Gender classification based on handwriting using Gurmukhi characters and hybrid feature extraction techniques

Gender classification using one or more features has emerged as a promising solution to issues in fields such as criminal and forensic examinations. However, predicting an individual’s gender based on their handwriting remains a challenging task. In this study, the authors propose a novel approach to classify gender based on pre-segmented Gurmukhi (Punjabi) characters. They employ feature extraction methods and classification algorithms such as K-nearest neighbours, random forest, Support Vector Machine, and Multilayer Perceptrons. The dataset consists of approximately 84,000 Gurmukhi characters, contributed by 280 writers, including 150 males and 130 females. Each writer provided 300 characters (60 characters written five times). The authors extracted features based on diagonal, transition, zoning, and peak extent. By using a hybrid of feature extraction techniques, the random forest classifier achieved higher accuracy than the other classifiers. This study presents a promising approach to gender classification based on handwriting and underscores the potential of hybrid feature extraction techniques to improve the accuracy of gender classification systems.