstituto para el Desarrollo Tecnológico y la Innovación en Comunicaciones (IDeTIC), Universidad de Las Palmas de Gran Canaria, 35017 Las Palmas de Gran Canaria, SpainInstitute of Medical Technology, Brandenburg University of Technology Cottbus, 01968 Senftenberg, GermanyInstitute of Medical Technology, Brandenburg University of Technology Cottbus, 01968 Senftenberg, GermanyInstitute of Medical Technology, Brandenburg University of Technology Cottbus, 01968 Senftenberg, GermanyInstituto para el Desarrollo Tecnológico y la Innovación en Comunicaciones (IDeTIC), Universidad de Las Palmas de Gran Canaria, 35017 Las Palmas de Gran Canaria, SpainOne of the biometric methods in authentication systems is the writer verification/identification using password handwriting. The main objective of this paper is to present a robust writer verification system by using cursive texts as well as block letter words. To evaluate the system, two datasets have been used. One of them is called Secure Password DB 150, which is composed of 150 users with 18 samples of single character words per user. Another dataset is public and called IAM online handwriting database, and it is composed of 220 users of cursive text samples. Each sample has been defined by a set of features, composed of 67 geometrical, statistical, and temporal features. In order to get more discriminative information, two feature reduction methods have been applied, Fisher Score and Info Gain Attribute Evaluation. Finally, the classification system has been implemented by hold-out cross validation and k-folds cross validation strategies for three different classifiers, K-NN, Naïve Bayes and Bayes Net classifiers. Besides, it has been applied for verification and identification approaches. The best results of 95.38% correct classification are achieved by using the k-nearest neighbor classifier for single character DB. A feature reduction by Info Gain Attribute Evaluation improves the results for Naïve Bayes Classifier to 98.34% for IAM online handwriting DB. It is concluded that the set of features and its reduction are a strong selection for the based-password handwritten writer identification in comparison with the state-of-the-art.https://www.mdpi.com/2079-9292/8/4/391handwritingpassword identificationonline strokeswriter verificationreduction featureon-line handwriting features |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tobias Kutzner Carlos F. Pazmiño-Zapatier Matthias Gebhard Ingrid Bönninger Wolf-Dietrich Plath Carlos M. Travieso |
spellingShingle |
Tobias Kutzner Carlos F. Pazmiño-Zapatier Matthias Gebhard Ingrid Bönninger Wolf-Dietrich Plath Carlos M. Travieso Writer Identification Using Handwritten Cursive Texts and Single Character Words Electronics handwriting password identification online strokes writer verification reduction feature on-line handwriting features |
author_facet |
Tobias Kutzner Carlos F. Pazmiño-Zapatier Matthias Gebhard Ingrid Bönninger Wolf-Dietrich Plath Carlos M. Travieso |
author_sort |
Tobias Kutzner |
title |
Writer Identification Using Handwritten Cursive Texts and Single Character Words |
title_short |
Writer Identification Using Handwritten Cursive Texts and Single Character Words |
title_full |
Writer Identification Using Handwritten Cursive Texts and Single Character Words |
title_fullStr |
Writer Identification Using Handwritten Cursive Texts and Single Character Words |
title_full_unstemmed |
Writer Identification Using Handwritten Cursive Texts and Single Character Words |
title_sort |
writer identification using handwritten cursive texts and single character words |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2019-04-01 |
description |
One of the biometric methods in authentication systems is the writer verification/identification using password handwriting. The main objective of this paper is to present a robust writer verification system by using cursive texts as well as block letter words. To evaluate the system, two datasets have been used. One of them is called Secure Password DB 150, which is composed of 150 users with 18 samples of single character words per user. Another dataset is public and called IAM online handwriting database, and it is composed of 220 users of cursive text samples. Each sample has been defined by a set of features, composed of 67 geometrical, statistical, and temporal features. In order to get more discriminative information, two feature reduction methods have been applied, Fisher Score and Info Gain Attribute Evaluation. Finally, the classification system has been implemented by hold-out cross validation and k-folds cross validation strategies for three different classifiers, K-NN, Naïve Bayes and Bayes Net classifiers. Besides, it has been applied for verification and identification approaches. The best results of 95.38% correct classification are achieved by using the k-nearest neighbor classifier for single character DB. A feature reduction by Info Gain Attribute Evaluation improves the results for Naïve Bayes Classifier to 98.34% for IAM online handwriting DB. It is concluded that the set of features and its reduction are a strong selection for the based-password handwritten writer identification in comparison with the state-of-the-art. |
topic |
handwriting password identification online strokes writer verification reduction feature on-line handwriting features |
url |
https://www.mdpi.com/2079-9292/8/4/391 |
work_keys_str_mv |
AT tobiaskutzner writeridentificationusinghandwrittencursivetextsandsinglecharacterwords AT carlosfpazminozapatier writeridentificationusinghandwrittencursivetextsandsinglecharacterwords AT matthiasgebhard writeridentificationusinghandwrittencursivetextsandsinglecharacterwords AT ingridbonninger writeridentificationusinghandwrittencursivetextsandsinglecharacterwords AT wolfdietrichplath writeridentificationusinghandwrittencursivetextsandsinglecharacterwords AT carlosmtravieso writeridentificationusinghandwrittencursivetextsandsinglecharacterwords |
_version_ |
1725910117852905472 |