A Real-Time Deep Learning Framework for Classroom Facial Expression Recognition: Performance Optimization and Model Evaluation

Shardha Nand; Siti Haryani Shaikh Ali; Shahrulniza Musa; Mazliham Mohd Su’ud

doi:10.48084/etasr.17088

Authors

Shardha Nand Malaysian Institute of Information Technology, Universiti Kuala Lumpur, Kuala Lumpur, Malaysia
Siti Haryani Shaikh Ali Malaysian Institute of Information Technology, Universiti Kuala Lumpur, Kuala Lumpur, Malaysia
Shahrulniza Musa Malaysian Institute of Information Technology, Universiti Kuala Lumpur, Kuala Lumpur, Malaysia
Mazliham Mohd Su’ud Multimedia University, Persiaran Multimedia, Cyberjaya, Selangor, Malaysia

Volume: 16 | Issue: 3 | Pages: 35523-35528 | June 2026 | https://doi.org/10.48084/etasr.17088

Received: 21 December 2025 | Revised: 9 January 2026, 20 January 2026, and 24 January 2026 | Accepted: 28 January 2026 | Online: 20 April 2026
Corresponding author: Shahrulniza Musa

Abstract

Facial expressions indicate a person’s affective state and can be a significant determinant of cognitive performance. This study proposes a Facial Expression Recognition System (FERS) to detect and analyze students’ real-time emotions, thereby providing teachers with insights. The proposed system was trained and evaluated using eight pretrained models on the CK+ dataset. A comparative analysis indicates that the Xception model achieved the highest accuracy in emotion classification. To improve model performance, the grayscale images in the CK+ dataset were enhanced and used as input to an Xception-based Convolutional Neural Network (CNN), employing 3×3 Conv2D filters with ReLU activation and same-padded layer feature extraction. The model demonstrated excellent performance, achieving an accuracy of 99.34%, a precision of 90%, a recall of 87%, and an F1-score of 88%, confirming the system's reliability and efficiency, applying macro averaging. In conclusion, the proposed Xception-based CNN FERS can accurately recognize students’ emotions, allowing teachers to monitor students' moods in the classroom.

Keywords:

facial emotion recognition, pretrained models, deep learning, Xception, transfer learning

Downloads

Download data is not yet available.

References

W. Strielkowski, V. Grebennikova, A. Lisovskiy, G. Rakhimova, and T. Vasileva, "AI-Driven Adaptive Learning for Sustainable Educational Transformation," Sustainable Development, vol. 33, no. 2, pp. 1921–1947, Apr. 2025.

A. A. Salah and A. El Ali, "Affective User Interfaces," in Handbook of Human Computer Interaction, J. Vanderdonckt, P. Palanque, and M. Winckler, Eds. Cham: Springer Nature Switzerland, 2025, pp. 1–32.

M. Carrasco, C. González-Martín, S. Navajas-Torrente, and R. Dastres, "Level of Agreement between Emotions Generated by Artificial Intelligence and Human Evaluation: A Methodological Proposal," Electronics, vol. 13, no. 20, Oct. 2024, Art. no. 4014.

M. J. A. Dujaili, "Survey on Facial Expressions Recognition: Databases, Features and Classification Schemes," Multimedia Tools and Applications, vol. 83, no. 3, pp. 7457–7478, Jan. 2024.

S. D. Qasim, Beyond the Classroom: Emerging Technologies to Enhance Learning. Book Bazooka Publication, 2024.

A. McIntosh, "Teachers Perception of Student Engagement Using Face-to-Face and Remote Instructional Methods," PhD Dissertation, St. John’s University, New York City, NY, USA, 2025.

M. Kaur and M. Kumar, "Facial Emotion recognition: A comprehensive review," Expert Systems, vol. 41, no. 10, Oct. 2024, Art. no. e13670.

K. Kusano, J. L. Napier, and J. Jost, "The Mismeasure of Culture: When Measurement Invariance Requirements Hinder Social-Psychological Research." PsyArXiv, Mar. 28, 2024.

H. L. Gururaj, B. C. Soundarya, S. Priya, J. Shreyas, and F. Flammini, "A Comprehensive Review of Face Recognition Techniques, Trends, and Challenges," IEEE Access, vol. 12, pp. 107903–107926, 2024.

A. Caruso et al., "Adaptive 360° Video Streaming over a Federated 6G Network: Experimenting In-Network Computing for Enhanced User Experience," in 2024 20th International Conference on Network and Service Management, Prague, Czech Republic, Oct. 2024, pp. 1–7.

N. M. Alruwais and M. Zakariah, "Student Recognition and Activity Monitoring in E-Classes Using Deep Learning in Higher Education," IEEE Access, vol. 12, pp. 66110–66128, 2024.

K. Malta, C. Glickman, K. Hunter, and A. McBride, "Comparing the Impact of Online and In-Person Active Learning in Preclinical Medical Education," BMC Medical Education, vol. 25, no. 1, Mar. 2025, Art. no. 329.

B. Fang, X. Li, G. Han, and J. He, "Facial Expression Recognition in Educational Research from the Perspective of Machine Learning: A Systematic Review," IEEE Access, vol. 11, pp. 112060–112074, 2023.

M. B. Govind, A. S. Humaid, and G. Malu, "Revolutionizing Student Engagement: Real-Time Emotion Detection and Interest Identification in Live Video Streams," in Fifth International Conference on Computing and Network Communications, vol. 1221, S. M. Thampi, V. Chaudhary, A.-S. K. Pathan, K. Ching Li, and D. Krishnaswamy, Eds. Singapore: Springer Nature Singapore, 2025, pp. 409–422.

C. R. Tirkey, "AI-Driven Real-Time Student Monitoring System for Enhancing Engagement, Learning, and Identifying Support Needs in K-12 Classrooms Through Visual Programming," M. S. Thesis, Kent State University, Kent, Ohio, 2025.

A. Imran, R. Ahmed, M. M. Hasan, M. H. U. Ahmed, A. K. M. Azad, and S. A. Alyami, "FaceEngine: A Tracking-Based Framework for Real-Time Face Recognition in Video Surveillance System," SN Computer Science, vol. 5, no. 5, May 2024, Art. no. 609.

R. Grover and S. Bansal, "Optimizing Facial Expression Recognition in Challenging Environment: A Streamlined CNN with Pre-Processing Techniques," Journal of The Institution of Engineers (India): Series B, vol. 106, no. 4, pp. 1329–1348, Aug. 2025.

I. D. Mienye and T. G. Swart, "A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications," Information, vol. 15, no. 12, Nov. 2024, Art. no. 755.

S. Alok, "CK+ Dataset." Kaggle, Apr. 2025, [Online]. Available: https://www.kaggle.com/datasets/shuvoalok/ck-dataset.

T. E. Köksal, "Deep Learning Based Real-Time Sequential Facial Expression Analysis Using Geometric Features," M. S. Thesis, İzmir Institute of Technology, Urla, Türkiye, 2023.

J. A. Ballesteros, G. M. Ramírez., F. Moreira, A. Solano, and C. A. Pelaez, "Facial Emotion Recognition Through Artificial Intelligence," Frontiers in Computer Science, vol. 6, Jan. 2024, Art. no. 1359471.