Gender Classification Based on Machine Learning Models
Mubeen Ahmed Khan, Naveen Kulkarni, Abdul Haq Nalband · 2025
Automatic gender categorization has become an increasingly significant area in computer vision, with several applications. Gender equality is nowadays a keyword for today's scenario. This research explores the efficacy of deep learning algorithms for gender classification using veiled faces and body postures. This work compares several deep learning models trained on a specifically curated veiled face and body posture dataset. Each model's performance is calculated using accuracy, precision, recall, and the F1-score. This study attempts to provide insight into the viability and constraints of gender categorization with obscured facial features and body language cues. This work helps detect gender classifications in medical investigations, and police investigations, and to reduce gender inequalities in society. This work is also helpful to Education-ratio in gender-based quality education. Also this analysis could be helpful to census identification and for calculating the gender equality wherever required for the growth and development of of the country.