Abstract
Facial micro-expression(ME) recognition has great significance for the progress of human society and could find a person's true feelings. Meanwhile, ME recognition faces a huge challenge, since it is difficult to detect and easy to be disturbed by the environment. In this article, we propose two novel preprocessing methods based on Pixel Residual Sum. These methods can preprocess video clips according to the unit pixel displacement of images, resist environmental interference, and be easy to extract subtle facial features. Furthermore, we propose a Cropped Gaussian Pyramid with Overlapping(CGPO) module, which divides images of different resolutions through Gaussian pyramids and crops different resolutions images into multiple overlapping subplots. Then, we use a convolutional neural networks of progressively increasing channels based on the depthwise convolution to extract preliminary features. Finally, we fuse preliminary features and make position embedding to get the last features. Our experiments show that the proposed methods and model have better performance than the well-known methods.
Highlights
Facial expression is a crucial channel for interpersonal socializing and can be used to convey inner emotions in daily life
Ekman and Paul tried a lot of efforts to improve the ability of individuals to recognize the ME, and they developed a tool for ME recognition in 2002 Micro Expression Training Tool (METT) (Ekman, 2009a), which can effectively improve the individual’s ability to recognize ME
The structure of the study is as follows: In Section II, the pieces of literature related to ME recognition are reviewed in detail; In Section III, a preprocessing method and network framework for ME recognition are proposed; In Section IV, we describe the experimental settings and analyze the experimental results; Section V summarizes this study with remarks
Summary
Facial expression is a crucial channel for interpersonal socializing and can be used to convey inner emotions in daily life. ME is an unconscious and involuntary facial expression appearing when people disguise one’s emotions and can be triggered in high-risk environments and show real or hidden emotions. ME usually needs to be analyzed in the video clip, and macro-expression can be analyzed in the image. Due to these characteristics, it is difficult to recognize the ME artificially. Ekman and Paul tried a lot of efforts to improve the ability of individuals to recognize the ME, and they developed a tool for ME recognition in 2002 Micro Expression Training Tool (METT) (Ekman, 2009a), which can effectively improve the individual’s ability to recognize ME. We design a network with feature fusion, and the network structure adopts a gradual way of increasing channels
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.