Facial Emotion Recognition via VGG19 and CNN: A Data- Augmented Approach to Broadening Applications
DOI:
https://doi.org/10.54489/ijcim.v5i2.543Keywords:
Facial emotion recognition (FER), Convolutional Neural Networks (CNNs), Facial expressions, Technological Development, Medical-Care, Paralinguistic Communication, CybercrimeAbstract
Facial emotion recognition (FER) has emerged as a significant Research Area within the domains of Computer Vision (CV) and Pattern Recognition (PR). This paper provides a thorough review of recent advancements in FER, focusing particularly on the utilization of Convolutional Neural Networks (CNNs). Facial expressions play a crucial role in Human Communication and Behavior, conveying Emotions, Intentions, and Social Cues. Non-verbal communication, including Facial Expressions, accounts for a substantial portion of overall communication, ranging from 55% to 93%. FER finds applications across Diverse Fields such as Human- Computer Interaction, Surveillance Videos, Expression Analysis, Gesture Recognition, Smart Homes, Computer Games, Detecting Genetic Disorders, Depression/Anxiety Treatment, Patient Monitoring, Lie Detection in Cybercrime or High-Security Organizations, Psychoanalysis, Paralinguistic Communication, Detecting Operator Fatigue, & Robotics etc. This research implements a convolutional neural network (CNN) leveraging the VGG19 architecture for FER, using the FER2013 dataset. Data augmentation and transfer learning techniques were employed to enhance the model’s performance. The final model achieved high accuracy in recognizing seven distinct emotional states: anger, disgust, fear, happiness, sadness, surprise, and neutral. Additionally, the paper discusses emerging Trends and Future directions in FER, highlighting its expanding Applications beyond Traditional Domains.
References
Bartlett, M., Littlewort, G., Vural, E., Lee, K., Cetin, M., Ercil, A., & Movellan, J. (2008). Data mining spontaneous facial behavior with automatic expression coding. In A. Esposito, N. G. Bourbakis, N. Avouris, & I. Hatzilygeroudis (Eds.), Verbal and nonverbal features of human-human and human-machine interaction (pp. 1– 20). Springer. DOI: https://doi.org/10.1007/978-3-540-70872-8_1
Ubaid, M. T., Khalil, M., Khan, M. U. G., Saba, T., & Rehman, A. (2022). Beard and hair detection, segmentation, and changing color using Mask R-CNN. In Proceedings of the International Conference on Information Technology and Applications, Dubai, United Arab Emirates, 13–14 November 2021 (pp. 63–73). Springer. DOI: https://doi.org/10.1007/978-981-16-7618-5_6
Meethongjan, K., Dzulkifli MRehman, A., Altameem, A., & Saba,
T. (2013). An intelligent fused approach for face recognition. Journal of Intelligent Systems, 22(3), 197– DOI: https://doi.org/10.1515/jisys-2013-0010
https://doi.org/10.1515/jisys-2013-0107 Oluwagbemi, O., & Jatto, A. (2019). Implementation of a TCM-
based computational health informatics diagnostic tool for Sub-Saharan African students. Informatics in Medicine Unlocked, 14, 43–58. https://doi.org/10.1016/j.imu.2019.100194 DOI: https://doi.org/10.1016/j.imu.2018.12.002
Oluwagbemi, O., Keshinro, M., & Ayo, C. (2011). Design and implementation of a secured census information management system. Egyptian Computer Science Journal, 35(1), 1–11.
Oluwagbemi, O., Ojutalayo, T., & Obinna, N. (2010). Development of a secured information system to manage malaria-related cases in the southwestern region of Nigeria. Egyptian Computer Science Journal, 34(5), 23–34.
Cheng, D., Zhang, L., Bu, C., Wang, X., Wu, H., & Song, A. (2023). ProtoHAR: Prototype guided personalized federated learning for human activity recognition. IEEE Journal of Biomedical and Health Informatics, 27(8), 3900–3911. https://doi.org/10.1109/JBHI.2023.3205419 DOI: https://doi.org/10.1109/JBHI.2023.3275438
Zafar, B., Ashraf, R., Ali, N., Iqbal, M., Sajid, M., Dar, S., & Ratyal,
N. (2018). A novel discriminating and relative global spatial image representation with applications in CBIR. Applied Sciences, 8(11), 2242. DOI: https://doi.org/10.3390/app8112242
https://doi.org/10.3390/app8112242 DOI: https://doi.org/10.3390/app8112242
Ali, N., Zafar, B., Riaz, F., Dar, S. H., Ratyal, N. I., Bajwa, K. B., Iqbal, M. K., & Sajid, M. (2018). A hybrid geometric spatial image representation for scene classification. PLOS ONE, 13(9), e0203339. DOI: https://doi.org/10.1371/journal.pone.0203339
https://doi.org/10.1371/journal.pone.0203339 DOI: https://doi.org/10.1371/journal.pone.0203339
Ali, N., Zafar, B., Iqbal, M. K., Sajid, M., Younis, M. Y., Dar, S. H., Mahmood, M. T., & Lee, I. H. (2019). Modeling global geometric spatial information for rotation invariant classification of satellite images. PLOS ONE, 14(7), e0214307. DOI: https://doi.org/10.1371/journal.pone.0219833
https://doi.org/10.1371/journal.pone.0214307 DOI: https://doi.org/10.1371/journal.pone.0214307
