Psychological activity data classification based on micro-expression recognition

Real-time classification of psychological activity is crucial for various applications, and micro-expression recognition has emerged as a promising approach. In this study, an innovative approach is presented to classify psychological activity data using micro-expression recognition. The study first...

Full description

Saved in:
Bibliographic Details
Published in2024 Second International Conference on Inventive Computing and Informatics (ICICI) pp. 651 - 656
Main Author Zhou, Mengxuan
Format Conference Proceeding
LanguageEnglish
Published IEEE 11.06.2024
Subjects
Accuracy
Data classification
Emotion detection
Feature extraction
Histograms
Micro-expression recognition
Psychological activity
Psychological analysis
Psychology
Reviews
Robustness
Solids
Online AccessGet full text

Cover

More Information
Summary:Real-time classification of psychological activity is crucial for various applications, and micro-expression recognition has emerged as a promising approach. In this study, an innovative approach is presented to classify psychological activity data using micro-expression recognition. The study first reviews the theoretical foundations of face recognition and then details the proposed algorithm, focusing on feature extraction using the Histogram of Oriented Gradients (HOG) method. This study also introduces a novel enhancement method called the cutout module to increase data diversity and improve network generalization. In addition, the study uses the Ghost module to optimize feature processing and proposes a centroid-based upsampling algorithm to handle unbalanced data. Experimental results on the Fer2013 dataset demonstrate the effectiveness and robustness of the proposed approach, achieving improved recognition accuracy. This study highlights the potential of micro-expression recognition for psychological activity classification.
DOI:10.1109/ICICI62254.2024.00111