Facial Expression Recognition with YOLOv11 and YOLOv12: A Comparative Study

TL;DR

This study compares lightweight YOLOv11n and YOLOv12n models for facial expression recognition, evaluating their performance on benchmark datasets to understand their effectiveness in real-world and controlled environments.

Contribution

It provides a comparative analysis of two nano YOLO models for FER, highlighting their strengths and trade-offs in sensitivity and precision across different datasets.

Findings

YOLOv12n achieves 95.6 mAP on KDEF.

YOLOv11n shows higher precision (65.2) on FER2013.

Both models effectively balance performance and efficiency.

Abstract

Facial Expression Recognition remains a challenging task, especially in unconstrained, real-world environments. This study investigates the performance of two lightweight models, YOLOv11n and YOLOv12n, which are the nano variants of the latest official YOLO series, within a unified detection and classification framework for FER. Two benchmark classification datasets, FER2013 and KDEF, are converted into object detection format and model performance is evaluated using mAP 0.5, precision, recall, and confusion matrices. Results show that YOLOv12n achieves the highest overall performance on the clean KDEF dataset with a mAP 0.5 of 95.6, and also outperforms YOLOv11n on the FER2013 dataset in terms of mAP 63.8, reflecting stronger sensitivity to varied expressions. In contrast, YOLOv11n demonstrates higher precision 65.2 on FER2013, indicating fewer false positives and better reliability in noisy, real-world conditions. On FER2013, both models show more confusion between visually similar expressions, while clearer class separation is observed on the cleaner KDEF dataset. These findings underscore the trade-off between sensitivity and precision, illustrating how lightweight YOLO models can effectively balance performance and efficiency. The results demonstrate adaptability across both controlled and real-world conditions, establishing these models as strong candidates for real-time, resource-constrained emotion-aware AI applications.