A Review of Machine Learning Methods for Facial Image-Based Gender Classification

This work was presented at ICCS 2023 as part of undergraduate research conducted at Lovely Professional University, India. The paper provides a comprehensive review of machine learning and deep learning approaches for gender classification using facial image data. It covers feature extraction techniques such as Local Binary Patterns (LBP), Principal Component Analysis (PCA), and Convolutional Neural Networks (CNNs), along with classification methods including Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), and Artificial Neural Networks (ANNs). A comparative analysis of these approaches is presented based on performance metrics such as accuracy, F1-score, and computational efficiency across benchmark datasets. The study highlights the strengths and limitations of traditional machine learning techniques versus modern deep learning methods. The findings indicate that deep learning-based approaches, particularly those leveraging transfer learning, achieve superior performance, while classical methods remain effective in resource-constrained environments. This work demonstrates foundational research skills in literature review, comparative analysis, and applied machine learning within the domain of computer vision.