Hybrid Deep Feature Fusion for Facial Emotion Recognition Using VGG19 and ResNet152V2

Shivani Singh; Jay Kumar Pandey

doi:10.55524/ijircst.2026.14.2.10

Abstract

Facial Emotion Recognition (FER) has become an area of research in human-computer interaction and affective computing. This study presents a deep learning-based FER framework that can recognize facial emotions in both controlled and real-world environments. The proposed method uses an architecture that brings together VGG19 and ResNet152V2 to make use of their different feature learning strengths. VGG19 helps to pick up spatial and texture information while ResNet152V2 focuses on pulling out deeper semantic representations through residual learning. A full preprocessing pipeline, including normalization, resizing and techniques like rotation and flipping is used to improve robustness against changes in lighting pose variations and class imbalance. The effective framework is tested using two datasets, CK+ and FER2013. The experimental results show that the combined model consistently outperforms baseline architectures. On CK+ it achieves a classification accuracy of 98.0%. On FER2013 it achieves 92.0% along with good precision, recall and F1-score. The results show that combining features at the feature level greatly improves the framework ability to generalize. This makes the proposed framework suitable for FER applications and can be used in various applications.

Keywords

Deep Learning, Facial Emotion Recognition, Transfer Learning, Computer Vision, VGG-19, ResNet152V2.

References

N. Siyad et al., “Comparison and analysis of deep neural networks in facial expression recognition,” ResearchGate. Available from: https://doi.org/10.54254/2755-2721/21/20231122
T. Ahmed and R. A. Rahman, “Four-layer ConvNet for facial emotion recognition with minimal epochs and the significance of data diversity,” Scientific Reports. Available from: https://doi.org/10.1038/s41598-022-11173-0
Hassan et al., “A survey on facial expression recognition using deep learning and explainable artificial intelligence,” IJRTI. Available from: https://www.ijrti.org/papers/IJRTI2207297.pdf
S. Singh and J. K. Pandey, “Facial emotion recognition: An efficient CNN approach,” in Proc. 2025 1st IEEE Uttar Pradesh Section WIE Int. Conf. Electrical, Electronics and Computer Engineering (UPWIECON), Dehradun, India, 2025, pp. 442–447. Available from: https://doi.org/10.1109/UPWIECON67212.2025.1139010
S. Singh and J. K. Pandey, “Enhancing real-time surveillance video analysis with AI-powered deep learning techniques,” in AI and Deep Learning Enabled Surveillance System Using Image Processing, J. K. Pandey, M. Rai, and F. Ahmad, Eds., 2026. Available from: https://doi.org/10.1108/978-1-80592-815-720261006
S. Singh, J. K. Pandey, et al., “Machine and deep learning techniques for emotion detection,” in Advancements in Facial Expression Recognition Using Machine and Deep Learning Techniques, M. Rai and J. K. Pandey, Eds. IGI Global, 2023. Available from: https://doi.org/10.4018/979-8-3693-4143-8
J. K. Pandey, D. Bhuva, A. Bhuva, S. H. Abbas, A. Verma, and T. T. Moharekar, “Classification and clustering of Internet of Things (IoT) for integrating IoT services platform,” in Proc. 2023 IEEE 2nd Int. Conf. Industrial Electronics: Developments & Applications (ICIDeA), Imphal, India, 2023, p. 25. Available from: https://ieeexplore.ieee.org/abstract/document/10295225
I. Sumaya et al., “Comparative analysis of AlexNet, GoogLeNet, VGG19, ResNet152V2-50, and ResNet152V2-101 for improved plant disease detection,” in Proc. 2024 2nd Int. Conf. Artificial Intelligence, Blockchain, and Internet of Things (AIBThings), 2024, pp. 1–6. Available from: https://ieeexplore.ieee.org/abstract/document/10863407
S. Mascarenhas and M. Agarwal, “A comparison between VGG16, VGG19 and ResNet152V2 architecture frameworks for image classification,” in Proc. 2021 Int. Conf. Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON), 2021, pp. 96–99. Available from: https://ieeexplore.ieee.org/abstract/document/9687944
Paulchamy, A. Yahya, N. Chinnasamy, and K. Kasilingam, “Facial expression recognition through transfer learning: Integration of VGG16, ResNet152V2, and AlexNet with a multiclass classifier,” Acadlore Trans. AI Mach. Learn., vol. 4, no. 1, pp. 25–39, 2025. Available from: https://doi.org/10.56578/ataiml040103
R. Kumar et al., “Transfer learning for facial expression recognition,” Information, vol. 16, no. 4, p. 320, 2025. Available from: https://doi.org/10.3390/info16040320
M. Tan and Q. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. Int. Conf. Machine Learning (ICML), 2019, pp. 6105–6114. Available from: https://proceedings.mlr.press/v97/tan19a.html?ref=ji
S. Singh, M. Rai, et al., “Emotional intelligence and collaborative dynamics in Industry 5.0 for human–machine interactions,” in Human-Machine Collaboration and Emotional Intelligence in Industry 5.0, IGI Global, 2024. Available from: https://doi.org/10.4018/979-8-3693-6806-0
Dhabliya et al., “Using machine learning to detect emotions and predict human psychology,” in Ethical Considerations in Emotion Data Collection and IoT Integration, IGI Global, 2024, pp. 52–74. Available from: https://doi.org/10.4018/979-8-3693-1910-9
H. A. Santoso et al., “Comparative analysis of convolutional neural network and DenseNet121 transfer learning in agriculture focusing on crop leaf disease identification,” Applied Computing and Informatics, 2024. Available from: https://doi.org/10.1108/ACI-03-2024-0132
H. Ge, Z. Zhu, Y. Dai, B. Wang, and X. Wu, “Facial expression recognition based on deep learning,” Computer Methods and Programs in Biomedicine, vol. 215, p. 106621, 2022. Available from: https://doi.org/10.1016/j.cmpb.2022.106621

Cites this article as

S. Singh, J. K. Pandey, "Hybrid Deep Feature Fusion for Facial Emotion Recognition Using VGG19 and ResNet152V2", International Journal of Innovative Research in Computer Science and Technology (IJIRCST), Vol-14, Issue-2, Page No-74-80, 2026. Available from: https://doi.org/10.55524/ijircst.2026.14.2.10

Corresponding Author

Shivani Singh

Research Scholar, Department of Electrical and Electronics Engineering, Shri Ramswaroop Memorial University, Lucknow Deva Road, Barabanki, Uttar Pradesh, India

Download Full Paper

Download PDF

No. of Downloads: 11 | No. of Views: 224

Hybrid Photonic–Electronic Data Processing Architecture for Ultra-Fast Signal Transmission in Intelligent Embedded Systems

Khushbu Yadav, Aashu Kori.

May 2026 - Vol 14, Issue 3
Integrated Framework for Design & Testing of a Low-Solidity Vertical Axis Water Turbine for Renewable Micro-Hydro Applications

Saba Irum, Saram Abbas, Muhammad Ibraheem.

May 2025 - Vol 13, Issue 3
Hybrid Active Power Filter for Power Quality Improvement

B. Vijay Chandra, SK. Jani Basha, SK. Abdul Rasool, P. Hari Krishna, R. Veda Kumar, CH. Srinivas, K. SowjanKumar, G.V.K. Murthy.

July 2022 - Vol 10, Issue 4

Hybrid Deep Feature Fusion for Facial Emotion Recognition Using VGG19 and ResNet152V2

Citations

Download Full Paper PDF

Total View 224

Total Download 11