A lightweight facial expression recognition model for automated engagement detection

Real-time monitoring of students' classroom engagement level is of paramount importance in modern education. Facial expression recognition has been extensively explored in various studies to achieve this goal. However, conventional models often grapple with a high number of parameters and substantial computational costs, limiting their practicality in real-time applications and real-world scenarios. To address this limitation, this paper proposes "Light_Fer," a lightweight model designed to attain high accuracy while reducing parameters. Light_Fer's novelty lies in the integration of depthwise separable convolution, group convolution, and inverted bottleneck structure. These techniques optimize the models' architecture, resulting in superior accuracy with fewer parameters. Experimental results demonstrate that Light_Fer, with just 0.23M parameters, achieves remarkable accuracies of 87.81% and 88.20% on FERPLUS and RAF-DB datasets, respectively. Furthermore, by establishing a correlation between facial expressions and students' engagement levels, we extend the application of Light_Fer to real-time detection and monitoring of students' engagement during classroom activities. In conclusion, the proposed Light_Fer model, with its lightweight design and enhanced accuracy, offers a promising solution for real-time student engagement monitoring through facial expression recognition.