A comprehensive survey on masked face recognition techniques using deep learning: Motivations, research progress, and future challenges

Masked Face Recognition (MFR) has become a critical research area, accelerated by the widespread adoption of facial masks during and after the COVID-19 pandemic. Traditional face recognition systems struggle under partial occlusion, motivating extensive research into specialized techniques capable of recognizing masked faces with high reliability. This survey provides a comprehensive and systematic review of existing work in the field, covering research published from 2021 onward. The study examines the motivations, methodological evolution, and challenges of MFR, focusing on key deep learning–based approaches such as Occlusion-Robust Feature Extraction (ORFE), Occlusion-Aware Face Recognition (OAFR), and Occlusion Recovery-Based Face Recognition (ORBFR). In addition, the survey analyzes commonly used pipelines, loss functions, network architectures, evaluation metrics, and datasets relevant to MFR. A detailed comparative overview of performance results from existing studies is also presented to support benchmarking and methodological selection. Finally, the paper highlights open challenges, emerging trends, and future research directions, such as dataset limitations, model generalization, validation strategies, and ethical considerations, aimed at guiding researchers toward the development of more accurate, robust, and efficient masked face recognition systems.