Nov 2026· Computers· Vol 15, pp. 790· 0 citations· 28 references
TL;DR
A novel hierarchical FER framework that integrates a lightweight PAtt-Lite MobileNetV1 backbone with a divide-and-conquer learning strategy, making it a promising solution for real-time edge deployment in practical HMI scenarios.
Abstract
Facial Expression Recognition (FER) plays a pivotal role in human–machine interaction (HMI), supporting applications such as driver monitoring, healthcare, and intelligent systems. Despite significant progress, real-time FER systems still face critical challenges, particularly reduced accuracy in distinguishing visually similar expressions and high computational complexity that limits deployment on resource-constrained platforms. In this work, we propose a novel hierarchical FER framework that integrates a lightweight PAtt-Lite MobileNetV1 backbone with a divide-and-conquer learning strategy. The proposed architecture adopts a two-stage hierarchical design: a primary lightweight model performs initial emotion classification, while low-confidence predictions are selectively forwarded to specialized binary expert models for refinement. These expert models are trained on commonly confused emotion pairs, enabling enhanced discrimination where it is most needed. By activating expert models only on demand, the framework improves classification performance without incurring substantial computational overhead. Experimental evaluation on the RAF-DB dataset demonstrates strong performance, achieving a validation accuracy of 93.75% ± 0.35% (mean ± standard deviation over five random seeds). On the held-out test set, the primary model achieves 70.00% ± 1.60%, while the hybrid framework improves performance to 70.72% ± 1.37%, all while maintaining real-time operation at approximately 101.6 FPS on CPU-only hardware. Unlike many FER studies that evaluate performance using data distributions involved in training or model selection, this work employs a completely independent external test set that remains isolated from all training, validation, and tuning stages. Consequently, neither the main model nor the expert classifiers encounter these samples during learning, ensuring that the reported results reflect genuine generalization to unseen data and preserving the integrity of the evaluation process, including confidence-threshold and expert-routing optimization. These results highlight the proposed framework’s effectiveness in balancing accuracy, efficiency, and reliable real-world generalization, making it a promising solution for real-time edge deployment in practical HMI scenarios.
A modified MobileNetV2-based lightweight network that integrates Selective Kernel (SK) and Coordinate Attention (CA) modules to enhance feature extraction and spatial awareness while maintaining a low parameter count is proposed.
It is seen that the joint enhancement-recognition models can be more effective in restoring the semantically meaningful features when the light is low, and attention and transformer-based models are more efficient in coping with the occlusion through focusing on informative areas of the faces.
Rajesh Kumar Jha, Brajesh Kumar· International Journal of Dru...· 0 citations
A hybrid model which uses several ResNet50 mixed with VGG16 backbones to improve the local facial features with the global context for a robust FER solu-tion, and shows superior robustness to occlusions and pose, even under cross-dataset testing.
Abderrahim Ouza, Mohamed El Ghmary, A. Choukri· Multimedia tools and applica...· 0 citations
Facial Expression Recognition (FER) is an important component of affective computing and human-computer interaction, yet it is difficult to apply in practice because of the variations in illumination, pose variation, occlusions, low-resolution images, and skew in the classes. To overcome these issues, this paper introd...
Aqeel Majeed Breesam, Roaa Safi Abed Alah, Mina Faris Ali Alnaimy· International journal of ele...· 0 citations
Facial emotion recognition (FER) in e-learning environments faces a persistent tension between recognition performance and deployment efficiency; high-performing architectures typically impose prohibitive computational costs that preclude real-time use on commodity hardware. This paper presents ARECA-Lite, a lightweigh...