Enhancing Facial Expression Analysis Using CNNs: Insights from ML and Deep Learning Comparisons

Volume: 12 | Issue: 1 | Year 2026 | Subscription
International Journal of Image Processing and Pattern Recognition
Received Date: 07/08/2025
Acceptance Date: 07/15/2025
Published On: 2026-02-18
First Page: 23
Last Page: 31

Journal Menu

By: Aashi, Shobhit Jaiswal, and Mandeep.

1 Undergraduate Student, School of Computer Science and Engineering, Galgotias University, Greater Noida, Uttar Pradesh, India
2 Undergraduate Student, School of Computer Science and Engineering, Galgotias University, Greater Noida, Uttar Pradesh, India
3 Faculty, School of Computer Science and Engineering, Galgotias University, Greater Noida, Uttar Pradesh, India

Abstract

Emotion recognition from facial manifestations increases the interaction between humans and computers by enabling the interaction between humans and computers to effectively explain human feelings. This study presents a comparative analysis of three approaches to the emotional recognition of faces: a custom Convolutional Neural Network (CNN) model, Traditional Machine Learning (ML) methods, and other deep learning architectures such as VGG, ResNet, and Hybrid CNN–RNN models. The proposed CNN-based system, developed using TensorFlow and Keras, utilizes interaction layers to extract important features from facial images, achieving 83% accuracy. This paper proposes an adaptive facial emotion recognition system using deep learning techniques. We explore model robustness and real-time response optimization to improve emotion classification performance. In contrast, traditional ML methods, which involve high-dimensional functional extraction, achieved accuracy levels between 70–80%, but with notable limitations and significant emotional changes. Other deep learning models, such as affected CNN, improve both traditional ML and adapted CNN, achieving an accuracy rate of up to 92% by taking advantage of deep architecture and extensive data set growth. Evaluation measurements such as precision, recall, F1 score, and confusion matrices further exposed the difference in emotional classification efficiency. Traditional ML approaches often abuse similar feelings due to overlap, while deep learning models, especially CNN-based frameworks, increase the classification strength. Effective models are distinguished by distinguishing fine emotions but require significant calculation resources.

Loading

Citation:

How to cite this article: Aashi, Shobhit Jaiswal, and Mandeep Enhancing Facial Expression Analysis Using CNNs: Insights from ML and Deep Learning Comparisons. International Journal of Image Processing and Pattern Recognition. 2026; 12(1): 23-31p.

How to cite this URL: Aashi, Shobhit Jaiswal, and Mandeep, Enhancing Facial Expression Analysis Using CNNs: Insights from ML and Deep Learning Comparisons. International Journal of Image Processing and Pattern Recognition. 2026; 12(1): 23-31p. Available from:https://journalspub.com/publication/ijippr/article=26334

Refrences:

  1. Kim BK, Roh J, Dong SY, Lee SY. Hierarchical committee of deep convolutional neural networks for robust facial expression recognition. J Multimodal User Interfaces. 2016;10(2):173–189.
  2. Li S, Deng W. Deep facial expression recognition: A survey. IEEE Trans Affect Comput. 2020;13(3):1195–1215.
  3. Wang C, Zeng J, Shan S, Chen X. Multi-task learning of emotion recognition and facial action unit detection with adaptively weighted sharing network. In: 2019 IEEE International Conference on Image Processing (ICIP); 2019 Sep 22; New York, USA. IEEE; 2019. p. 56–60.
  4. Mehendale N. Facial emotion recognition using convolutional neural networks (FERC). SN Appl Sci. 2020;2(3):446.
  5. Gupta S. Facial emotion recognition in real-time and static images. In: 2018 2nd International Conference on Inventive Systems and Control (ICISC); 2018 Jan 19; Coimbatore, India. IEEE; 2018. p. 553–560.
  6. Wong YJ, Lee KH, Tham ML, Kwan BH. Multi-camera face detection and recognition in unconstrained environment. In: 2023 IEEE World AI IoT Congress (AIIoT); 2023 Jun 7; Seattle, USA. IEEE; 2023. p. 0548–0553.
  7. Büyüktaş B, Erdem ÇE, Erdem T. More learning with less labeling for face recognition. Digit Signal Process. 2023;136:103915.
  8. Zhang G, Zou W, Zhang X, Hu X, Zhao Y. Singular value decomposition based sample diversity and adaptive weighted fusion for face recognition. Digit Signal Process. 2017;62:150–160.
  9. Turabzadeh S, Meng H, Swash RM, Pleva M, Juhar J. Facial expression emotion detection for real-time embedded systems. Technologies. 2018;6(1):10.
  10. Deshmukh RS, Jagtap V, Paygude S. Facial emotion recognition system through machine learning approach. In: 2017 International Conference on Intelligent Computing and Control Systems (ICICCS); 2017 Jun 15; Madurai, India. IEEE; 2017. p. 272–277.
  11. Lim AP, Kusuma GP, Zahra A. Facial emotion recognition using computer vision. In: 2018 Indonesian Association for Pattern Recognition International Conference (INAPR); 2018 Sep 7; Solo, Indonesia. IEEE; 2018. p. 46–50.
  12. Correa E, Jonker A, Ozo M, Stolk R. Emotion recognition using deep convolutional neural networks. Tech Rep IN4015. 2016.
  13. Tian YI, Kanade T, Cohn JF. Recognizing action units for facial expression analysis. IEEE Trans Pattern Anal Mach Intell. 2001;23(2):97–115.
  14. Ekman P, Friesen WV. Constants across cultures in the face and emotion. J Pers Soc Psychol. 1971;17(2):124.
  15. Mollahosseini A, Chan D, Mahoor MH. Going deeper in facial expression recognition using deep neural networks. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV); 2016 Mar 7; New York, USA. IEEE; 2016. p. 1–10.
  16. Nicholson J, Takahashi K, Nakatsu R. Emotion recognition in speech using neural networks. Neural Comput Appl. 2000;9(4):290–296.
  17. Noroozi F, Marjanovic M, Njegus A, Escalera S, Anbarjafari G. Audio-visual emotion recognition in video clips. IEEE Trans Affect Comput. 2017;10(1):60–75.
  18. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016; Las Vegas, USA. IEEE; 2016. p. 770–778.
  19. Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2015; Boston, USA. IEEE; 2015. p. 3431–3440.
  20. Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. In: European Conference on Computer Vision (ECCV); 2014 Sep 6; Cham, Switzerland. Springer; 2014. p. 818–833.
  21. Imani M, Montazer GA. A survey of emotion recognition methods with emphasis on e-learning environments. J Netw Comput Appl. 2019;147:102423.
  22. Goyal P, Pandey S, Jain K. Introduction to natural language processing and deep learning. In: Goyal P, editor. Deep learning for natural language processing: Creating neural networks with Python. 1st ed. Berkeley, USA: Apress; 2018. p. 1–74.
  23. Miikkulainen R, Liang J, Meyerson E, Rawal A, Fink D, Francon O, et al. Evolving deep neural networks. In: Miikkulainen R, editor. Artificial intelligence in the age of neural networks and brain computing. 1st ed. Academic Press; 2024. p. 269–287.

 

 Previous Article
Next Article

Powered by
►
Necessary cookies enable essential site features like secure log-ins and consent preference adjustments. They do not store personal data.
None
►
Functional cookies support features like content sharing on social media, collecting feedback, and enabling third-party tools.
None
►
Analytical cookies track visitor interactions, providing insights on metrics like visitor count, bounce rate, and traffic sources.
None
►
Advertisement cookies deliver personalized ads based on your previous visits and analyze the effectiveness of ad campaigns.
None
Powered by