Micro Expression Recognition - Contemporary Challenges, Options and Analysis

Facial expressions are involuntary facial movements that reveal concealed emotions and genuine feelings, which individuals try to hide or mask. These subtle expressions can provide valuable insights into a person's true emotions. The significance of facial micro-expression (MEs) has grown in recent years, owing to its possible uses ranging from the courtroom judgment to the clinical diagnosis. MEs, in contrast to macro-expressions, are transient, brief, and difficult for both people and identification algorithms to identify and interpret. This study provides an overview for MEs recognition systems, including pre-processing, face feature detection and extraction, existing datasets, and classification algorithms. The significance of these features and the methodologies used, as well as the important factors influencing MEs recognition, are highlighted. Additionally, the paper highlights the challenges, unsolved issues, and future research directions in the domain of MEs analysis. The article also asserts that temporal information, dimensionality reduction approaches, and precise MEs detection are important for enhancing recognition accuracy. Furthermore, the paper concludes that MEs recognition is a fascinating and emerging research area with significant potential for practical applications and further advancement in the future.