Login | Register

A Multi-Feature Selection Approach for Gender Identification of Handwriting based on Kernel Mutual Information


A Multi-Feature Selection Approach for Gender Identification of Handwriting based on Kernel Mutual Information

Bi, Ning, Suen, Ching Y, Nobile, Nicola and Tan, Jun (2018) A Multi-Feature Selection Approach for Gender Identification of Handwriting based on Kernel Mutual Information. Pattern Recognition Letters . ISSN 01678655 (In Press)

Text (application/pdf)
Suen-2018.pdf - Accepted Version
Restricted to Repository staff only until 18 May 2020.
Available under License Spectrum Terms of Access.

Official URL: http://dx.doi.org/10.1016/j.patrec.2018.05.005


This paper presents a new flexible approach to predict the gender of the writers from their handwriting samples. Handwriting features like slant, curvature, line separation, chain code, character shapes, and more, can be extracted from different methods. Therefore, the multi-feature sets are irrelevant and redundant. The conflict of the features exists in the sets, which affects the accuracy of classification and the computing cost. This paper proposes an approach, named Kernel Mutual Information (KMI), that focuses on feature selection. The KMI approach can decrease redundancies and conflicts. In addition, it extracts an optimal subset of features from the writing samples produced by male and female writers. To ensure that KMI can apply the various features, this paper describes the handwriting segmentation and handwritten text recognition technology used. The classification is carried out using a Support Vector Machine (SVM) on two databases. The first database comes from the ICDAR 2013 competition on gender prediction, which provides the samples in both Arabic and English. The other database contains the Registration-Document-Form (RDF) database in Chinese. The proposed and compared methods were evaluated on both databases. Results from the methods highlight the importance of feature selection for gender prediction from handwriting.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Article
Authors:Bi, Ning and Suen, Ching Y and Nobile, Nicola and Tan, Jun
Journal or Publication:Pattern Recognition Letters
Date:18 May 2018
  • Guangdong Provincial Government of China through the ”Computational Science Innovative Research Team” program
  • Guangdong Province Key Laboratory of Computational Science at the Sun Yat-Sen University
  • Technology Program of GuangDong (grant no. 2012B091100334)
  • National Science Foundation of China (grant no. 11471012)
  • China Scholarship Council (grant no. 201506385010)
Digital Object Identifier (DOI):10.1016/j.patrec.2018.05.005
Keywords:Gender prediction; Feature selection; Kernel method; Classification; Handwriting; Machine learning
ID Code:983893
Deposited On:28 May 2018 14:32
Last Modified:28 May 2018 14:32


G.A. Abandah, F.T. Jamour, E.A. Qaralleh Recognizing handwritten arabic words using grapheme segmentation and recurrent neural networks International Journal on Document Analysis and Recognition (IJDAR), 17 (3) (2014), pp. 275–291

H. Abbasi, M. Olyaee, H.R. Ghafari Rectifying reverse polygonization of digital curves for dominant point detection International Journal of Computer Science Issues(IJCSI), 10 (3) (2013), pp. 154–163

P. Ahmed, H. Mathkour On the development of an automated graphology system. Proceedings of International Conference on Artificial Intelligence (2008), pp. 897–901

S. Al Máadeed, W. Ayouby, A. Hassaine, J.M. Aljaam Quwi: An arabic and english handwriting dataset for offline writer identification Proceedings of International Conference on Frontiers in Handwriting Recognition (ICFHR), IEEE (2012), pp. 746–751

K. Bandi, S.N. Srihari Writer demographic classification using bagging and boosting Proceedings of 12th International Conference on Graphonomics Society (2005), pp. 133–137

J.R. Beech, I.C. Mackintosh Do differences in sex hormones affect handwriting style? evidence from digit ratio and sex role identity as determinants of the sex of handwriting Personality and Individual Differences, 39 (2) (2005), pp. 459–468

M. Blumenstein, X.Y. Liu, B. Verma An investigation of the modified direction feature for cursive character recognition Pattern Recognition, 40 (2) (2007), pp. 376–388

M. Bulacu, L. Schomaker Text-independent writer identification and verification using textural and allographic features IEEE Transactions on Pattern Analysis and Machine Intelligence, 29 (4) (2007), pp. 701–717

Q. Chen, Y. Yan, W. Deng, F. Yuan Handwriting identification based on constructing texture Proceedings of First International Conference on Intelligent Networks and Intelligent Systems(ICINIS), IEEE (2008), pp. 523–526

M. Dash, H. Liu Consistency-based search in feature selection Artificial Intelligence, 151 (1) (2003), pp. 155–176

C. Ding, H. Peng Minimum redundancy feature selection from microarray gene expression data Journal of Bioinformatics and Computational Biology, 3 (02) (2005), pp. 185–205

