Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning-Based Facial Expression Recognition for the Elderly: A Systematic Review

F. Xavier Gaya-Morey, Jose M. Buades-Rubio, Philippe Palanque, Raquel Lacuesta, Cristina Manresa-Yee

TL;DR

This systematic review evaluates deep learning–based facial expression recognition (FER) for elderly populations. Analyzing 31 studies from 2015–2024, it finds convolutional neural networks (CNNs) dominate FER pipelines, with lightweight variants enabling deployment on resource-limited devices, yet elderly-specific datasets remain underrepresented and real-world adoption is limited. The review highlights persistent challenges in data imbalance, age-related expression differences, privacy concerns, and a dearth of explainable AI (XAI) approaches. It provides concrete recommendations to develop age-inclusive datasets, embrace multimodal data, and integrate XAI to build trustworthy systems for elderly care, thereby bridging the gap between academic progress and practical deployment.

Abstract

The rapid aging of the global population has highlighted the need for technologies to support elderly, particularly in healthcare and emotional well-being. Facial expression recognition (FER) systems offer a non-invasive means of monitoring emotional states, with applications in assisted living, mental health support, and personalized care. This study presents a systematic review of deep learning-based FER systems, focusing on their applications for the elderly population. Following a rigorous methodology, we analyzed 31 studies published over the last decade, addressing challenges such as the scarcity of elderly-specific datasets, class imbalances, and the impact of age-related facial expression differences. Our findings show that convolutional neural networks remain dominant in FER, and especially lightweight versions for resource-constrained environments. However, existing datasets often lack diversity in age representation, and real-world deployment remains limited. Additionally, privacy concerns and the need for explainable artificial intelligence emerged as key barriers to adoption. This review underscores the importance of developing age-inclusive datasets, integrating multimodal solutions, and adopting XAI techniques to enhance system usability, reliability, and trustworthiness. We conclude by offering recommendations for future research to bridge the gap between academic progress and real-world implementation in elderly care.

Deep Learning-Based Facial Expression Recognition for the Elderly: A Systematic Review

TL;DR

This systematic review evaluates deep learning–based facial expression recognition (FER) for elderly populations. Analyzing 31 studies from 2015–2024, it finds convolutional neural networks (CNNs) dominate FER pipelines, with lightweight variants enabling deployment on resource-limited devices, yet elderly-specific datasets remain underrepresented and real-world adoption is limited. The review highlights persistent challenges in data imbalance, age-related expression differences, privacy concerns, and a dearth of explainable AI (XAI) approaches. It provides concrete recommendations to develop age-inclusive datasets, embrace multimodal data, and integrate XAI to build trustworthy systems for elderly care, thereby bridging the gap between academic progress and practical deployment.

Abstract

The rapid aging of the global population has highlighted the need for technologies to support elderly, particularly in healthcare and emotional well-being. Facial expression recognition (FER) systems offer a non-invasive means of monitoring emotional states, with applications in assisted living, mental health support, and personalized care. This study presents a systematic review of deep learning-based FER systems, focusing on their applications for the elderly population. Following a rigorous methodology, we analyzed 31 studies published over the last decade, addressing challenges such as the scarcity of elderly-specific datasets, class imbalances, and the impact of age-related facial expression differences. Our findings show that convolutional neural networks remain dominant in FER, and especially lightweight versions for resource-constrained environments. However, existing datasets often lack diversity in age representation, and real-world deployment remains limited. Additionally, privacy concerns and the need for explainable artificial intelligence emerged as key barriers to adoption. This review underscores the importance of developing age-inclusive datasets, integrating multimodal solutions, and adopting XAI techniques to enhance system usability, reliability, and trustworthiness. We conclude by offering recommendations for future research to bridge the gap between academic progress and real-world implementation in elderly care.

Paper Structure

This paper contains 26 sections, 5 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Effects of Aging on Facial Expression Recognition
  4. Summary of Previous Reviews
  5. Review Questions
  6. Review Methods
  7. Data sources
  8. Search strategy
  9. Quality assessment
  10. Study selection
  11. Data extraction and synthesis
  12. Results
  13. RQ1. DL techniques for FER in elderly populations
  14. RQ1.1. Deep learning architectures
  15. RQ1.2. Datasets
  16. ...and 11 more sections

Figures (5)

  • Figure 1: Distribution of publications retrieved across the five databases.
  • Figure 2: Number of publications found from 2015 to September 2024 (both included).
  • Figure 3: Summary of the systematic review process: collection of publications from the five databases, duplicate removal, and final study selection.
  • Figure 4: Information extracted from each relevant study.
  • Figure 5: Distribution of FER classes observed in the analyzed studies.