Children’s Facial Emotion Recognition using Deep Learning Models

Date Received: 13-10-2025

Date Accepted: 12-03-2026

Date Published: 29-04-2026

##submissions.doi##: https://doi.org/10.31817/tckhnnvn.2026.24.4.08

Views

2

Downloads

1

How to Cite:

Trang, N., Thang, P., & kuong, N. (2026). Children’s Facial Emotion Recognition using Deep Learning Models. Vietnam Journal of Agricultural Sciences, 24(4), 506–513. https://doi.org/10.31817/tckhnnvn.2026.24.4.08

Children’s Facial Emotion Recognition using Deep Learning Models

Nguyen Quynh Trang , Pham Van Thang , Nguyen Trong kuong (*)

  • Tác giả liên hệ: [email protected]

    • Keywords

    Deep learning, convolutional neural networks, facial emotion recognition

    Abstract


    Artificial Intelligence (AI) has been making great strides and is increasingly becoming a useful tool in supporting the solution of complex problems in all areas of life. This study presented the application of convolutional neural networks (CNN) to recognize users' emotional images from videos of children’s activities. The pre-processing and facial recognition process used Multi-Task Cascade Convolutional Network (MTCNN) to detect and recognize faces. MTCNN helps to detect distinctive faces, then provides data to CNN for emotion classification. The dataset used in this study consisted of videos recording the activities of children aged 3 to 5 years old at a preschool. These videos contained emotional images of children in a classroom, they were used to train the learning model to detect how emotional the children express from the videos. As the results, the CNN network achieved 92% accuracy on the training and 95% on the test. The CNN network demonstrated the better learning than conventional neural networks for the same tasks.

    References

    Adam K.D.B.J. (2014). A method for stochastic optimization. 1412(6). ArXiv. 1412.6980. Afolabi I.A., Omolegho A.I., Idama O., Jones U.E. & Michael O.I. (2025). Effective preprocessing techniques for improved facial recognition under variable conditions. Franklin Open. 10: 100225. Ayham F. & Anis Z. (2014). Novel Solution Based on Face Recognition to Address Identity Theft and Cheating in Online Examination Systems, Advances in Internet of Things. Scientific Research. Diederik P.K. & Jimmy Lei Ba (2014). Adam: A method for stochastic optimization. ArXiv. 1412.6980. Ekman P. (2007). Recognizing faces and feelings to improve communication and emotional life. Emotions revealed. Times Books. ISBN 0-8050-7275-6. Ekman P., Davidson R.J. & Friesen W.V. (1990). The Duchenne smile: Emotional expression and brain physiology: II. Journal of Personality and Social Psychology. 58(2): 342-353. Fernández R., Redolat M., Serra R.E. & González A.G. (2021). A systematic review of facial emotion recognition in Alzheimer's disease: A developmental and gender perspective. Anal. Psicol. Iván d.P.C. (2024). Ipazc/mtcnn: v1.0.0., Zenodo. 13901378. Jiahong S., Davy T.K.N. & Samuel K.W.C. (2023). Artificial Intelligence (AI) Literacy in Early Childhood Education: The Challenges and Opportunities. Computers and Education: Artificial Intelligence. 4: 100124. Jyotsna C., Amudha J., Amritanshu R., Giandomenico N. (2023). IntelEye: An Intelligent Tool for the Detection of Stressful State based on Eye Gaze Data While Watching Video, Procedia Computer Science. 218: 1270-1279. LeCun Y., Bengio Y. & Hinton G. (2015). Deep learning. Nature. 521(7553): 436-444. Mase K. (1991). Recognition of facial expression from optical flow. IEICE Transactions. Information and Systems. 74: 3474-3483. Mehrabian A. (1971). Silent Messages (1st ed.). Belmont, CA: Wadsworth. ISBN 0-534-00910-7.