Face Recognition is an active and critical research problem in computer vision and image understanding. In the technology of biometrics, face detection plays a significant role in fingerprint, retinal scanning, and voice identification. Attractive application areas of face recognition are consumer applications, law enforcement, automobile security, access control, immigration, education, retail, and healthcare.
   To address the challenges such as pose changes, presence or absence of structuring elements, facial expression changes, aging of the face, several illumination conditions, image resolution and modality, and availability, researchers have incorporated diverse machine learning and deep learning techniques to perform face recognition.
   More recently, with the rapid advancement of deep learning technology, face recognition majorly utilizes deep learning architectures. Deep learning possesses significant benefits to contend with the issues in face recognition, such as pose, illumination, expression, 3D, heterogeneous, and matching. Deep learning technique helps to attain superhuman performance and high accuracy in face recognition.
   Still, Image-based Face Recognition (SIFR), Video-based Face Recognition (VFR), Heterogeneous Face Recognition (HFR), Still-to-Video Face Recognition (S2V), NIR-VIS Face Recognition, Sketch-Based Face Recognition (SBFR), Cross-Resolution Face Recognition, 3D based Face Recognition, D-Selfie Face Recognition and Image Set-based Face Recognition (ISFR) are the application tasks of deep learning based face recognition in diverse real-world scenarios.
   Convolutional Neural Networks (CNN), Autoencoder (AE), Generative Adversarial Networks (GAN), Deep Belief Networks (DBN), Restricted Boltzmann Machine (RBM), Deep Boltzmann Machine (DBM), and Recurrent Neural Networks (RNN) are popular deep learning frameworks applied for face recognition. Some of the technical challenges that need more research effort in deep learning enabled face recognition are security issues, privacy-preserving face recognition, understanding deep face recognition, non-saturated benchmark datasets, pervasive face recognition over applications and scenes, and the quest for extreme accuracy and efficiency and fusion issues.
   Diverse studies and surveys have been established in various aspects of face recognition listed below, which presents an overview, face recognition problems, state-of-the-art methodologies under machine learning and deep learning, their advantages, limitations, novel approaches, further development, open challenges, and future directions.