Gender Estimation via Handwriting Dynamics : A Statistical and Machine Learning Approach
Article content
Abstract
Gender estimation from handwriting has long been of interest in forensic document examination. However, most prior studies rely on static handwriting features, with limited exploration of dynamic writing behaviour. The advent of advanced technologies in recording handwriting made it possible to study the dynamic nature of the handwriting. The present study investigates gender-related differences in dynamic handwriting features derived from digitally captured natural style-handwriting, integrating statistical analysis with machine learning classification. Handwriting samples were collected from 200 participants (100 males, 100 females) using a pen-enabled digital tablet across three trials. Five primary dynamic features: Time-stamped X and Y coordinate data, pressure, azimuth, altitude and time, were recorded and used to derive 21 kinematic, spatial, pressure-based, and temporal features. The statistical analysis using Mann-Whitney U test, indicated significant gender-related differences in several dynamic features, including temporal parameters (pen-up duration, pen-down duration, total duration), pressure-related measures, spatial (handwriting width and height) and kinematic parameters like velocity and acceleration. Features demonstrating statistical significance were subsequently employed as inputs to supervised machine learning models, including Random Forest, Support Vector Machine, and Gradient Boosting classifiers. The Random Forest achieved the highest classification accuracy (86.7%) followed by Support Vector Machine (82.7%) and Gradient Boosting (80%). The findings demonstrate the potential of dynamic handwriting features in forensic document examination for gender estimation and preliminary profiling of writers
Keywords
forensic sciences, forensic document examination, dynamic handwriting, gender classification, statistical analysis, machine learning
Downloads
References
Hilton, O. (1993). Scientific examination of questioned documents (Rev. ed.). CRC Press.
Thomassen, A. J. W. M., & Teulings, H. L. (1983). The development of handwriting. In The psychology of written language (pp. 179–213).
Bisesi, M. S. (2006). Scientific examination of questioned documents. In J. S. Kelly & B. S. Lindblom (Eds.), Scientific examination of questioned documents (2nd ed.). CRC Press.
Harralson, H. H., & Miller, L. S. (2017). Huber and Headrick’s handwriting identification: Facts and fundamentals. CRC Press.
Faundez-Zanuy, M., Fierrez, J., Ferrer, M. A., Díaz, M., Tolosana, R., & Plamondon, R. (2020). Handwriting biometrics: Applications and future trends in e-security and e-health. Cognitive Computation, 12, 940–953.
Mergl, R., Tigges, P., Schröter, A., Möller, H. J., & Hegerl, U. (1999). Digitized analysis of handwriting and drawing movements in healthy subjects. Journal of Neuroscience Methods, 90(2), 157–169.
Harralson, H. H., Teulings, H. L., & Farley, B. G. (2007). Comparison of handwriting kinematics in movement disorders and forgery. In Proceedings of the 13th Conference of the International Graphonomics Society (pp. 143–148).
Faundez-Zanuy, M., Mekyska, J., & Impedovo, D. (2021). Online handwriting, signature and touch dynamics: Tasks and potential applications in the field of security and health. Cognitive Computation, 13, 940–954.
Accardo, A. P., Genna, M., & Borean, M. (2013). Development, maturation, and learning influence on handwriting kinematics. Human Movement Science, 32(1), 136–146.
Hopcan, S., & Tokel, S. T. (2021). Exploring the effectiveness of a mobile writing application for students with dysgraphia. Education and Information Technologies, 26, 5561–5584.
Osborn, A. S. (1929). Questioned documents (2nd ed.). Boyd Printing (p.140).
Hodgins, J. H. (1971). Determination of sex from handwriting. Canadian Society of Forensic Science Journal, 4(4), 124–132.
Hamid, S., & Loewenthal, K. M. (1996). Inferring gender from handwriting in Urdu and English. Journal of Social Psychology, 136(6), 778–782.
Young, P. T. (1931). Sex differences in handwriting. Journal of Applied Psychology, 15(5), 486–498.
Hecker, M. R. (1996). The scientific examination of sex differences in handwriting. Paper presented at the American Society of Questioned Document Examiners Meeting.
Lester, D., Werling, N., & Heinle, N. H. (1982). Graphoanalytic differences by sex and handedness. Perceptual and Motor Skills, 55(3), 1190.
Totty, R. N., Hardcastle, R. A., & Dempsey, J. (1983). The dependence of slope of handwriting upon the sex and handedness of the writer. Journal of the Forensic Science Society, 23(3), 237–240.
Kumar, S., Saran, V., Vaid, B. A., & Gupta, A. K. (2013). Handwriting and gender: A statistical study. Z Zagadnień Nauk Sądowych, 95, 620–626.
Upadhyay, S., & Singh, J. (2017). Determination of sex through handwriting characteristics. International Journal of Current Research and Review, 9(13), 11–18.
