A Comprehensive Review of Face Detection Technologies

This review paper scrutinizes various methodologies in face detection, encompassing traditional and incremental learning approaches. Addressing pivotal research questions, it examines the efficiency and accuracy of existing face detection technologies, alongside assessing the pace of research advancement in this domain. Leveraging a diverse array of papers from Scopus, the paper conducts a meticulous comparison of model accuracies, dataset compositions, and annual research trends. Key findings highlight Google FaceNet's leading accuracy of 99.63%, closely trailed by DLIB at 99.38% and Blazeface at 98.61%. Notably, the paper underscores the critical influence of dataset composition on model performance, emphasizing the significance of judicious dataset selection. Moreover, standout performers in Scopus-indexed papers include Support Vector Machine and Logistic Regression algorithms, demonstrating high accuracies and robustness in face detection tasks. The analysis also reveals an exponential increase in research engagement over the past nine years over face detection, indicating the increasing relevance and importance of face recognition technologies. This comprehensive exploration offers valuable insights and practical guidance for researchers and practitioners navigating the evolving landscape of face detection research.