Seeing the Unseen: Real-Time Micro-Expression Recognition with Action Units and GPT-Based Reasoning

This paper presents a real-time system for the detection and classification of facial micro-expressions, evaluated on the CASME II dataset. Micro-expressions are brief and subtle indicators of genuine emotions, posing significant challenges for automatic recognition due to their low intensity, short...

Full description

Saved in:
Bibliographic Details
Main Authors: Gabriela Laura Sălăgean, Monica Leba, Andreea Cristina Ionica
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/12/6417
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434036671348736
author Gabriela Laura Sălăgean
Monica Leba
Andreea Cristina Ionica
author_facet Gabriela Laura Sălăgean
Monica Leba
Andreea Cristina Ionica
author_sort Gabriela Laura Sălăgean
collection DOAJ
description This paper presents a real-time system for the detection and classification of facial micro-expressions, evaluated on the CASME II dataset. Micro-expressions are brief and subtle indicators of genuine emotions, posing significant challenges for automatic recognition due to their low intensity, short duration, and inter-subject variability. To address these challenges, the proposed system integrates advanced computer vision techniques, rule-based classification grounded in the Facial Action Coding System, and artificial intelligence components. The architecture employs MediaPipe for facial landmark tracking and action unit extraction, expert rules to resolve common emotional confusions, and deep learning modules for optimized classification. Experimental validation demonstrated a classification accuracy of 93.30% on CASME II, highlighting the effectiveness of the hybrid design. The system also incorporates mechanisms for amplifying weak signals and adapting to new subjects through continuous knowledge updates. These results confirm the advantages of combining domain expertise with AI-driven reasoning to improve micro-expression recognition. The proposed methodology has practical implications for various fields, including clinical psychology, security, marketing, and human-computer interaction, where the accurate interpretation of emotional micro-signals is essential.
format Article
id doaj-art-306f47c505f34ac190299d05d16d8b8a
institution Kabale University
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-306f47c505f34ac190299d05d16d8b8a2025-08-20T03:26:48ZengMDPI AGApplied Sciences2076-34172025-06-011512641710.3390/app15126417Seeing the Unseen: Real-Time Micro-Expression Recognition with Action Units and GPT-Based ReasoningGabriela Laura Sălăgean0Monica Leba1Andreea Cristina Ionica2Doctoral School, University of Petroșani, 332006 Petrosani, RomaniaSystem Control and Computer Engineering Department, University of Petroșani, 332006 Petrosani, RomaniaManagement and Industrial Engineering Department, University of Petroșani, 332006 Petrosani, RomaniaThis paper presents a real-time system for the detection and classification of facial micro-expressions, evaluated on the CASME II dataset. Micro-expressions are brief and subtle indicators of genuine emotions, posing significant challenges for automatic recognition due to their low intensity, short duration, and inter-subject variability. To address these challenges, the proposed system integrates advanced computer vision techniques, rule-based classification grounded in the Facial Action Coding System, and artificial intelligence components. The architecture employs MediaPipe for facial landmark tracking and action unit extraction, expert rules to resolve common emotional confusions, and deep learning modules for optimized classification. Experimental validation demonstrated a classification accuracy of 93.30% on CASME II, highlighting the effectiveness of the hybrid design. The system also incorporates mechanisms for amplifying weak signals and adapting to new subjects through continuous knowledge updates. These results confirm the advantages of combining domain expertise with AI-driven reasoning to improve micro-expression recognition. The proposed methodology has practical implications for various fields, including clinical psychology, security, marketing, and human-computer interaction, where the accurate interpretation of emotional micro-signals is essential.https://www.mdpi.com/2076-3417/15/12/6417affective computingfacial action coding systememotion classificationhuman-computer interactionmultimodal AI
spellingShingle Gabriela Laura Sălăgean
Monica Leba
Andreea Cristina Ionica
Seeing the Unseen: Real-Time Micro-Expression Recognition with Action Units and GPT-Based Reasoning
Applied Sciences
affective computing
facial action coding system
emotion classification
human-computer interaction
multimodal AI
title Seeing the Unseen: Real-Time Micro-Expression Recognition with Action Units and GPT-Based Reasoning
title_full Seeing the Unseen: Real-Time Micro-Expression Recognition with Action Units and GPT-Based Reasoning
title_fullStr Seeing the Unseen: Real-Time Micro-Expression Recognition with Action Units and GPT-Based Reasoning
title_full_unstemmed Seeing the Unseen: Real-Time Micro-Expression Recognition with Action Units and GPT-Based Reasoning
title_short Seeing the Unseen: Real-Time Micro-Expression Recognition with Action Units and GPT-Based Reasoning
title_sort seeing the unseen real time micro expression recognition with action units and gpt based reasoning
topic affective computing
facial action coding system
emotion classification
human-computer interaction
multimodal AI
url https://www.mdpi.com/2076-3417/15/12/6417
work_keys_str_mv AT gabrielalaurasalagean seeingtheunseenrealtimemicroexpressionrecognitionwithactionunitsandgptbasedreasoning
AT monicaleba seeingtheunseenrealtimemicroexpressionrecognitionwithactionunitsandgptbasedreasoning
AT andreeacristinaionica seeingtheunseenrealtimemicroexpressionrecognitionwithactionunitsandgptbasedreasoning