This is the authors' abstract. We don't add key points for this paper.
The domain of Deep Learning (DL) methods for face recognition has captured significant attention from researchers in the field. This is due to their practical applications in various fields, including security, image scene auto-tagging, social networking applications, homeland security, and DoD, to name a few. Extensive research is being done in this domain, and numerous research papers showcase a wide range of Deep Convolutional Neural Network (DCNN) model iterations, demonstrating these approaches’ robust potential and effectiveness and showcasing significant advancements in technology for face identification and verification. Certain DL face recognition models are designed as multi-class classifiers utilizing the Softmax classifier, while others generate embeddings, such as FaceNet. However, a significant issue with many of these DL methods for face recognition is the scarcity of studies analyzing the factors that influence face recognition prediction accuracy. This paper studies some challenges and factors affecting image face recognition accuracy in DL techniques.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Subramanya et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: