Automatic face recognition (AFR) is an increasingly popular field of computer technology research at present. It is widely applicable to daily life, with uses such as face access control systems, intelligent monitoring systems, human-computer interaction systems, and safe driving systems. In the future there will be more potential applications requiring a fully reliable AFR system. Therefore, the technology of the AFR system must be more mature in order to be widely used in practice.

AFR is a challenging task in the field of pattern recognition. In the past few decades, AFR technologies have achieved significant research results, which can be divided into three categories: intensity image-based algorithms, video-based algorithms, and 3D facial information-based algorithms. However, there are still many challenges to be faced in practical application. Natural factors of low resolution, expression and illumination changes, pose changes and occlusion will reduce the face recognition accuracy. In addition, there are facial expression recognition challenges in human-computer interaction, electronic health, and safe driving systems. There are also face recognition issues related to underlying computing machines, such as embedded systems, GPU servers, and systems with limited resources. In order to solve these problems and make AFR systems more reliable, further study is needed.

This Special Issue aims to provide a platform for researchers to study and develop novel automatic face recognition approaches. It aims to present state-of-the-art theories related to automatic face recognition and develop novel methods and applications to improve face recognition accuracy in diverse scenarios. We also aim to propose innovative applications of machine learning in face recognition and survey the recent progress in this field. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

• Automatic face recognition, detection, and tracking
• Face description
• Face attributes recognition (including age and gender)
• Face reconstruction
• Face parsing
• Facial expression recognition
• Machine learning, deep learning, and continuous learning in automatic face recognition
• Transformer neural networks in automatic face recognition
• Transfer learning, multitask learning, cross-domain feature learning, and reinforcement learning in automatic face recognition