Enhancing Precision in Facial Micro- Expression Recognition with Support Vector Machine in Comparison to ELM Algorithm

The primary objective of this study is to develop a new method for recognising facial micro-expressions by comparing the accuracy of the SVM and ELM algorithms. The extreme learning machine (N=10) and support vector machine (N=10) used a sample size of 10 and 20 iterations respectively to identify m...

Full description

Saved in:
Bibliographic Details
Published in2024 Third International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS) pp. 1 - 4
Main Authors Nagalakshmi, T.J., Reddy, Anji
Format Conference Proceeding
LanguageEnglish
Published IEEE 14.03.2024
Subjects
Accuracy
Emotions
Extreme learning machine (ELM)
Extreme learning machines
Face recognition
Machine learning
Machine learning algorithms
Micro-expressions
Signal processing
Signal processing algorithms
Support vector machine (SVM)
Support vector machines
Training
Online AccessGet full text

Cover

More Information
Summary:The primary objective of this study is to develop a new method for recognising facial micro-expressions by comparing the accuracy of the SVM and ELM algorithms. The extreme learning machine (N=10) and support vector machine (N=10) used a sample size of 10 and 20 iterations respectively to identify micro expressions with g power of 80%, limit of 0.608, and confidence stretch of 95%. In comparison to extreme learning machines, which have an accuracy of 91.0%, support vector machines will deliver superior exactness (94.8 % ). The difference in statistical significance, p = 0.608 (p<0.05), According to the free example T -test value, the study's findings are not statistically significant. When it comes to detecting facial micro-expressions, support vector machine algorithms outperform extreme learning machine methods in terms of accuracy.
DOI:10.1109/INCOS59338.2024.10527633