Online Handwriting-Based Gender Recognition Using Statistical and Machine Learning Approaches

• Published in: IEEE access Vol. 12; pp. 93791 - 93801
• Main Authors: Shin, Jungpil, Uchida, Yuta, Maniruzzaman, Md, Hirooka, Koki, Megumi, Akiko, Yasumura, Akira
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Algorithms; Automation; Biometrics (access control); Classification; Classification algorithms; Feature extraction; Gender; Gender issues; gender recognition; Handwriting; Handwriting recognition; handwritten; Image classification; Machine learning; Online analysis; Pattern recognition; Statistical analysis; Support vector machines; Task analysis
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3424453

The classification of gender from handwriting is a challenging issue that have great attention recently. Most of the exiting works were conducted on gender classification using face image and offline handwritten texts. This study explored an automated system for gender classification from online handwritten patterns. The handwritten samples were collected from 79 (Male: 32 and Female: 47) using pen tablet device. Each subject was asked to perform four tasks such as Zigzag trace (ZigZ-T), Zigzag predict (ZigZ-P), periodic line trace (PL-T), and periodic line predict (PL-P) and repeated its into three times. Thirty-six statistical features were derived from the six raw features, obtained from the Pen tablet device. Following that, we selected the best subset of features by employing Sequential Forward Floating Selection (SFFS)-based algorithm. At the same time, four machine learning (ML)-based algorithms like support vector machine (SVM), random forest, AdaBoost, and Gradient Boosting (GB) were employed for gender classification. We trained these four ML-based algorithms with leave-one-out method and optimized their hyperparameters using Optuna. The experimental results showed that SVM achieved a recognition accuracy of 88.10% for adult ZigZ-T tasks and 90.09% recognition accuracy was obtained by GB-based algorithm for children whose drawing ZigZ-P tasks. our proposed system demonstrates promise in automating gender classification based on handwriting patterns, offering insights into the significant differences between adult and child handwriting. The ability to identify gender accurately from handwriting has broad applications, including security enhancements and personalized service provision.