Biometric recognition refers to the use of inherent physiological or behavioral characteristics of human body for personal identification, such as face recognition, fingerprint recognition, and iris recognition. Early technologies are usually based on handcrafted features and traditional machine learning methods, and constrained by data and computing power acquisition ability. Thus, they are generally limited to controlled environment and difficult to build powerful biometric recognition models by making use of large-scale biometric data effectively. In recent years, with the advancement of machine learning, especially deep learning and increasing computing power of GPU, big data based biometric recognition technologies have received widespread attention and have been widely used in the areas such as personal authentication, intelligent video surveillance, and prevention and control of epidemic. This paper summarizes the development of big-data based biometrics technologies, covering different types of biometrics and their applications, and then discusses the trend of big-data based biometrics technologies in the future.

biometric recognition  /  big data driven  /  self-supervised learning  /  universal domain representation  /  artificial intelligence