LightEmoNet: Lightweight Deep Learning for Facial Emotion Recognition
DOI:
https://doi.org/10.62671/perfect.v3i1.273Keywords:
Facial Emotion Recognition, Lightweight CNN, Data Augmentation, Class Imbalance, Real-Time InferenceAbstract
Facial emotion recognition (FER) is a critical component of human-computer interaction, affective computing, and intelligent surveillance systems. Existing deep learning approaches, while achieving high accuracy, are often computationally expensive and unsuitable for deployment on resource-constrained or real-time systems. In this paper, we present LightEmoNet, a lightweight Convolutional Neural Network (CNN) architecture specifically designed for efficient and accurate facial emotion recognition. Our model is trained on the FER2013 benchmark dataset, which contains 35,887 grayscale images distributed across seven emotion classes: Happy, Neutral, Sad, Fear, Angry, Surprise, and Disgust. To address the inherent class imbalance within the dataset, we employ a dual strategy combining class-weighted loss penalization with targeted data augmentation applied selectively to underrepresented categories. The proposed architecture totals approximately 2.1 million trainable parameters and occupies only 8.3 MB on disk, making it deployable on edge and embedded platforms without GPU acceleration. Experimental results demonstrate that LightEmoNet achieves a training accuracy of 91.0% and a validation accuracy of 88.5% on the FER2013 test split, with an average inference latency of 4.2 ms per image on a standard CPU. The model exhibits robust performance across all seven emotion classes while maintaining a compact footprint suitable for real-time inference. These findings confirm that lightweight CNNs, when paired with principled augmentation strategies, can achieve competitive performance without the overhead of large-scale deep models.
References
Chou, Y., Lin, C., & Kuo, C. (2018). Emotion recognition from imbalanced facial expression datasets. Proceedings of the British Machine Vision Conference (BMVC), 1–12.
Ekman, P., & Friesen, W. V. (1978). Facial action coding system: A technique for the measurement of facial movement. Consulting Psychologists Press.
Farzaneh, A. H., & Qi, X. (2021). Facial expression recognition in the wild via deep attentive center loss. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2402–2411.
Goodfellow, I. J., Erhan, D., Carrier, P. L., Courville, A., Mirza, M., Hamner, B., Cukierski, W., Tang, Y., Thaler, D., Lee, D. H., Zhou, Y., Ramaiah, C., Feng, F., Li, R., Wang, X., Athanasakis, D., Shawe-Taylor, J., Milakov, M., Park, J., ... Bengio, Y. (2013). Challenges in representation learning: A report on three machine learning contests. In Z. Li, J. Li, & Z. Zhou (Eds.), Neural information processing: 20th international conference (Vol. 8228, pp. 117–124). Springer.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. https://doi.org/10.1109/CVPR.2016.90
Jabbooree, A. I., Alkaabi, H., & Kamber, A. N. (2025). Facial expression recognition using fused features: a comparison of deep and machine learning. Journal of Computer Networks, Architecture and High Performance Computing, 7(3), 684-699.
Khaireddin, Y., & Chen, Z. (2021). Facial emotion recognition: State of the art performance on FER2013. arXiv preprint arXiv:2105.03588. https://doi.org/10.48550/arXiv.2105.03588
Li, S., & Deng, W. (2020). Deep facial expression recognition: A survey. IEEE Transactions on Affective Computing, 13(3), 1195–1215. https://doi.org/10.1109/TAFFC.2020.2981446
Li, Y., Zeng, J., Shan, S., & Chen, X. (2017). Occlusion aware facial expression recognition using CNN with attention mechanism. IEEE Transactions on Image Processing, 28(5), 2439–2450. https://doi.org/10.1109/TIP.2019.2890895
Ma, F., Sun, B., & Li, S. (2021). Facial expression recognition with visual transformers and attentional selective fusion. IEEE Transactions on Affective Computing, 14(2), 1236–1248. https://doi.org/10.1109/TAFFC.2021.3122146
Mollahosseini, A., Chan, D., & Mahoor, M. H. (2016). Going deeper in facial expression recognition using deep neural networks. Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 1–10. https://doi.org/10.1109/WACV.2016.7477450
Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. Proceedings of the International Conference on Learning Representations (ICLR), 1–14. https://doi.org/10.48550/arXiv.1409.1556
Tang, Y. (2013). Deep learning using linear support vector machines. arXiv preprint arXiv:1306.0239. https://doi.org/10.48550/arXiv.1306.0239
Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 511–518. https://doi.org/10.1109/CVPR.2001.990517
Wang, K., Peng, X., Yang, J., Lu, S., & Qiao, Y. (2020). Suppressing uncertainties for large-scale facial expression recognition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6897–6906. https://doi.org/10.1109/CVPR42600.2020.00693
Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016). A discriminative feature learning approach for deep face recognition. European Conference on Computer Vision (ECCV), 499–515. https://doi.org/10.1007/978-3-319-46478-7_31
Xue, F., Wang, Q., & Guo, G. (2022). Transfer learning with pose-based part attention for facial action unit recognition. IEEE Transactions on Image Processing, 30, 4450–4460. https://doi.org/10.1109/TIP.2021.3072037
Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (1998). Joint face detection and alignment using multi-task cascaded convolutional networks. IEEE Signal Processing Letters, 23(10), 1499–1503.
Zhang, Y., Wang, C., Deng, W., & Yin, B. (2019). Lightweight network for real-time facial expression recognition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 1–9.
Zhang, Y., Wang, C., Ling, X., & Deng, W. (2022). Learn from all: Towards benefited semantic learning with multi-task adversarial network for facial expression recognition. IEEE Transactions on Circuits and Systems for Video Technology, 32(7), 4604–4617. https://doi.org/10.1109/TCSVT.2021.3127649
Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2021). Unpaired image-to-image translation using cycle-consistent adversarial networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(12), 4500–4515. https://doi.org/10.1109/TPAMI.2020.3038572
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ali Nadhim Kamber, Hussein Alaa Alkaabi (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
