Facial Micro-Expression Analysis: A Survey of Features and Algorithms

Unlike traditional facial expressions, micro-expressions are unconscious and brief facial expressions that true emotions people try to hide. Therefore, they can provide important information in a wide range of applications, including lie detection and criminal investigations. However, due to their brevity and low intensity, detecting and recognizing micro-expressions is challenging, and micro-expression analysis has become an active research field due to its inherent uniqueness and complexity in recent years. In this review paper, the research on micro-expression analysis is surveyed, including the neuropsychological basis, features, discovery algorithms, recognition algorithms, application and evaluation of state-of- the-art methods. For each aspect, the basic techniques, advanced developments, and key challenges are discussed and analyzed. Finally, some potential future research directions are explored and outlined.