By: Shravani Jadhav, Pratik Kakade, Amar Raut, and Achala Deshmukh
Facial expressions are necessary in human communication and understanding emotions. First and foremost, identifying emotions is a critical factor for many businesses to comprehend how their customers are responding to the things they have introduced. It can also be utilized to find out if the amenities provided to their staff are meeting their needs. Additionally, it has a plethora of other applications, such as utilizing a camera to identify someone’s attitude without having to approach them. Additionally, with little adjustments, the same technique may be used to a variety of different sectors, including face detection, attendance tracking, mask detection, and many more. Detecting facial expressions automatically has significant uses in different platforms, like interaction between human and machines, emotion analysis, or mental health diagnostics. This research focuses on developing a robust and efficient system for facial expression detection using deep learning techniques. The experimental findings show how well the suggested method works to reliably identify and categorize expressions. The system achieves performance on benchmark datasets, showcasing its potential for real-world applications. Additionally, we compare our results with those of conventional machine learning approaches, emphasizing the superior performance of deep learning methods in tasks involving facial emotion identification. This work advances the field of computer vision by offering a sophisticated method for automatic face emotion recognition. The accuracy, resilience, and real time capabilities of the built system make it a useful tool for a variety of applications, such as virtual reality, gaming, healthcare, and customer experience analysis. Facial emotion analysis is effectively employed in surveillance films, expression analysis, gesture recognition, computer games, smart homes, depression treatment, patient monitoring, anxiety, lying detection, psychoanalysis, paralinguistic communication, operator tiredness detection, and robotics.
Keywords: Facial emotion detection, convolutional neural network (CNN), image edge computing, real-time expression detection
Citation:
Refrences:
- Agarwal S, Santra B, Mukherjee DP. Anubhav: recognizing emotions through facial expression. De Visual Computer. 2018; 34 (2): 177–191.
- Pan X, Ying G, Chen G, Li H, Li W. A deep spatial and temporal aggregation framework for video-based facial expression recognition. IEEE Access. 2019; 7: 48807–48815.
- Aneja D, Colburn A, Faigin G, Shapiro L, Mones B. Modeling stylized character expressions via deep learning. In: Lai S-H, Lepetit V, Nishino K, Sato Y, editors. Proceedings of the Asian Conference on Computer Vision. Cham, Switzerland: Springer; 2016. pp. 136–153.
- Zhao S, Cai H, Liu H, Zhang J, Chen S. Feature selection mechanism in CNNs for facial expression recognition. In: Proceedings of the British Machine Vision Conference, Newcastle, UK, September 3–6, 2018.
- Oloyede MO, Hancke GP. Unimodal and multimodal biometric sensing systems: a review. IEEE Access. 2019; 4: 7532–7555.
- Phelps EA. Emotion and cognition: insights from studies of the human amygdala. Annu Rev Psychol. 2020; 57: 27–53.
- Hossain MS, Muhammad G. An audio-visual emotion recognition system using deep learning fusion for a cognitive wireless framework. IEEE Wireless Commun. 2019; 26 (3): 62–68.
- Huo J, Li WB, Shi YH, Gao Y, Yin HJ. WebCaricature: a bench-mark for caricature recognition. arXiv preprint: 1703.03230, 2020. Available at https://arxiv.org/abs/1703.03230
- Jiang C-S, Liu Z-T, Wu M, She J, Cao W-H. Efficient facial ex- pression recognition with representation reinforcement network and transfer self-training for human–machine interaction. IEEE Trans Ind Informatics. 2023; 19 (9): 9943–9952. doi: 10.1109/TII.2022.3233650.
- Rasheed A, San O, Kvamsdal T. Digital twin: values, challenges and enablers from a modeling perspective. IEEE Access. 2020; 8: 21980–22012. doi: 10.1109/ACCESS.2020.2970143.
