Real-Time Lightweight Emotional Face Recognition Framework Based on CNN Algorithms
DOI:
https://doi.org/10.31185/wjps.975Keywords:
Face recognition, Lightweight face detection, Pattern Recognition, Real-Time SystemsAbstract
In this study, emotional face recognition uses the CNN algorithm. CNN is employed because of its ability to process local tissue and high-resolution connections. This design is planned to authenticate emotion scores for real-time and user-friendly implementations. The preliminary work begins in the neighboring part of the study. Software is utilized to preprocess the data in this study. A CNN model is created using a framework. The process consists of three phases: preprocessing, classifying, and evaluating data. The system was tested on several datasets. The lightweight CNN's performance for training and testing images showed approximately 88.67%. The performance of the system was also compared with existing methods. The research highlights the CNN model's ability to provide state-of-the-art performance in real-time applications, with potential implications for medical and safety applications. However, limitations such as data imbalance and a lack of multimodal approaches were identified for future exploration.
References
[1] J. S. Morton, B. Rimé, G. Herman, D. Bourguignon, and O. Luminet, “Towards an interdisciplinary consensual measure of social participation: From scoping review to clustering measurement,” Int. Rev. Soc. Psychol., vol. 37, no. 1, 2024.
[2] G. Tonguç, “Effect of distance education courses held in different environments on emotions of the instructor,” PLoS One, vol. 19, no. 1, p. e0295935, 2024.
[3] S. Meng et al., “Security-aware dynamic scheduling for real-time optimization in cloud-based industrial applications,” IEEE Trans. Ind. Informatics, vol. 17, no. 6, pp. 4219–4228, 2020.
[4] V. Skaramagkas et al., “Review of eye tracking metrics involved in emotional and cognitive processes,” IEEE Rev. Biomed. Eng., vol. 16, pp. 260–277, 2021.
[5] R. Rishab, G. Sumathi, A. Mohanty, and K. C. Sriharipriya, “Harnessing IoT and CNNs for Real-Time Emotion Recognition and Positive Reinforcement,” in 2025 1st International Conference on AIML-Applications for Engineering & Technology (ICAET), IEEE, 2025, pp. 1–5.
[6] Y. Yaddaden, “Efficient Dynamic Emotion Recognition from Facial Expressions using Statistical Spatio-Temporal Geometric Features,” Big Data Cogn. Comput., vol. 9, no. 8, p. 213, 2025.
[7] J. H. Joloudari, M. Maftoun, B. Nakisa, R. Alizadehsani, and M. Yadollahzadeh-Tabari, “Complex Emotion Recognition System using basic emotions via Facial Expression, EEG, and ECG Signals: a review,” arXiv Prepr. arXiv2409.07493, 2024.
[8] S. Schindler and F. Bublatzky, “Attention and emotion: An integrative review of emotional face processing as a function of attention,” Cortex, vol. 130, pp. 362–386, 2020.
[9] M. Marini, A. Ansani, F. Paglieri, F. Caruana, and M. Viola, “The impact of facemasks on emotion recognition, trust attribution and re-identification,” Sci. Rep., vol. 11, no. 1, p. 5577, 2021.
[10] R. R. Devaram, G. Beraldo, R. De Benedictis, M. Mongiovì, and A. Cesta, “LEMON: a lightweight facial emotion recognition system for assistive robotics based on dilated residual convolutional neural networks,” Sensors, vol. 22, no. 9, p. 3366, 2022.
[11] J. Costa, “Mixed Methods in Educational Large-Scale Studies: Integrating Qualitative Perspectives into Secondary Data Analysis,” Educ. Sci., vol. 14, no. 12, p. 1347, 2024.
[12] S. Lee, N. Lee, T. J. Lee, and S. S. Hyun, “The influence of social support from intermediary organizations on innovativeness and subjective happiness in community-based tourism,” J. Sustain. Tour., vol. 32, no. 4, pp. 795–817, 2024.
[13] K. S. Al-Omoush, M. Orero-Blat, and D. Ribeiro-Soriano, “The role of sense of community in harnessing the wisdom of crowds and creating collaborative knowledge during the COVID-19 pandemic,” J. Bus. Res., vol. 132, pp. 765–774, 2021.
[14] N. Singh, “Keun Lee, Distinguished Professor of Economics, Seoul National University, Seoul, South Korea and Editor, Research Policy”.
[15] N. T. Nguyen, A. Collins, and C. M. Collins, “Revealing the value and feedback dynamics of green space co-design through causal loop diagrams,” npj Urban Sustain., vol. 5, no. 1, p. 76, 2025.
[16] J. Lee et al., “Influences on user engagement in online professional learning: A narrative synthesis and meta-analysis,” Rev. Educ. Res., vol. 91, no. 4, pp. 518–576, 2021.
[17] M. Boston et al., “Community resilience: A multidisciplinary exploration for inclusive strategies and scalable solutions,” Resilient Cities Struct., vol. 3, no. 1, pp. 114–130, 2024.
[18] B. H. Kothari, C. Fischer, N. Mullican, S. T. Lipscomb, and J. Jaramillo, “Interagency collaboration among community organizations serving children and families in child welfare,” J. Community Appl. Soc. Psychol., vol. 32, no. 6, pp. 1115–1132, 2022.
[19] R. Johnson et al., “Global service-learning: A systematic review of principles and practices,” 2021.
[20] B. Alankar, M. S. Ammar, and H. Kaur, “Facial emotion detection using deep learning and Haar Cascade Face Identification algorithm,” in Advances in Intelligent Computing and Communication: Proceedings of ICAC 2020, Springer, 2021, pp. 163–180.
[21] N. Bukhari, S. Hussain, M. Ayoub, Y. Yu, and A. Khan, “Deep learning based framework for emotion recognition using facial expression,” Pakistan J. Eng. Technol., vol. 5, no. 3, pp. 51–57, 2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Suryanti Awang, MOHAMMED AHMED TALAB
This work is licensed under a Creative Commons Attribution 4.0 International License.