Sharma, V., Bains, M., Verma, R., Verma, N., & Kumar, R. (2023). Novel use of logistic regression and likelihood ratios for estimation of gender from handwriting features. Australian Journal of Forensic Sciences, 55(1), 89–106.
Harralson, H. H. (2013). Developments in handwriting and signature identification in the digital age. Anderson Publishing.
Angel, M., & Kelly, J. S. (Eds.). (2020). Forensic document examination in the 21st century. CRC Press.
Mohammed, L. A., Found, B., Caligiuri, M., & Rogers, D. (2011). The dynamic character of disguise behavior for text-based, mixed, and stylized signatures. Journal of Forensic Sciences, 56, S136–S141.
Ahmad, S. M. S., Ling, L. Y., Anwar, R. M., Faudzi, M. A., & Shakil, A. (2013). Analysis of the effects and relationship of perceived handwritten signature size, graphical complexity, and legibility with dynamic parameters for forged and genuine samples. Journal of Forensic Sciences, 58(3), 724–731.
Sharma, P., Singh, M., & Jasuja, O. P. (2021). Forensic examination of electronic signatures: A comparative study. Nowa Kodyfikacja Prawa Karnego, 59, 149–149.
Liwicki, M., Schlapbach, A., & Bunke, H. (2011). Automatic gender detection using online and offline information. Pattern Analysis and Applications, 14(1), 87–92.
Sesa-Nogueras, E., Faundez-Zanuy, M., & Roure-Alcobé, J. (2016). Gender classification by means of online uppercase handwriting: A text-dependent allographic approach. Cognitive Computation, 8(1), 15–29.
Likforman-Sulem, L., Cordasco, G., & Esposito, A. (2022). Is online handwriting gender-sensitive? In Pattern Recognition and Artificial Intelligence (LNCS Vol. 13363, pp. 300–314). Springer.
Cordasco, G., Buonanno, M., Faundez-Zanuy, M., Riviello, M. T., Likforman-Sulem, L., & Esposito, A. (2020). Gender identification through handwriting: An online approach. In Proceedings of the 11th IEEE International Conference on Cognitive Infocommunications (CogInfoCom) (pp. 1–6). IEEE.
Faundez-Zanuy, M., & Mekyska, J. (2023). Analysis of gender differences in online handwriting signals for enhancing e-health and e-security applications. Cognitive Computation, 15, 208–219.
Al-Qawasmeh, N., Khayyat, M., & Suen, C. Y. (2023). Novel features to detect gender from handwritten documents. Pattern Recognition Letters, 171, 201–208.
Shin, J., Uchida, Y., Maniruzzaman, M., Hirooka, K., Megumi, A., & Yasumura, A. (2024). Online handwriting-based gender recognition using statistical and machine learning approaches. IEEE Access, 12, 1–10.
NeuroScript. (n.d.). NeuroScript website. https://neuroscript.net/
International Organization for Standardization. (2014). ISO/IEC 19794-7: Information Technology-Biometric data interchange Formats-Part 7: Signature/sign time series data. ISO/IEC.
Mann, H. B., & Whitney, D. R. (1947). On a test of whether one of two random variables is stochastically larger than the other. The Annals of Mathematical Statistics, 18, 50–60.
Alkahtani, A. A., & Platt, A. W. (2011). The influence of gender on the ability to simulate handwritten signatures: A study of Arabic writers. Journal of Forensic Sciences, 56(4), 950–953.
Meissel, K., & Yao, E. S. (2024). Using Cliff’s delta as a non-parametric effect size measure: an accessible web app and R tutorial. Practical Assessment, Research, and Evaluation, 29(1).
Zhou, Z.H. (2021). Machine learning. Springer Nature.
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20, 273–297.
Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32.
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232.
Berrar, D. (2019). Performance measures for binary classification. In Encyclopaedia of bioinformatics and computational biology (Vol. 1, pp. 546–560). Elsevier.
Scikit-learn developers. (2007). Scikit-learn user guide. https://scikit-learn.org
Lei, H., & Govindaraju, V. A. (2005). A comparative study on the consistency of features in on-line signature verification. Pattern Recognition Letters, 26(15), 2483–2489.
Pascal, G. R. (1943). Handwriting pressure: Its measurement and significance. Journal of Personality, 11(3), 235–254.
Linden, J., Marquis, R., Bozza, S., & Taroni, F. (2018). Dynamic signatures: A review of dynamic feature variation and forensic methodology. Forensic Science International, 291, 216–229.
Dewhurst, T. N., Ballantyne, K. N., & Found, B. (2016). Empirical investigation of biometric, non-visible, intra-signature features in known and simulated signatures. Australian Journal of Forensic Sciences, 48(6), 659–675.
Article details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
You must read and accept the copyright terms and conditions(click here for copyright terms).