Transfer Learning for Facial Expression Recognition

Facial expressions reflect psychological states and are crucial for understanding human emotions. Traditional facial expression recognition methods face challenges in real-world healthcare applications due to variations in facial structure, lighting conditions and occlusion. We present a methodology...

Full description

Saved in:
Bibliographic Details
Main Authors: Rajesh Kumar, Giacomo Corvisieri, Tullio Flavio Fici, Syed Ibrar Hussain, Domenico Tegolo, Cesare Valenti
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/4/320
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713841957502976
author Rajesh Kumar
Giacomo Corvisieri
Tullio Flavio Fici
Syed Ibrar Hussain
Domenico Tegolo
Cesare Valenti
author_facet Rajesh Kumar
Giacomo Corvisieri
Tullio Flavio Fici
Syed Ibrar Hussain
Domenico Tegolo
Cesare Valenti
author_sort Rajesh Kumar
collection DOAJ
description Facial expressions reflect psychological states and are crucial for understanding human emotions. Traditional facial expression recognition methods face challenges in real-world healthcare applications due to variations in facial structure, lighting conditions and occlusion. We present a methodology based on transfer learning with the pre-trained models VGG-19 and ResNet-152, and we highlight dataset-specific preprocessing techniques that include resizing images to 124 × 124 pixels, augmenting the data and selectively freezing layers to enhance the robustness of the model. This study explores the application of deep learning-based facial expression recognition in healthcare, particularly for remote patient monitoring and telemedicine, where accurate facial expression recognition can enhance patient assessment and early diagnosis of psychological conditions such as depression and anxiety. The proposed method achieved an average accuracy of 0.98 on the CK+ dataset, demonstrating its effectiveness in controlled environments. However performance varied across datasets, with accuracy rates of 0.44 on FER2013 and 0.89 on JAFFE, reflecting the challenges posed by noisy and diverse data. Our findings emphasize the potential of deep learning-based facial expression recognition in healthcare applications while underscoring the importance of dataset-specific model optimization to improve generalization across different data distributions. This research contributes to the advancement of automated facial expression recognition in telemedicine, supporting enhanced doctor–patient communication and improving patient care.
format Article
id doaj-art-e32805fef2d345a5afc0433dae656d19
institution DOAJ
issn 2078-2489
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-e32805fef2d345a5afc0433dae656d192025-08-20T03:13:51ZengMDPI AGInformation2078-24892025-04-0116432010.3390/info16040320Transfer Learning for Facial Expression RecognitionRajesh Kumar0Giacomo Corvisieri1Tullio Flavio Fici2Syed Ibrar Hussain3Domenico Tegolo4Cesare Valenti5Dipartimento di Matematica e Informatica, Università degli Studi di Palermo, Via Archirafi 34, 90123 Palermo, ItalyItaltel S.p.A., Viale Schiavonetti 270/F, 00173 Rome, ItalyItaltel S.p.A., Viale Schiavonetti 270/F, 00173 Rome, ItalyDipartimento di Matematica e Informatica, Università degli Studi di Palermo, Via Archirafi 34, 90123 Palermo, ItalyDipartimento di Matematica e Informatica, Università degli Studi di Palermo, Via Archirafi 34, 90123 Palermo, ItalyDipartimento di Matematica e Informatica, Università degli Studi di Palermo, Via Archirafi 34, 90123 Palermo, ItalyFacial expressions reflect psychological states and are crucial for understanding human emotions. Traditional facial expression recognition methods face challenges in real-world healthcare applications due to variations in facial structure, lighting conditions and occlusion. We present a methodology based on transfer learning with the pre-trained models VGG-19 and ResNet-152, and we highlight dataset-specific preprocessing techniques that include resizing images to 124 × 124 pixels, augmenting the data and selectively freezing layers to enhance the robustness of the model. This study explores the application of deep learning-based facial expression recognition in healthcare, particularly for remote patient monitoring and telemedicine, where accurate facial expression recognition can enhance patient assessment and early diagnosis of psychological conditions such as depression and anxiety. The proposed method achieved an average accuracy of 0.98 on the CK+ dataset, demonstrating its effectiveness in controlled environments. However performance varied across datasets, with accuracy rates of 0.44 on FER2013 and 0.89 on JAFFE, reflecting the challenges posed by noisy and diverse data. Our findings emphasize the potential of deep learning-based facial expression recognition in healthcare applications while underscoring the importance of dataset-specific model optimization to improve generalization across different data distributions. This research contributes to the advancement of automated facial expression recognition in telemedicine, supporting enhanced doctor–patient communication and improving patient care.https://www.mdpi.com/2078-2489/16/4/320face detectionfacial expression recognitiondeep learning techniques
spellingShingle Rajesh Kumar
Giacomo Corvisieri
Tullio Flavio Fici
Syed Ibrar Hussain
Domenico Tegolo
Cesare Valenti
Transfer Learning for Facial Expression Recognition
Information
face detection
facial expression recognition
deep learning techniques
title Transfer Learning for Facial Expression Recognition
title_full Transfer Learning for Facial Expression Recognition
title_fullStr Transfer Learning for Facial Expression Recognition
title_full_unstemmed Transfer Learning for Facial Expression Recognition
title_short Transfer Learning for Facial Expression Recognition
title_sort transfer learning for facial expression recognition
topic face detection
facial expression recognition
deep learning techniques
url https://www.mdpi.com/2078-2489/16/4/320
work_keys_str_mv AT rajeshkumar transferlearningforfacialexpressionrecognition
AT giacomocorvisieri transferlearningforfacialexpressionrecognition
AT tullioflaviofici transferlearningforfacialexpressionrecognition
AT syedibrarhussain transferlearningforfacialexpressionrecognition
AT domenicotegolo transferlearningforfacialexpressionrecognition
AT cesarevalenti transferlearningforfacialexpressionrecognition