L. Du, X. You, H. Xu, Z. Gao, Y. Tang Wavelet domain local binary pattern features for writer identification Proceedings of 20th International Conference on Pattern Recognition (ICPR), IEEE (2010), pp. 3691–3694

A. Hassaine, S. Al Maadeed, J. Aljaam, A. Jaoua Icdar 2013 competition on gender prediction from handwriting Proceedings of 12th International Conference on Document Analysis and Recognition (ICDAR), IEEE (2013), pp. 1417–1421

A.S. Ibrahim, A.E. Youssef, A.L. Abbott Global vs. local features for gender identification using arabic and english handwriting Proceedings of IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), IEEE (2014), pp. 000155–000160

X. Li, X. Ding Writer identification of chinese handwriting using grid microstructure feature Advances in Biometrics, Springer (2009), pp. 1230–1239

C.-L. Liu Normalization-cooperated gradient feature extraction for handwritten character recognition IEEE Transactions on Pattern Analysis and Machine Intelligence, 29 (8) (2007), pp. 1465–1469

C.-L. Liu, H. Sako, H. Fujisawa Effects of classifier structures and training regimes on integrated segmentation and recognition of handwritten numeral strings IEEE Transactions on Pattern Analysis and Machine Intelligence, 26 (11) (2004), pp. 1395–1407

M. Liwicki, A. Schlapbach, H. Bunke Automatic gender detection using on-line and off-line information Pattern Analysis and Applications, 14 (1) (2011), pp. 87–92

H. Peng, F. Long, C. Ding Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy IEEE Transactions on Pattern Analysis and Machine Intelligence, 27 (8) (2005), pp. 1226–1238

M. Ring, B.M. Eskofier Optimal feature selection for nonlinear data using branch-and-bound in kernel space Pattern Recognition Letters, 68 (P1) (2015), pp. 56–62

I. Siddiqi, C. Djeddi, A. Raza, L. Souici-meslati Automatic analysis of handwriting for gender classification Pattern Analysis and Applications (2014), pp. 1–13

I. Siddiqi, N. Vincent A set of chain code based features for writer recognition Proceedings of 10th International Conference on Document Analysis and Recognition(ICDAR), IEEE (2009), pp. 981–985

I. Siddiqi, N. Vincent Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features Pattern Recognition, 43 (11) (2010), pp. 3853–3865

E. Sokic, A. Salihbegovic, M. Ahic-Djokic Analysis of off-line handwritten text samples of different gender using shape descriptors Proceedings of IX International Symposium on Telecommunications (BIHTEL), IEEE (2012), pp. 1–6

J. Tan, J.-H. Lai, C.-D. Wang, M.-S. Feng A stroke shape and structure based approach for off-line chinese handwriting identification International Journal of Intelligent Systems and Applications (IJISA), 3 (2) (2011), p. 1

J. Tan, J.-H. Lai, P. Wang, N. Bi Multiscale region projection method to discriminate between printed and handwritten text on registration forms International Journal of Pattern Recognition and Artificial Intelligence, 29 (8) (2015), pp. 153–185

J. Tan, J.-H. Lai, X.-X. Zuo The dataset system of economic dispute handwritten (dsedh) based on stroke shape and structure features Proceedings of 21st International Conference on Pattern Recognition (ICPR), IEEE (2012), pp. 661–664

T. Tan Texture feature extraction via visual cortical channel modelling Proceedings of 11th IAPR International Conference on Pattern Recognition Vol. III. Conference C: Image, Speech and Signal Analysis, IEEE (1992), pp. 607–610

R.P. Tett, C.A. Palmer The validity of handwriting elements in relation to self-report personality trait measures Personality and Individual Differences, 22 (1) (1997), pp. 11–18

J.J.-Y. Wang, H. Bensmail, X. Gao Feature selection and multi-kernel learning for sparse representation on a manifold Neural Networks, 51 (2014), pp. 9–16

J. Wen, B. Fang, J. Chen, Y. Tang, H. Chen Fragmented edge structure coding for chinese writer identification Neurocomputing, 86 (2012), pp. 45–51

L. Xu, X. Ding, L. Peng, X. Li An improved method based on weighted grid micro-structure feature for text-independent writer recognition Proceedings of International Conference on Document Analysis and Recognition (ICDAR), IEEE (2011), pp. 638–642

F. Yin, C.-L. Liu Handwritten chinese text line segmentation by clustering with distance metric learning Pattern Recognition, 42 (12) (2009), pp. 3146–3157
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Back to top Back to top