Gender estimation using dynamic features of digitally captured handwriting: A pilot study

Handwriting is a neuromuscular task influenced by factors such as age, gender, and handedness, with gender being a significant feature that can aid in classification. In the present study, thirty handwriting samples were analysed using a digital tablet with MovAlyzeR software. The key dynamic features, including absolute jerk, peak vertical velocity and acceleration, loop surface area, slant and pressure, were analysed using software. The results highlighted a significant difference in absolute jerk, with males showing higher values, underscoring its importance in gender classification. Although other features did not show significant gender differences, they remain important for comprehensive handwriting analysis. The study highlights the importance of dynamic handwriting features for understanding gender differences. Further studies are underway to identify more dynamic features contributing to gender classification from digitally captured handwriting.