Micro-expression recognition: an updated review of current trends, challenges and solutions

Micro-expression (ME) recognition has attracted numerous interests within the computer vision circle in different contexts particularly, localization, magnification, and recognition. Challenges in these areas remain relevant due to the nature of ME’s split-second transition with minute intensity lev...

Full description

Saved in:
Bibliographic Details
Published in:The Visual computer 2020-03, Vol.36 (3), p.445-468
Main Authors: Goh, Kam Meng, Ng, Chee How, Lim, Li Li, Sheikh, U. U.
Format: Article
Language:English
Subjects:
Accuracy
Artificial Intelligence
Cameras
Computer Graphics
Computer Science
Computer vision
Datasets
Emotions
Ethnicity
Happiness
Image Processing and Computer Vision
Performance evaluation
Recognition
Survey
Trends
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Micro-expression (ME) recognition has attracted numerous interests within the computer vision circle in different contexts particularly, localization, magnification, and recognition. Challenges in these areas remain relevant due to the nature of ME’s split-second transition with minute intensity levels. In this paper, a comprehensive state-of-the-art analysis of ME recognition and detection challenges are provided. Contemporary solutions are categorized into low-level, mid-level, and high-level solutions with a review of their characteristics and performances. This paper also provides possible extensions to basic methods, highlight, and predict emerging trends. A thorough analysis of mainstream ME datasets is also provided by elucidating each of their advantages and limitations. This survey gives readers an understanding of ME recognition and an appreciation of future research direction in ME recognition systems.
ISSN:0178-2789
1432-2315
DOI:10.1007/s00371-018-1607-6